|
on Big Data |
| By: | Jens Ludwig; Sendhil Mullainathan; Ashesh Rambachan |
| Abstract: | Large language models (LLMs) are being used in economics research to form predictions, label text, simulate human responses, generate hypotheses, and even produce data for times and places where such data don't exist. While these uses are creative, are they valid? When can we abstract away from the inner workings of an LLM and simply rely on their outputs? We develop an econometric framework to answer this question. Our framework distinguishes between two types of empirical tasks. Using LLM outputs for prediction problems (including hypothesis generation) is valid under one condition: no "leakage" between the LLM's training dataset and the researcher's sample. Using LLM outputs for estimation problems to automate the measurement of some economic concept (expressed by some text or from human subjects) requires an additional assumption: LLM outputs must be as good as the gold standard measurements they replace. Otherwise estimates can be biased, even if LLM outputs are highly accurate but not perfectly so. We document the extent to which these conditions are violated and the implications for research findings in illustrative applications to finance and political economy. We also provide guidance to empirical researchers. The only way to ensure no training leakage is to use open-source LLMs with documented training data and published weights. The only way to deal with LLM measurement error is to collect validation data and model the error structure. A corollary is that if such conditions can't be met for a candidate LLM application, our strong advice is: don't. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.07031 |
| By: | Nick Huntington-Klein; Eleanor J. Murray |
| Abstract: | Large language models (LLMs) offer the potential to automate a large number of tasks that previously have not been possible to automate, including some in science. There is considerable interest in whether LLMs can automate the process of causal inference by providing the information about causal links necessary to build a structural model. We use the case of confounding in the Coronary Drug Project (CDP), for which there are several studies listing expert-selected confounders that can serve as a ground truth. LLMs exhibit mediocre performance in identifying confounders in this setting, even though text about the ground truth is in their training data. Variables that experts identify as confounders are only slightly more likely to be labeled as confounders by LLMs compared to variables that experts consider non-confounders. Further, LLM judgment on confounder status is highly inconsistent across models, prompts, and irrelevant concerns like multiple-choice option ordering. LLMs do not yet have the ability to automate the reporting of causal links. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.10635 |
| By: | Anton Korinek |
| Abstract: | Large language models (LLMs) have seen remarkable progress in speed, cost efficiency, accuracy, and the capacity to process larger amounts of text over the past year. This article is a practical guide to update economists on how to use these advancements in their research. The main innovations covered are (i) new reasoning capabilities, (ii) novel workspaces for interactive LLM collaboration such as Claude's Artifacts, ChatGPT's Canvas or Microsoft's Copilot, and (iii) recent improvements in LLM-powered internet search. Incorporating these capabilities in their work allows economists to achieve significant productivity gains. Additionally, I highlight new use cases in promoting research, such as automatically generated blog posts, presentation slides and interviews as well as podcasts via Google's NotebookLM. |
| JEL: | A10 B4 C88 O33 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:33198 |
| By: | Edward Li; Zhiyuan Tu; Dexin Zhou |
| Abstract: | We investigate how advanced large language models (LLMs), specifically GPT-4, process corporate disclosures to forecast earnings. Using earnings press releases issued around GPT-4's knowledge cutoff date, we address two questions: (1) Do GPT-generated earnings forecasts outperform analysts in accuracy? (2) How is GPT's performance related to its processing of textual and quantitative information? Our findings suggest that GPT forecasts are significantly less accurate than those of analysts. This underperformance can be traced to GPT's distinct textual and quantitative approaches: its textual processing follows a consistent, generalized pattern across firms, highlighting its strengths in language tasks. In contrast, its quantitative processing capabilities vary significantly across firms, revealing limitations tied to the uneven availability of domain-specific training data. Additionally, there is some evidence that GPT's forecast accuracy diminishes beyond its knowledge cutoff, underscoring the need to evaluate LLMs under hindsight-free conditions. Overall, this study provides a novel exploration of the "black box" of GPT-4's information processing, offering insights into LLMs' potential and challenges in financial applications. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.01069 |
| By: | Lin William Cong; Tengyuan Liang; Xiao Zhang; Wu Zhu |
| Abstract: | We introduce a general approach for analyzing large-scale text-based data, combining the strengths of neural network language processing and generative statistical modeling to create a factor structure of unstructured data for downstream regressions typically used in social sciences. We generate textual factors by (i) representing texts using vector word embedding, (ii) clustering the vectors using Locality-Sensitive Hashing to generate supports of topics, and (iii) identifying relatively interpretable spanning clusters (i.e., textual factors) through topic modeling. Our data-driven approach captures complex linguistic structures while ensuring computational scalability and economic interpretability, plausibly attaining certain advantages over and complementing other unstructured data analytics used by researchers, including emergent large language models. We conduct initial validation tests of the framework and discuss three types of its applications: (i) enhancing prediction and inference with texts, (ii) interpreting (non-text-based) models, and (iii) constructing new text-based metrics and explanatory variables. We illustrate each of these applications using examples in finance and economics such as macroeconomic forecasting from news articles, interpreting multi-factor asset pricing models from corporate filings, and measuring theme-based technology breakthroughs from patents. Finally, we provide a flexible statistical package of textual factors for online distribution to facilitate future research and applications. |
| JEL: | C13 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:33168 |
| By: | You Wu; Mengfang Sun; Hongye Zheng; Jinxin Hu; Yingbin Liang; Zhenghao Lin |
| Abstract: | This document presents an in-depth examination of stock market sentiment through the integration of Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU), enabling precise risk alerts. The robust feature extraction capability of CNN is utilized to preprocess and analyze extensive network text data, identifying local features and patterns. The extracted feature sequences are then input into the GRU model to understand the progression of emotional states over time and their potential impact on future market sentiment and risk. This approach addresses the order dependence and long-term dependencies inherent in time series data, resulting in a detailed analysis of stock market sentiment and effective early warnings of future risks. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.10199 |
| By: | Igor L. R. Azevedo; Toyotaro Suzumura |
| Abstract: | Stock market forecasting has been a topic of extensive research, aiming to provide investors with optimal stock recommendations for higher returns. In recent years, this field has gained even more attention due to the widespread adoption of deep learning models. While these models have achieved impressive accuracy in predicting stock behavior, tailoring them to specific scenarios has become increasingly important. Election Day represents one such critical scenario, characterized by intensified market volatility, as the winning candidate's policies significantly impact various economic sectors and companies. To address this challenge, we propose the Election Day Stock Market Forecasting (EDSMF) Model. Our approach leverages the contextual capabilities of large language models alongside specialized agents designed to analyze the political and economic consequences of elections. By building on a state-of-the-art architecture, we demonstrate that EDSMF improves the predictive performance of the S&P 500 during this uniquely volatile day. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.11192 |
| By: | Haohang Li; Yupeng Cao; Yangyang Yu; Shashidhar Reddy Javaji; Zhiyang Deng; Yueru He; Yuechen Jiang; Zining Zhu; Koduvayur Subbalakshmi; Guojun Xiong; Jimin Huang; Lingfei Qian; Xueqing Peng; Qianqian Xie; Jordan W. Suchow |
| Abstract: | Recent advancements have underscored the potential of large language model (LLM)-based agents in financial decision-making. Despite this progress, the field currently encounters two main challenges: (1) the lack of a comprehensive LLM agent framework adaptable to a variety of financial tasks, and (2) the absence of standardized benchmarks and consistent datasets for assessing agent performance. To tackle these issues, we introduce \textsc{InvestorBench}, the first benchmark specifically designed for evaluating LLM-based agents in diverse financial decision-making contexts. InvestorBench enhances the versatility of LLM-enabled agents by providing a comprehensive suite of tasks applicable to different financial products, including single equities like stocks, cryptocurrencies and exchange-traded funds (ETFs). Additionally, we assess the reasoning and decision-making capabilities of our agent framework using thirteen different LLMs as backbone models, across various market environments and tasks. Furthermore, we have curated a diverse collection of open-source, multi-modal datasets and developed a comprehensive suite of environments for financial decision-making. This establishes a highly accessible platform for evaluating financial agents' performance across various scenarios. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.18174 |
| By: | Xinghong Fu; Masanori Hirano; Kentaro Imajo |
| Abstract: | Large models have shown unprecedented capabilities in natural language processing, image generation, and most recently, time series forecasting. This leads us to ask the question: treating market prices as a time series, can large models be used to predict the market? In this paper, we answer this by evaluating the performance of the latest time series foundation model TimesFM on price prediction. We find that due to the irregular nature of price data, directly applying TimesFM gives unsatisfactory results and propose to fine-tune TimeFM on financial data for the task of price prediction. This is done by continual pre-training of the latest time series foundation model TimesFM on price data containing 100 million time points, spanning a range of financial instruments spanning hourly and daily granularities. The fine-tuned model demonstrates higher price prediction accuracy than the baseline model. We conduct mock trading for our model in various financial markets and show that it outperforms various benchmarks in terms of returns, sharpe ratio, max drawdown and trading cost. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.09880 |
| By: | Tarek Alexander Hassan; Stephan Hollander; Aakash Kalyani; Laurence van Lent; Markus Schwedeler; Ahmed Tahoun |
| Abstract: | This article applies simple methods from computational linguistics to analyze unstructured corporate texts for economic surveillance. We apply text-as-data approaches to earnings conference call transcripts, patent texts, and job postings to uncover unique insights into how markets and firms respond to economic shocks, such as a nuclear disaster or a geopolitical event—insights that often elude traditional data sources. This method enhances our ability to extract actionable intelligence from textual data, thereby aiding policy-making and strategic corporate decisions. By integrating computational linguistics into the analysis of economic shocks, our study opens new possibilities for real-time economic surveillance and offers a more nuanced understanding of firm-level reactions in volatile economic environments. |
| JEL: | E3 E5 E6 F01 F3 G12 G32 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:33158 |
| By: | Kirill Safonov |
| Abstract: | This paper contributes to the literature on parametric demand estimation by using deep learning to model consumer preferences. Traditional econometric methods often struggle with limited within-product price variation, a challenge addressed by the proposed neural network approach. The proposed method estimates the functional form of the demand and demonstrates higher performance in both simulations and empirical applications. Notably, under low price variation, the machine learning model outperforms econometric approaches, reducing the mean squared error of initial price parameter estimates by nearly threefold. In empirical setting, the ML model consistently predicts a negative relationship between demand and price in 100% of cases, whereas the econometric approach fails to do so in 20% of cases. The suggested model incorporates a wide range of product characteristics, as well as prices of other products and competitors. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.00920 |
| By: | Seemanta Bhattacharjee; MD. Muhtasim Fuad; A. K. M. Fakhrul Hossain |
| Abstract: | Quantum Support Vector Machine is a kernel-based approach to classification problems. We study the applicability of quantum kernels to financial data, specifically our self-curated Dhaka Stock Exchange (DSEx) Broad Index dataset. To the best of our knowledge, this is the very first systematic research work on this dataset on the application of quantum kernel. We report empirical quantum advantage in our work, using several quantum kernels and proposing the best one for this dataset while verifying the Phase Space Terrain Ruggedness Index metric. We estimate the resources needed to carry out these investigations on a larger scale for future practitioners. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.10860 |
| By: | Zhuohuan Hu; Richard Yu; Zizhou Zhang; Haoran Zheng; Qianying Liu; Yining Zhou |
| Abstract: | This paper leverages machine learning algorithms to forecast and analyze financial time series. The process begins with a denoising autoencoder to filter out random noise fluctuations from the main contract price data. Then, one-dimensional convolution reduces the dimensionality of the filtered data and extracts key information. The filtered and dimensionality-reduced price data is fed into a GANs network, and its output serve as input of a fully connected network. Through cross-validation, a model is trained to capture features that precede large price fluctuations. The model predicts the likelihood and direction of significant price changes in real-time price sequences, placing trades at moments of high prediction accuracy. Empirical results demonstrate that using autoencoders and convolution to filter and denoise financial data, combined with GANs, achieves a certain level of predictive performance, validating the capabilities of machine learning algorithms to discover underlying patterns in financial sequences. Keywords - CNN;GANs; Cryptocurrency; Prediction. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.18202 |
| By: | Sebastien Valeyre; Sofiane Aboura |
| Abstract: | Recently, LLMs (Large Language Models) have been adapted for time series prediction with significant success in pattern recognition. However, the common belief is that these models are not suitable for predicting financial market returns, which are known to be almost random. We aim to challenge this misconception through a counterexample. Specifically, we utilized the Chronos model from Ansari et al.(2024) and tested both pretrained configurations and fine-tuned supervised forecasts on the largest American single stocks using data from Guijarro-Ordonnez et al.(2022). We constructed a long/short portfolio, and the performance simulation indicates that LLMs can in reality handle time series that are nearly indistinguishable from noise, demonstrating an ability to identify inefficiencies amidst randomness and generate alpha. Finally, we compared these results with those of specialized models and smaller deep learning models, highlighting significant room for improvement in LLM performance to further enhance their predictive capabilities. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.09394 |
| By: | Jianhua Yao; Yuxin Dong; Jiajing Wang; Bingxing Wang; Hongye Zheng; Honglin Qin |
| Abstract: | This paper introduces a novel approach to stock data analysis by employing a Hierarchical Graph Neural Network (HGNN) model that captures multi-level information and relational structures in the stock market. The HGNN model integrates stock relationship data and hierarchical attributes to predict stock types effectively. The paper discusses the construction of a stock industry relationship graph and the extraction of temporal information from historical price sequences. It also highlights the design of a graph convolution operation and a temporal attention aggregator to model the macro market state. The integration of these features results in a comprehensive stock prediction model that addresses the challenges of utilizing stock relationship data and modeling hierarchical attributes in the stock market. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.06862 |
| By: | Andrew Holmes; Matt Jensen; Sarah Coffland; Hidemi Mitani Shen; Logan Sizemore; Seth Bassetti; Brenna Nieva; Claudia Tebaldi; Abigail Snyder; Brian Hutchinson |
| Abstract: | The Global Change Analysis Model (GCAM) simulates complex interactions between the coupled Earth and human systems, providing valuable insights into the co-evolution of land, water, and energy sectors under different future scenarios. Understanding the sensitivities and drivers of this multisectoral system can lead to more robust understanding of the different pathways to particular outcomes. The interactions and complexity of the coupled human-Earth systems make GCAM simulations costly to run at scale - a requirement for large ensemble experiments which explore uncertainty in model parameters and outputs. A differentiable emulator with similar predictive power, but greater efficiency, could provide novel scenario discovery and analysis of GCAM and its outputs, requiring fewer runs of GCAM. As a first use case, we train a neural network on an existing large ensemble that explores a range of GCAM inputs related to different relative contributions of energy production sources, with a focus on wind and solar. We complement this existing ensemble with interpolated input values and a wider selection of outputs, predicting 22, 528 GCAM outputs across time, sectors, and regions. We report a median $R^2$ score of 0.998 for the emulator's predictions and an $R^2$ score of 0.812 for its input-output sensitivity. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.08850 |
| By: | Miremad Soleymanian; Yi Qian |
| Abstract: | This study examines the effectiveness of virtual tours and digital marketing strategies in enhancing real estate sales using a unique dataset combining MLS data, government-assessed property values, and agents’ marketing activities. While virtual tours are often perceived as a powerful tool to boost sales, their impact is context-dependent. Using classical econometric models and causal machine learning techniques, we find that virtual tours increase property sale prices by an average of 1%. However, the effect has declined over time, particularly post-COVID, indicating a shift from being a novel feature to a standard practice. Further analysis using causal random forests reveals significant heterogeneity in their effectiveness across property attributes, market conditions, and agent characteristics. Virtual tours are less impactful for highly differentiated properties but more beneficial in competitive markets and for less experienced agents who lack familiarity with the local market. These results suggest that real estate agents may benefit from considering property features, market dynamics, and their own experience when deciding how to use virtual tours. Our findings offer valuable insights for practitioners looking to optimize digital marketing strategies and enhance sales performance. |
| JEL: | O31 R3 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:33204 |
| By: | Amine M. Aboussalah; Xuanze Li; Cheng Chi; Raj Patel |
| Abstract: | In the realm of option pricing, existing models are typically classified into principle-driven methods, such as solving partial differential equations (PDEs) that pricing function satisfies, and data-driven approaches, such as machine learning (ML) techniques that parameterize the pricing function directly. While principle-driven models offer a rigorous theoretical framework, they often rely on unrealistic assumptions, such as asset processes adhering to fixed stochastic differential equations (SDEs). Moreover, they can become computationally intensive, particularly in high-dimensional settings when analytical solutions are not available and thus numerical solutions are needed. In contrast, data-driven models excel in capturing market data trends, but they often lack alignment with core financial principles, raising concerns about interpretability and predictive accuracy, especially when dealing with limited or biased datasets. This work proposes a hybrid approach to address these limitations by integrating the strengths of both principled and data-driven methodologies. Our framework combines the theoretical rigor and interpretability of PDE-based models with the adaptability of machine learning techniques, yielding a more versatile methodology for pricing a broad spectrum of options. We validate our approach across different volatility modeling approaches-both with constant volatility (Black-Scholes) and stochastic volatility (Heston), demonstrating that our proposed framework, Finance-Informed Neural Network (FINN), not only enhances predictive accuracy but also maintains adherence to core financial principles. FINN presents a promising tool for practitioners, offering robust performance across a variety of market conditions. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.12213 |
| By: | Sohom Ghosh; Arnab Maji; N Harsha Vardhan; Sudip Kumar Naskar |
| Abstract: | With consistent growth in Indian Economy, Initial Public Offerings (IPOs) have become a popular avenue for investment. With the modern technology simplifying investments, more investors are interested in making data driven decisions while subscribing for IPOs. In this paper, we describe a machine learning and natural language processing based approach for estimating if an IPO will be successful. We have extensively studied the impact of various facts mentioned in IPO filing prospectus, macroeconomic factors, market conditions, Grey Market Price, etc. on the success of an IPO. We created two new datasets relating to the IPOs of Indian companies. Finally, we investigated how information from multiple modalities (texts, images, numbers, and categorical features) can be used for estimating the direction and underpricing with respect to opening, high and closing prices of stocks on the IPO listing day. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.16174 |
| By: | Ruiyu Zhang; Lin Nie; Ce Zhao; Qingyang Chen |
| Abstract: | Achieving consistent word interpretations across different time spans is crucial in social sciences research and text analysis tasks, as stable semantic representations form the foundation for research and task correctness, enhancing understanding of socio-political and cultural analysis. Traditional models like Word2Vec have provided significant insights into long-term semantic changes but often struggle to capture stable meanings in short-term contexts, which may be attributed to fluctuations in embeddings caused by unbalanced training data. Recent advancements, particularly BERT (Bidirectional Encoder Representations from Transformers), its pre-trained nature and transformer encoder architecture offer contextual embeddings that improve semantic consistency, making it a promising tool for short-term analysis. This study empirically compares the performance of Word2Vec and BERT in maintaining stable word meanings over time in text analysis tasks relevant to social sciences research. Using articles from the People's Daily spanning 20 years (2004-2023), we evaluated the semantic stability of each model across different timeframes. The results indicate that BERT consistently outperforms Word2Vec in maintaining semantic stability, offering greater stability in contextual embeddings. However, the study also acknowledges BERT's limitations in capturing gradual semantic shifts over longer periods due to its inherent stability. The findings suggest that while BERT is advantageous for short-term semantic analysis in social sciences, researchers should consider complementary approaches for long-term studies to fully capture semantic drift. This research underscores the importance of selecting appropriate word embedding models based on the specific temporal context of social science analyses. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.04505 |
| By: | Filip Wójcik (Wroclaw University of Economics and Business) |
| Abstract: | Aim: This study aimed to develop and apply the novel HexGIN (Heterogeneous extension for Graph Isomorphism Network) model to the FinCEN Files case data and compare its performance with existing solutions, such as the SAGE-based graph neural network and Multi-Layer Perceptron (MLP), to demonstrate its potential advantages in the field of anti-money laundering systems (AML). Methodology: The research employed the FinCEN Files case data to develop and apply the HexGIN model in a beneficiary prediction task for a suspicious transactions graph. The model's performance was compared with the existing solutions in a series of cross-validation experiments. Results: The experimental results on the cross-validation data and test dataset indicate the potential advantages of HexGIN over the existing solutions, such as MLP and Graph SAGE. The proposed model outperformed other algorithms in terms of F1 score, precision, and ROC AUC in both training and testing phases. Implications and recommendations: The findings demonstrate the potential of heterogeneous graph neural networks and their highly expressive architectures, such as GIN, in AML. Further research is needed, in particular to combine the proposed model with other existing algorithms and test the solution on various money-laundering datasets. Originality/value: Unlike many AML studies that rely on synthetic or undisclosed data sources, this research was based on a publicly available, real, heterogeneous transaction dataset, being part of a larger investigation. The results indicate a promising direction for the development of modern hybrid AML tools for analysing suspicious transactions, based on heterogeneous graph networks capable of handling various types of entities and their connections. |
| Keywords: | Money laundering, Deep learning, Neural netwoks, Finance, Graph |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-04839757 |
| By: | Vincent Lee Wai Seng; Shariff Abu Bakar Sarip Abidinsa |
| Abstract: | Since 2017, licensed money services business (MSB) operators in Malaysia report transactional data to the Central Bank of Malaysia on a monthly basis. The data allow supervisors to conduct off-site monitoring on the MSB industry; however, due to the increasing size of data and large population of the operators, supervisors face resource challenges to timely identify higher risk patterns, especially at the outlet level of the MSB. The paper proposes a weakly-supervised machine learning approach to detect anomalies in the MSB outlets on a periodic basis by combining transactional data with outlet information, including geolocation-related data. The test results highlight the benefits of machine learning techniques in facilitating supervisors to focus their resources on MSB outlets with abnormal behaviours in a targeted location. |
| Keywords: | suptech, money services business transactional data, outlet geolocation, machine learning, supervision on money services business |
| JEL: | C38 C81 G28 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:bis:bisiwp:23 |
| By: | Sumit Nawathe; Ravi Panguluri; James Zhang; Sashwat Venkatesh |
| Abstract: | We propose a reinforcement learning (RL) framework that leverages multimodal data including historical stock prices, sentiment analysis, and topic embeddings from news articles, to optimize trading strategies for SP100 stocks. Building upon recent advancements in financial reinforcement learning, we aim to enhance the state space representation by integrating financial sentiment data from SEC filings and news headlines and refining the reward function to better align with portfolio performance metrics. Our methodology includes deep reinforcement learning with state tensors comprising price data, sentiment scores, and news embeddings, processed through advanced feature extraction models like CNNs and RNNs. By benchmarking against traditional portfolio optimization techniques and advanced strategies, we demonstrate the efficacy of our approach in delivering superior portfolio performance. Empirical results showcase the potential of our agent to outperform standard benchmarks, especially when utilizing combined data sources under profit-based reward functions. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.17293 |
| By: | Andrea Bucci; Michele Palma; Chao Zhang |
| Abstract: | Traditional methods employed in matrix volatility forecasting often overlook the inherent Riemannian manifold structure of symmetric positive definite matrices, treating them as elements of Euclidean space, which can lead to suboptimal predictive performance. Moreover, they often struggle to handle high-dimensional matrices. In this paper, we propose a novel approach for forecasting realized covariance matrices of asset returns using a Riemannian-geometry-aware deep learning framework. In this way, we account for the geometric properties of the covariance matrices, including possible non-linear dynamics and efficient handling of high-dimensionality. Moreover, building upon a Fr\'echet sample mean of realized covariance matrices, we are able to extend the HAR model to the matrix-variate. We demonstrate the efficacy of our approach using daily realized covariance matrices for the 50 most capitalized companies in the S&P 500 index, showing that our method outperforms traditional approaches in terms of predictive accuracy. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.09517 |
| By: | Zhuohuan Hu; Fu Lei; Yuxin Fan; Zong Ke; Ge Shi; Zichao Li |
| Abstract: | In today's complex and volatile financial market environment, risk management of multi-asset portfolios faces significant challenges. Traditional risk assessment methods, due to their limited ability to capture complex correlations between assets, find it difficult to effectively cope with dynamic market changes. This paper proposes a multi-asset portfolio risk prediction model based on Convolutional Neural Networks (CNN). By utilizing image processing techniques, financial time series data are converted into two-dimensional images to extract high-order features and enhance the accuracy of risk prediction. Through empirical analysis of data from multiple asset classes such as stocks, bonds, commodities, and foreign exchange, the results show that the proposed CNN model significantly outperforms traditional models in terms of prediction accuracy and robustness, especially under extreme market conditions. This research provides a new method for financial risk management, with important theoretical significance and practical value. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.03618 |
| By: | Laura Chioda; Paul Gertler; Sean Higgins; Paolina C. Medina |
| Abstract: | Despite the promise of FinTech lending to expand access to credit to populations without a formal credit history, FinTech lenders primarily lend to applicants with a formal credit history and rely on conventional credit bureau scores as an input to their algorithms. Using data from a large FinTech lender in Mexico, we show that alternative data from digital transactions through a delivery app are effective at predicting creditworthiness for borrowers with no credit history. We also show that segmenting our machine learning model by gender can improve credit allocation fairness without a substantive effect on the model’s predictive performance. |
| JEL: | G23 G5 O16 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:33208 |
| By: | Akash Deep; Chris Monico; Abootaleb Shirvani; Svetlozar Rachev; Frank J. Fabozzi |
| Abstract: | This study evaluates the performance of random forest regression models enhanced with technical indicators for high-frequency stock price prediction. Using minute-level SPY data, we assessed 13 models that incorporate technical indicators such as Bollinger bands, exponential moving average, and Fibonacci retracement. While these models improved risk-adjusted performance metrics, they struggled with out-of-sample generalization, highlighting significant overfitting challenges. Feature importance analysis revealed that primary price-based features consistently outperformed technical indicators, suggesting their limited utility in high-frequency trading contexts. These findings challenge the weak form of the efficient market hypothesis, identifying short-lived inefficiencies during volatile periods but its limited persistence across market regimes. The study emphasizes the need for selective feature engineering, adaptive modeling, and a stronger focus on risk-adjusted performance metrics to navigate the complexities of high-frequency trading environments. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.15448 |
| By: | Marco Molinari; Victor Shao; Vladimir Tregubiak; Abhimanyu Pandey; Mateusz Mikolajczak; Sebastian Kuznetsov Ryder Torres Pereira |
| Abstract: | Determining company similarity is a vital task in finance, underpinning hedging, risk management, portfolio diversification, and more. Practitioners often rely on sector and industry classifications to gauge similarity, such as SIC-codes and GICS-codes - the former being used by the U.S. Securities and Exchange Commission (SEC), and the latter widely used by the investment community. Since these classifications can lack granularity and often need to be updated, using clusters of embeddings of company descriptions has been proposed as a potential alternative, but the lack of interpretability in token embeddings poses a significant barrier to adoption in high-stakes contexts. Sparse Autoencoders (SAEs) have shown promise in enhancing the interpretability of Large Language Models (LLMs) by decomposing LLM activations into interpretable features. We apply SAEs to company descriptions, obtaining meaningful clusters of equities in the process. We benchmark SAE features against SIC-codes, Major Group codes, and Embeddings. Our results demonstrate that SAE features not only replicate but often surpass sector classifications and embeddings in capturing fundamental company characteristics. This is evidenced by their superior performance in correlating monthly returns - a proxy for similarity - and generating higher Sharpe ratio co-integration strategies, which underscores deeper fundamental similarities among companies. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.02605 |
| By: | Wo Long; Victor Xiao |
| Abstract: | The residuals in factor models prevalent in asset pricing presents opportunities to exploit the mis-pricing from unexplained cross-sectional variation for arbitrage. We performed a replication of the methodology of Guijarro-Ordonez et al. (2019) (G-P-Z) on Deep Learning Statistical Arbitrage (DLSA), originally applied to U.S. equity data from 1998 to 2016, using a more recent out-of-sample period from 2016 to 2024. Adhering strictly to point-in-time (PIT) principles and ensuring no information leakage, we follow the same data pre-processing, factor modeling, and deep learning architectures (CNNs and Transformers) as outlined by G-P-Z. Our replication yields unusually strong performance metrics in certain tests, with out-of-sample Sharpe ratios occasionally exceeding 10. While such results are intriguing, they may indicate model overfitting, highly specific market conditions, or insufficient accounting for transaction costs and market impact. Further examination and robustness checks are needed to align these findings with the more modest improvements reported in the original study. (This work was conducted as the final project for IEOR 4576: Data-Driven Methods in Finance at Columbia University.) |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.11432 |
| By: | Fengpei Li; Haoxian Chen; Jiahe Lin; Arkin Gupta; Xiaowei Tan; Gang Xu; Yuriy Nevmyvaka; Agostino Capponi; Henry Lam |
| Abstract: | Despite being an essential tool across engineering and finance, Monte Carlo simulation can be computationally intensive, especially in large-scale, path-dependent problems that hinder straightforward parallelization. A natural alternative is to replace simulation with machine learning or surrogate prediction, though this introduces challenges in understanding the resulting errors.We introduce a Prediction-Enhanced Monte Carlo (PEMC) framework where we leverage machine learning prediction as control variates, thus maintaining unbiased evaluations instead of the direct use of ML predictors. Traditional control variate methods require knowledge of means and focus on per-sample variance reduction. In contrast, PEMC aims at overall cost-aware variance reduction, eliminating the need for mean knowledge. PEMC leverages pre-trained neural architectures to construct effective control variates and replaces computationally expensive sample-path generation with efficient neural network evaluations. This allows PEMC to address scenarios where no good control variates are known. We showcase the efficacy of PEMC through two production-grade exotic option-pricing problems: swaption pricing in HJM model and the variance swap pricing in a stochastic local volatility model. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.11257 |
| By: | Sahar Yarmohammadtoosky Dinesh Chowdary Attota |
| Abstract: | As several studies have shown, predicting credit risk is still a major concern for the financial services industry and is receiving a lot of scholarly interest. This area of study is crucial because it aids financial organizations in determining the probability that borrowers would default, which has a direct bearing on lending choices and risk management tactics. Despite the progress made in this domain, there is still a substantial knowledge gap concerning consumer actions that take place prior to the filing of credit card applications. The objective of this study is to predict customer responses to mail campaigns and assess the likelihood of default among those who engage. This research employs advanced machine learning techniques, specifically logistic regression and XGBoost, to analyze consumer behavior and predict responses to direct mail campaigns. By integrating different data preprocessing strategies, including imputation and binning, we enhance the robustness and accuracy of our predictive models. The results indicate that XGBoost consistently outperforms logistic regression across various metrics, particularly in scenarios using categorical binning and custom imputation. These findings suggest that XGBoost is particularly effective in handling complex data structures and provides a strong predictive capability in assessing credit risk. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.16333 |
| By: | Niko Hauzenberger; Florian Huber; Karin Klieber; Massimiliano Marcellino |
| Abstract: | We propose a method to learn the nonlinear impulse responses to structural shocks using neural networks, and apply it to uncover the effects of US financial shocks. The results reveal substantial asymmetries with respect to the sign of the shock. Adverse financial shocks have powerful effects on the US economy, while benign shocks trigger much smaller reactions. Instead, with respect to the size of the shocks, we find no discernible asymmetries. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.07649 |
| By: | Zheng Cao; Helyette Geman |
| Abstract: | This manuscript introduces the hype-adjusted probability measure developed in the context of a new Natural Language Processing (NLP) approach for market forecasting. A novel sentiment score equation is presented to capture component and memory effects and assign dynamic parameters, enhancing the impact of intraday news data on forecasting next-period volatility for selected U.S. semiconductor stocks. This approach integrates machine learning techniques to analyze and improve the predictive value of news. Building on the research of Geman's, this work improves forecast accuracy by assigning specific weights to each component of news sources and individual stocks in the portfolio, evaluating time-memory effects on market reactions, and incorporating shifts in sentiment direction. Finally, we propose the Hype-Adjusted Probability Measure, proving its existence and uniqueness, and discuss its theoretical applications in finance for NLP-based volatility forecasting, outlining future research pathways inspired by its concepts. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.07587 |
| By: | Yuxin Fan; Zhuohuan Hu; Lei Fu; Yu Cheng; Liyang Wang; Yuxiang Wang |
| Abstract: | High-frequency trading (HFT) represents a pivotal and intensely competitive domain within the financial markets. The velocity and accuracy of data processing exert a direct influence on profitability, underscoring the significance of this field. The objective of this work is to optimise the real-time processing of data in high-frequency trading algorithms. The dynamic feature selection mechanism is responsible for monitoring and analysing market data in real time through clustering and feature weight analysis, with the objective of automatically selecting the most relevant features. This process employs an adaptive feature extraction method, which enables the system to respond and adjust its feature set in a timely manner when the data input changes, thus ensuring the efficient utilisation of data. The lightweight neural networks are designed in a modular fashion, comprising fast convolutional layers and pruning techniques that facilitate the expeditious completion of data processing and output prediction. In contrast to conventional deep learning models, the neural network architecture has been specifically designed to minimise the number of parameters and computational complexity, thereby markedly reducing the inference time. The experimental results demonstrate that the model is capable of maintaining consistent performance in the context of varying market conditions, thereby illustrating its advantages in terms of processing speed and revenue enhancement. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.01062 |
| By: | Hortense Fong; George Gui |
| Abstract: | Understanding when and why consumers engage with stories is crucial for content creators and platforms. While existing theories suggest that audience beliefs of what is going to happen should play an important role in engagement decisions, empirical work has mostly focused on developing techniques to directly extract features from actual content, rather than capturing forward-looking beliefs, due to the lack of a principled way to model such beliefs in unstructured narrative data. To complement existing feature extraction techniques, this paper introduces a novel framework that leverages large language models to model audience forward-looking beliefs about how stories might unfold. Our method generates multiple potential continuations for each story and extracts features related to expectations, uncertainty, and surprise using established content analysis techniques. Applying our method to over 30, 000 book chapters from Wattpad, we demonstrate that our framework complements existing feature engineering techniques by amplifying their marginal explanatory power on average by 31%. The results reveal that different types of engagement-continuing to read, commenting, and voting-are driven by distinct combinations of current and anticipated content features. Our framework provides a novel way to study and explore how audience forward-looking beliefs shape their engagement with narrative media, with implications for marketing strategy in content-focused industries. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.15239 |
| By: | Robert Kelchen; Dubravka Ritter; Douglas A. Webber |
| Abstract: | In this paper, we assemble the most comprehensive dataset to date on the characteristics of colleges and universities, including dates of operation, institutional setting, student body, staff, and finance data from 2002 to 2023. We provide an extensive description of what is known and unknown about closed colleges compared with institutions that did not close. Using this data, we first develop a series of predictive models of financial distress, utilizing factors like operational revenue/expense patterns, sources of revenue, metrics of liquidity and leverage, enrollment/staff patterns, and prior signs of significant financial strain. We benchmark these models against existing federal government screening mechanisms such as financial responsibility scores and heightened cash monitoring. We document a high degree of missing data among colleges that eventually close and show that this is a key impediment to identifying at risk institutions. We then show that modern machine learning techniques, combined with richer data, are far more effective at predicting college closures than linear probability models, and considerably more effective than existing accountability metrics. Our preferred model, which combines an off-the-shelf machine learning algorithm with the richest set of explanatory variables, can significantly improve predictive accuracy even for institutions with complete data, but is particularly helpful for predicting instances of financial distress for institutions with spotty data. Finally, we conduct simulations using our estimates to contemplate likely increases in future closures, showing that enrollment challenges resulting from an impending demographic cliff are likely to significantly increase annual college closures for reasonable scenarios. |
| Keywords: | Higher education; College, university; Enrollment; Tuition; Revenue; Budget; Closure; Fiscal challenge; Demographic cliff |
| JEL: | I22 I23 J21 J24 |
| Date: | 2025–01–06 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedgfe:2025-03 |
| By: | Thomas Krause; Steffen Otterbach; Johannes Singer |
| Abstract: | This report documents the development, test, and application of Large Language Models (LLMs) for automated text analysis, with a specific focus on gambling-like elements in digital games, such as lootboxes. The project aimed not only to analyse user opinions and attitudes towards these mechanics, but also to advance methodological research in text analysis. By employing prompting techniques and iterative prompt refinement processes, the study sought to test and improve the accuracy of LLM-based text analysis. The findings indicate that while LLMs can effectively identify relevant patterns and themes on par with human coders, there are still challenges in handling more complex tasks, underscoring the need for ongoing refinement in methodologies. The methodological advancements achieved through this study significantly enhance the application of LLMs in real-world text analysis. The research provides valuable insights into how these models can be better utilized to analyze complex, user-generated content. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.09345 |
| By: | Yuhan Wang; Zhen Xu; Yue Yao; Jinsong Liu; Jiating Lin |
| Abstract: | With the development of the financial industry, credit default prediction, as an important task in financial risk management, has received increasing attention. Traditional credit default prediction methods mostly rely on machine learning models, such as decision trees and random forests, but these methods have certain limitations in processing complex data and capturing potential risk patterns. To this end, this paper proposes a deep learning model based on the combination of convolutional neural networks (CNN) and Transformer for credit user default prediction. The model combines the advantages of CNN in local feature extraction with the ability of Transformer in global dependency modeling, effectively improving the accuracy and robustness of credit default prediction. Through experiments on public credit default datasets, the results show that the CNN+Transformer model outperforms traditional machine learning models, such as random forests and XGBoost, in multiple evaluation indicators such as accuracy, AUC, and KS value, demonstrating its powerful ability in complex financial data modeling. Further experimental analysis shows that appropriate optimizer selection and learning rate adjustment play a vital role in improving model performance. In addition, the ablation experiment of the model verifies the advantages of the combination of CNN and Transformer and proves the complementarity of the two in credit default prediction. This study provides a new idea for credit default prediction and provides strong support for risk assessment and intelligent decision-making in the financial field. Future research can further improve the prediction effect and generalization ability by introducing more unstructured data and improving the model architecture. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.18222 |
| By: | Zong Ke; Jingyu Xu; Zizhou Zhang; Yu Cheng; Wenjun Wu |
| Abstract: | This paper provides a unique approach with AI algorithms to predict emerging stock markets volatility. Traditionally, stock volatility is derived from historical volatility, Monte Carlo simulation and implied volatility as well. In this paper, the writer designs a consolidated model with back-propagation neural network and genetic algorithm to predict future volatility of emerging stock markets and found that the results are quite accurate with low errors. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.07223 |
| By: | Dou, Liyu (School of Economics, Singapore Management University); KASTL, Jakub (Department of Economics, Princeton University, NBER and CEPR); LAZAREV, John (Stern Economics, New York University) |
| Abstract: | We develop a framework for quantifying delay propagation in airline networks that combines structural modeling and machine learning methods together to estimate causal objects of interest. Using a large comprehensive data set on actual delays and a model-selection algorithm (elastic net) we estimate a weighted directed graph of delay propagation for each major airline in the US and derive conditions under which the estimates of the propagation coefficients are causal. We use these estimates to decompose the airline performance into “luck” and “ability.” We find that luck may explain about 38% of the performance difference between Delta and American in our data. We further use these estimates to describe how network topology and other airline network characteristics (such as aircraft fleet heterogeneity) affect the expected delays. |
| Keywords: | Airline Networks; Shock Propagation; Elastic Net |
| JEL: | C50 L14 L93 |
| Date: | 2025–09–01 |
| URL: | https://d.repec.org/n?u=RePEc:ris:smuesw:2024_014 |
| By: | Van-Duc Le |
| Abstract: | Financial analysis heavily relies on the evaluation of earnings reports to gain insights into company performance. Traditional generation of these reports requires extensive financial expertise and is time-consuming. With the impressive progress in Large Language Models (LLMs), a wide variety of financially focused LLMs has emerged, addressing tasks like sentiment analysis and entity recognition in the financial domain. This paper presents a novel challenge: developing an LLM specifically for automating the generation of earnings reports analysis. Our methodology involves an in-depth analysis of existing earnings reports followed by a unique approach to fine-tune an LLM for this purpose. This approach combines retrieval augmentation and the generation of instruction-based data, specifically tailored for the financial sector, to enhance the LLM's performance. With extensive financial documents, we construct financial instruction data, enabling the refined adaptation of our LLM to financial contexts. Preliminary results indicate that our augmented LLM outperforms general open-source models and rivals commercial counterparts like GPT-3.5 in financial applications. Our research paves the way for streamlined and insightful automation in financial report generation, marking a significant stride in the field of financial analysis. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.08179 |
| By: | Gang Huang; Xiaohua Zhou; Qingyang Song |
| Abstract: | Artificial intelligence is fundamentally transforming financial investment decision-making paradigms, with deep reinforcement learning (DRL) demonstrating significant application potential in domains such as robo-advisory services. Given that traditional portfolio optimization methods face significant challenges in effectively managing dynamic asset weight adjustments, this paper approaches the problem from the perspective of practical trading processes and develops a dynamic optimization model using deep reinforcement learning to achieve more effective asset allocation. The study's innovations are twofold: First, we propose a Sharpe ratio reward function specifically designed for Actor-Critic deep reinforcement learning algorithms, which optimizes portfolio performance by maximizing the average Sharpe ratio through random sampling and reinforcement learning algorithms during the training process; Second, we design deep neural networks that are specifically structured to meet asset optimization objectives. The study empirically evaluates the model using randomly selected constituent stocks from the CSI300 index and conducts comparative analyses against traditional approaches, including mean-variance optimization and risk parity strategies. Backtesting results demonstrate the dynamic optimization model's effectiveness in portfolio asset allocation, yielding enhanced risk reduction, superior risk-return metrics, and optimal performance across comprehensive evaluation criteria. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.18563 |
| By: | Philippe Goulet Coulombe; Maximilian Goebel; Karin Klieber |
| Abstract: | Machine learning predictions are typically interpreted as the sum of contributions of predictors. Yet, each out-of-sample prediction can also be expressed as a linear combination of in-sample values of the predicted variable, with weights corresponding to pairwise proximity scores between current and past economic events. While this dual route leads nowhere in some contexts (e.g., large cross-sectional datasets), it provides sparser interpretations in settings with many regressors and little training data-like macroeconomic forecasting. In this case, the sequence of contributions can be visualized as a time series, allowing analysts to explain predictions as quantifiable combinations of historical analogies. Moreover, the weights can be viewed as those of a data portfolio, inspiring new diagnostic measures such as forecast concentration, short position, and turnover. We show how weights can be retrieved seamlessly for (kernel) ridge regression, random forest, boosted trees, and neural networks. Then, we apply these tools to analyze post-pandemic forecasts of inflation, GDP growth, and recession probabilities. In all cases, the approach opens the black box from a new angle and demonstrates how machine learning models leverage history partly repeating itself. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.13076 |
| By: | Siqiao Zhao; Dan Wang; Raphael Douady |
| Abstract: | The domain of hedge fund investments is undergoing significant transformation, influenced by the rapid expansion of data availability and the advancement of analytical technologies. This study explores the enhancement of hedge fund investment performance through the integration of machine learning techniques, the application of PolyModel feature selection, and the analysis of fund size. We address three critical questions: (1) the effect of machine learning on trading performance, (2) the role of PolyModel feature selection in fund selection and performance, and (3) the comparative reliability of larger versus smaller funds. Our findings offer compelling insights. We observe that while machine learning techniques enhance cumulative returns, they also increase annual volatility, indicating variability in performance. PolyModel feature selection proves to be a robust strategy, with approaches that utilize a comprehensive set of features for fund selection outperforming more selective methodologies. Notably, Long-Term Stability (LTS) effectively manages portfolio volatility while delivering favorable returns. Contrary to popular belief, our results suggest that larger funds do not consistently yield better investment outcomes, challenging the assumption of their inherent reliability. This research highlights the transformative impact of data-driven approaches in the hedge fund investment arena and provides valuable implications for investors and asset managers. By leveraging machine learning and PolyModel feature selection, investors can enhance portfolio optimization and reassess the dependability of larger funds, leading to more informed investment strategies. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.11019 |
| By: | Vidhi Agrawal; Eesha Khalid; Tianyu Tan; Doris Xu |
| Abstract: | This study applies machine learning to predict S&P 500 membership changes: key events that profoundly impact investor behavior and market dynamics. Quarterly data from WRDS datasets (2013 onwards) was used, incorporating features such as industry classification, financial data, market data, and corporate governance indicators. Using a Random Forest model, we achieved a test F1 score of 0.85, outperforming logistic regression and SVC models. This research not only showcases the power of machine learning for financial forecasting but also emphasizes model transparency through SHAP analysis and feature engineering. The model's real world applicability is demonstrated with predicted changes for Q3 2023, such as the addition of Uber (UBER) and the removal of SolarEdge Technologies (SEDG). By incorporating these predictions into a trading strategy i.e. buying stocks announced for addition and shorting those marked for removal, we anticipate capturing alpha and enhancing investment decision making, offering valuable insights into index dynamics |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.12539 |
| By: | Jiajun Gu; Zichen Yang; Xintong Lin; Sixun Chen; YuTing Lu |
| Abstract: | This project investigates the interplay of technical, market, and statistical factors in predicting stock market performance, with a primary focus on S&P 500 companies. Utilizing a comprehensive dataset spanning multiple years, the analysis constructs advanced financial metrics, such as momentum indicators, volatility measures, and liquidity adjustments. The machine learning framework is employed to identify patterns, relationships, and predictive capabilities of these factors. The integration of traditional financial analytics with machine learning enables enhanced predictive accuracy, offering valuable insights into market behavior and guiding investment strategies. This research highlights the potential of combining domain-specific financial expertise with modern computational tools to address complex market dynamics. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.12438 |
| By: | Stéphane Goutte (PSB - Paris School of Business - HESAM - HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université, SOURCE - SOUtenabilité et RésilienCE - UVSQ - Université de Versailles Saint-Quentin-en-Yvelines - IRD [Ile-de-France] - Institut de Recherche pour le Développement); Klemens Klotzner; Hoang Viet Le (SOURCE - SOUtenabilité et RésilienCE - UVSQ - Université de Versailles Saint-Quentin-en-Yvelines - IRD [Ile-de-France] - Institut de Recherche pour le Développement); Hans Jörg von Mettenheim (IPAG Business School) |
| Abstract: | In this paper, we address the refinement of solar energy forecasting within a 2-day window by integrating weather forecast data and strategically employing entity embedding, with a specific focus on the Multilayer Perceptron (MLP) algorithm. Through the analysis of two years of hourly solar energy production data from 16 power plants in Northern Italy (2020-2021), our research underscores the substantial impact of weather variables on solar energy production. Notably, we explore the augmentation of forecasting models by incorporating entity embedding, with a particular emphasis on embedding techniques for both general weather descriptors and individual power plants. By highlighting the nuanced integration of entity embedding within the MLP algorithm, our study reveals a significant enhancement in forecasting accuracy compared to popular machine learning algorithms like XGBoost and LGBM, showcasing the potential of this approach for more precise solar energy forecasts. |
| Keywords: | Entity embedding, Machine learning, Neural networks, Solar energy, Time series forecasting |
| Date: | 2024–09–06 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-04779953 |
| By: | Shasha Yu; Qinchen Zhang; Yuwei Zhao |
| Abstract: | This project aims to predict short-term and long-term upward trends in the S&P 500 index using machine learning models and feature engineering based on the "101 Formulaic Alphas" methodology. The study employed multiple models, including Logistic Regression, Decision Trees, Random Forests, Neural Networks, K-Nearest Neighbors (KNN), and XGBoost, to identify market trends from historical stock data collected from Yahoo! Finance. Data preprocessing involved handling missing values, standardization, and iterative feature selection to ensure relevance and variability. For short-term predictions, KNN emerged as the most effective model, delivering robust performance with high recall for upward trends, while for long-term forecasts, XGBoost demonstrated the highest accuracy and AUC scores after hyperparameter tuning and class imbalance adjustments using SMOTE. Feature importance analysis highlighted the dominance of momentum-based and volume-related indicators in driving predictions. However, models exhibited limitations such as overfitting and low recall for positive market movements, particularly in imbalanced datasets. The study concludes that KNN is ideal for short-term alerts, whereas XGBoost is better suited for long-term trend forecasting. Future enhancements could include advanced architectures like Long Short-Term Memory (LSTM) networks and further feature refinement to improve precision and generalizability. These findings contribute to developing reliable machine learning tools for market trend prediction and investment decision-making. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.11462 |
| By: | Bhaskarjit Sarmah; Mingshu Li; Jingrao Lyu; Sebastian Frank; Nathalia Castellanos; Stefano Pasquali; Dhagash Mehta |
| Abstract: | To ensure and monitor large language models (LLMs) reliably, various evaluation metrics have been proposed in the literature. However, there is little research on prescribing a methodology to identify a robust threshold on these metrics even though there are many serious implications of an incorrect choice of the thresholds during deployment of the LLMs. Translating the traditional model risk management (MRM) guidelines within regulated industries such as the financial industry, we propose a step-by-step recipe for picking a threshold for a given LLM evaluation metric. We emphasize that such a methodology should start with identifying the risks of the LLM application under consideration and risk tolerance of the stakeholders. We then propose concrete and statistically rigorous procedures to determine a threshold for the given LLM evaluation metric using available ground-truth data. As a concrete example to demonstrate the proposed methodology at work, we employ it on the Faithfulness metric, as implemented in various publicly available libraries, using the publicly available HaluBench dataset. We also lay a foundation for creating systematic approaches to select thresholds, not only for LLMs but for any GenAI applications. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.12148 |
| By: | Jiti Gao; Fei Liu; Bin Peng; Yanrong Yang |
| Abstract: | In this paper, we investigate a semiparametric regression model under the context of treatment effects via a localized neural network (LNN) approach. Due to a vast number of parameters involved, we reduce the number of effective parameters by (i) exploring the use of identification restrictions; and (ii) adopting a variable selection method based on the group-LASSO technique. Subsequently, we derive the corresponding estimation theory and propose a dependent wild bootstrap procedure to construct valid inferences accounting for the dependence of data. Finally, we validate our theoretical findings through extensive numerical studies. In an empirical study, we revisit the impacts of a tightening monetary policy action on a variety of economic variables, including short-/long-term interest rate, inflation, unemployment rate, industrial price and equity return via the newly proposed framework using a monthly dataset of the US. |
| Keywords: | Dependent Wild Bootstrap; Group-LASSO; Semiparametric Model; Treatment Effects |
| JEL: | C14 C22 C45 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:msh:ebswps:2024-14 |
| By: | Gero Junike; Hauke Stier |
| Abstract: | Fourier pricing methods such as the Carr-Madan formula or the COS method are classic tools for pricing European options for advanced models such as the Heston model. These methods require tuning parameters such as a damping factor, a truncation range, a number of terms, etc. Estimating these tuning parameters is difficult or computationally expensive. Recently, machine learning techniques have been proposed for fast pricing: they are able to learn the functional relationship between the parameters of the Heston model and the option price. However, machine learning techniques suffer from error control and require retraining for different error tolerances. In this research, we propose to learn the tuning parameters of the Fourier methods (instead of the prices) using machine learning techniques. As a result, we obtain very fast algorithms with full error control: Our approach works with any error tolerance without retraining, as demonstrated in numerical experiments using the Heston model. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.05070 |
| By: | Olamilekan Shobayo; Sidikat Adeyemi-Longe; Olusogo Popoola; Bayode Ogunleye |
| Abstract: | This study explores the comparative performance of cutting-edge AI models, i.e., Finaance Bidirectional Encoder representations from Transsformers (FinBERT), Generatice Pre-trained Transformer GPT-4, and Logistic Regression, for sentiment analysis and stock index prediction using financial news and the NGX All-Share Index data label. By leveraging advanced natural language processing models like GPT-4 and FinBERT, alongside a traditional machine learning model, Logistic Regression, we aim to classify market sentiment, generate sentiment scores, and predict market price movements. This research highlights global AI advancements in stock markets, showcasing how state-of-the-art language models can contribute to understanding complex financial data. The models were assessed using metrics such as accuracy, precision, recall, F1 score, and ROC AUC. Results indicate that Logistic Regression outperformed the more computationally intensive FinBERT and predefined approach of versatile GPT-4, with an accuracy of 81.83% and a ROC AUC of 89.76%. The GPT-4 predefined approach exhibited a lower accuracy of 54.19% but demonstrated strong potential in handling complex data. FinBERT, while offering more sophisticated analysis, was resource-demanding and yielded a moderate performance. Hyperparameter optimization using Optuna and cross-validation techniques ensured the robustness of the models. This study highlights the strengths and limitations of the practical applications of AI approaches in stock market prediction and presents Logistic Regression as the most efficient model for this task, with FinBERT and GPT-4 representing emerging tools with potential for future exploration and innovation in AI-driven financial analytics |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.06837 |
| By: | Yixuan Liang; Yuncong Liu; Boyu Zhang; Christina Dan Wang; Hongyang Yang |
| Abstract: | Financial sentiment analysis is crucial for understanding the influence of news on stock prices. Recently, large language models (LLMs) have been widely adopted for this purpose due to their advanced text analysis capabilities. However, these models often only consider the news content itself, ignoring its dissemination, which hampers accurate prediction of short-term stock movements. Additionally, current methods often lack sufficient contextual data and explicit instructions in their prompts, limiting LLMs' ability to interpret news. In this paper, we propose a data-driven approach that enhances LLM-powered sentiment-based stock movement predictions by incorporating news dissemination breadth, contextual data, and explicit instructions. We cluster recent company-related news to assess its reach and influence, enriching prompts with more specific data and precise instructions. This data is used to construct an instruction tuning dataset to fine-tune an LLM for predicting short-term stock price movements. Our experimental results show that our approach improves prediction accuracy by 8\% compared to existing methods. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.10823 |
| By: | Samuel Arts; Nicola Melluso; Reinhilde Veugelers |
| Abstract: | New scientific ideas drive progress, yet measuring scientific novelty remains challenging. We use natural language processing to detect the origin and impact of new ideas in scientific publications. To validate our methods, we analyze Nobel Prize-winning papers, which likely pioneered impactful new ideas, and literature review papers, which typically consolidate existing knowledge. We also show that novel papers have more intellectual neighbors published after them, indicating they are ahead of their intellectual peers. Finally, papers introducing new ideas, particularly those with greater follow-on reuse, attract more citations. |
| Keywords: | natural language processing, science, novelty, impact, breakthrough, Nobel, OpenAlex |
| Date: | 2025–01–13 |
| URL: | https://d.repec.org/n?u=RePEc:ete:msiper:757417 |
| By: | Dongwoo Lee; Gavin Kader |
| Abstract: | As Large Language Models (LLMs) are increasingly used for a variety of complex and critical tasks, it is vital to assess their logical capabilities in strategic environments. This paper examines their ability in strategic reasoning -- the process of choosing an optimal course of action by predicting and adapting to other agents' behavior. Using six LLMs, we analyze responses from play in classical games from behavioral economics (p-Beauty Contest, 11-20 Money Request Game, and Guessing Game) and evaluate their performance through hierarchical models of reasoning (level-$k$ theory and cognitive hierarchy theory). Our findings reveal that while LLMs show understanding of the games, the majority struggle with higher-order strategic reasoning. Although most LLMs did demonstrate learning ability with games involving repeated interactions, they still consistently fall short of the reasoning levels demonstrated by typical behavior from human subjects. The exception to these overall findings is with OpenAI's GPT-o1 -- specifically trained to solve complex reasoning tasks -- which consistently outperforms other LLMs and human subjects. These findings highlight the challenges and pathways in advancing LLMs toward robust strategic reasoning from the perspective of behavioral economics. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.13013 |
| By: | Julian Junyan Wang; Victor Xiaoqi Wang |
| Abstract: | Unequal access to costly datasets essential for empirical research has long hindered researchers from disadvantaged institutions, limiting their ability to contribute to their fields and advance their careers. Recent breakthroughs in Large Language Models (LLMs) have the potential to democratize data access by automating data collection from unstructured sources. We develop and evaluate a novel methodology using GPT-4o-mini within a Retrieval-Augmented Generation (RAG) framework to collect data from corporate disclosures. Our approach achieves human-level accuracy in collecting CEO pay ratios from approximately 10, 000 proxy statements and Critical Audit Matters (CAMs) from more than 12, 000 10-K filings, with LLM processing times of 9 and 40 minutes respectively, each at a cost under $10. This stands in stark contrast to the hundreds of hours needed for manual collection or the thousands of dollars required for commercial database subscriptions. To foster a more inclusive research community by empowering researchers with limited resources to explore new avenues of inquiry, we share our methodology and the resulting datasets. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.02065 |