|
on Computational Economics |
| By: | Achintya Gopal |
| Abstract: | The use of machine learning for statistical modeling (and thus, generative modeling) has grown in popularity with the proliferation of time series models, text-to-image models, and especially large language models. Fundamentally, the goal of classical factor modeling is statistical modeling of stock returns, and in this work, we explore using deep generative modeling to enhance classical factor models. Prior work has explored the use of deep generative models in order to model hundreds of stocks, leading to accurate risk forecasting and alpha portfolio construction; however, that specific model does not allow for easy factor modeling interpretation in that the factor exposures cannot be deduced. In this work, we introduce NeuralFactors, a novel machine-learning based approach to factor analysis where a neural network outputs factor exposures and factor returns, trained using the same methodology as variational autoencoders. We show that this model outperforms prior approaches both in terms of log-likelihood performance and computational efficiency. Further, we show that this method is competitive to prior work in generating realistic synthetic data, covariance estimation, risk analysis (e.g., value at risk, or VaR, of portfolios), and portfolio optimization. Finally, due to the connection to classical factor analysis, we analyze how the factors our model learns cluster together and show that the factor exposures could be used for embedding stocks. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.01499 |
| By: | Teng Ye; Jingnan Zheng; Junhui Jin; Jingyi Qiu; Wei Ai; Qiaozhu Mei |
| Abstract: | While small businesses are increasingly turning to online crowdfunding platforms for essential funding, over 40% of these campaigns may fail to raise any money, especially those from low socio-economic areas. We utilize the latest advancements in AI technology to identify crucial factors that influence the success of crowdfunding campaigns and to improve their fundraising outcomes by strategically optimizing these factors. Our best-performing machine learning model accurately predicts the fundraising outcomes of 81.0% of campaigns, primarily based on their textual descriptions. Interpreting the machine learning model allows us to provide actionable suggestions on improving the textual description before launching a campaign. We demonstrate that by augmenting just three aspects of the narrative using a large language model, a campaign becomes more preferable to 83% human evaluators, and its likelihood of securing financial support increases by 11.9%. Our research uncovers the effective strategies for crafting descriptions for small business fundraising campaigns and opens up a new realm in integrating large language models into crowdfunding methodologies. |
| Date: | 2024–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.09480 |
| By: | Haowei Ni; Shuchen Meng; Xupeng Chen; Ziqing Zhao; Andi Chen; Panfeng Li; Shiyao Zhang; Qifu Yin; Yuanqing Wang; Yuxi Chan |
| Abstract: | Accurate stock market predictions following earnings reports are crucial for investors. Traditional methods, particularly classical machine learning models, struggle with these predictions because they cannot effectively process and interpret extensive textual data contained in earnings reports and often overlook nuances that influence market movements. This paper introduces an advanced approach by employing Large Language Models (LLMs) instruction fine-tuned with a novel combination of instruction-based techniques and quantized low-rank adaptation (QLoRA) compression. Our methodology integrates 'base factors', such as financial metric growth and earnings transcripts, with 'external factors', including recent market indices performances and analyst grades, to create a rich, supervised dataset. This comprehensive dataset enables our models to achieve superior predictive performance in terms of accuracy, weighted F1, and Matthews correlation coefficient (MCC), especially evident in the comparison with benchmarks such as GPT-4. We specifically highlight the efficacy of the llama-3-8b-Instruct-4bit model, which showcases significant improvements over baseline models. The paper also discusses the potential of expanding the output capabilities to include a 'Hold' option and extending the prediction horizon, aiming to accommodate various investment styles and time frames. This study not only demonstrates the power of integrating cutting-edge AI with fine-tuned financial data but also paves the way for future research in enhancing AI-driven financial analysis tools. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.06634 |
| By: | Gregory Yampolsky; Dhruv Desai; Mingshu Li; Stefano Pasquali; Dhagash Mehta |
| Abstract: | The explainability of black-box machine learning algorithms, commonly known as Explainable Artificial Intelligence (XAI), has become crucial for financial and other regulated industrial applications due to regulatory requirements and the need for transparency in business practices. Among the various paradigms of XAI, Explainable Case-Based Reasoning (XCBR) stands out as a pragmatic approach that elucidates the output of a model by referencing actual examples from the data used to train or test the model. Despite its potential, XCBR has been relatively underexplored for many algorithms such as tree-based models until recently. We start by observing that most XCBR methods are defined based on the distance metric learned by the algorithm. By utilizing a recently proposed technique to extract the distance metric learned by Random Forests (RFs), which is both geometry- and accuracy-preserving, we investigate various XCBR methods. These methods amount to identify special points from the training datasets, such as prototypes, critics, counter-factuals, and semi-factuals, to explain the predictions for a given query of the RF. We evaluate these special points using various evaluation metrics to assess their explanatory power and effectiveness. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.06679 |
| By: | Wee Ling Tan; Stephen Roberts; Stefan Zohren |
| Abstract: | We introduce a novel approach to options trading strategies using a highly scalable and data-driven machine learning algorithm. In contrast to traditional approaches that often require specifications of underlying market dynamics or assumptions on an option pricing model, our models depart fundamentally from the need for these prerequisites, directly learning non-trivial mappings from market data to optimal trading signals. Backtesting on more than a decade of option contracts for equities listed on the S&P 100, we demonstrate that deep learning models trained according to our end-to-end approach exhibit significant improvements in risk-adjusted performance over existing rules-based trading strategies. We find that incorporating turnover regularization into the models leads to further performance enhancements at prohibitively high levels of transaction costs. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.21791 |
| By: | Jian-Qiao Zhu; Joshua C. Peterson; Benjamin Enke; Thomas L. Griffiths |
| Abstract: | Understanding how people behave in strategic settings--where they make decisions based on their expectations about the behavior of others--is a long-standing problem in the behavioral sciences. We conduct the largest study to date of strategic decision-making in the context of initial play in two-player matrix games, analyzing over 90, 000 human decisions across more than 2, 400 procedurally generated games that span a much wider space than previous datasets. We show that a deep neural network trained on these data predicts people's choices better than leading theories of strategic behavior, indicating that there is systematic variation that is not explained by those theories. We then modify the network to produce a new, interpretable behavioral model, revealing what the original network learned about people: their ability to optimally respond and their capacity to reason about others are dependent on the complexity of individual games. This context-dependence is critical in explaining deviations from the rational Nash equilibrium, response times, and uncertainty in strategic decisions. More broadly, our results demonstrate how machine learning can be applied beyond prediction to further help generate novel explanations of complex human behavior. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.07865 |
| By: | Andras Komaromi; Xiaomin Wu; Ran Pan; Yang Liu; Pablo Cisneros; Anchal Manocha; Hiba El Oirghi |
| Abstract: | The International Monetary Fund (IMF) has expanded its online learning program, offering over 100 Massive Open Online Courses (MOOCs) to support economic and financial policymaking worldwide. This paper explores the application of Artificial Intelligence (AI), specifically Large Language Models (LLMs), to analyze qualitative feedback from participants in these courses. By fine-tuning a pre-trained LLM on expert-annotated text data, we develop models that efficiently classify open-ended survey responses with accuracy comparable to human coders. The models’ robust performance across multiple languages, including English, French, and Spanish, demonstrates its versatility. Key insights from the analysis include a preference for shorter, modular content, with variations across genders, and the significant impact of language barriers on learning outcomes. These and other findings from unstructured learner feedback inform the continuous improvement of the IMF's online courses, aligning with its capacity development goals to enhance economic and financial expertise globally. |
| Keywords: | IMF Economics training; measuring training impact; learner feedback; application of artificial intelligence; learner satisfaction; Artificial intelligence; Machine learning; Information systems and platforms; Automation; Sub-Saharan Africa; Western Hemisphere; Middle East and Central Asia; Europe; Asia and Pacific |
| Date: | 2024–08–02 |
| URL: | https://d.repec.org/n?u=RePEc:imf:imfwpa:2024/166 |
| By: | Julian Ashwin; Paul Beaudry; Martin Ellison |
| Abstract: | Neural networks offer a promising tool for the analysis of nonlinear economies. In this paper, we derive conditions for the global stability of nonlinear rational expectations equilibria under neural network learning. We demonstrate the applicability of the conditions in analytical and numerical examples where the nonlinearity is caused by monetary policy targeting a range, rather than a specific value, of inflation. If shock persistence is high or there is inertia in the structure of the economy, then the only rational expectations equilibria that are learnable may involve inflation spending long periods outside its target range. Neural network learning is also useful for solving and selecting between multiple equilibria and steady states in other settings, such as when there is a zero lower bound on the nominal interest rate. |
| JEL: | C45 E19 E47 |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:32807 |
| By: | Thiago Christiano Silva; Paulo Victor Berri Wilhelm; Diego Raphael Amancio |
| Abstract: | This study examines the effects of deglobalization trends on international trade networks and their role in improving forecasts for economic growth. Using section-level trade data from more than 200 countries from 2010 to 2022, we identify significant shifts in the network topology driven by rising trade policy uncertainty. Our analysis highlights key global players through centrality rankings, with the United States, China, and Germany maintaining consistent dominance. Using a horse race of supervised regressors, we find that network topology descriptors evaluated from section-specific trade networks substantially enhance the quality of a country's economic growth forecast. We also find that non-linear models, such as Random Forest, eXtreme Gradient Boosting, and Light Gradient Boosting Machine, outperform traditional linear models used in the economics literature. Using SHapley Additive exPlanations values to interpret these non-linear model's predictions, we find that about half of the most important features originate from the network descriptors, underscoring their vital role in refining forecasts. Moreover, this study emphasizes the significance of recent economic performance, population growth, and the primary sector's influence in shaping economic growth predictions, offering novel insights into the intricacies of economic growth forecasting. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:bcb:wpaper:597 |
| By: | Hué, Sullivan (Aix-Marseille University - Aix-Marseille School of Economics); Hurlin, Christophe (University of Orleans); Pérignon, Christophe (HEC Paris); Saurin, Sébastien (University of Orleans, Laboratoire d'économie d'Orléans, Students) |
| Abstract: | In credit scoring, machine learning models are known to outperform standard parametric models. As they condition access to credit, banking supervisors and internal model validation teams need to monitor their predictive performance and to identify the features with the highest impact on performance. To facilitate this, we introduce the XPER methodology to decompose a performance metric (e.g., AUC, R^2) into specific contributions associated with the various features of a classification or regression model. XPER is theoretically grounded on Shapley values and is both model-agnostic and performance metric-agnostic. Furthermore, it can be implemented either at the model level or at the individual level. Using a novel dataset of car loans, we decompose the AUC of a machine-learning model trained to forecast the default probability of loan applicants. We show that a small number of features can explain a surprisingly large part of the model performance. Furthermore, we find that the features that contribute the most to the predictive performance of the model may not be the ones that contribute the most to individual forecasts (SHAP). We also show how XPER can be used to deal with heterogeneity issues and significantly boost out-of-sample performance. |
| Keywords: | Machine learning; Explainability; Performance metric; Shapley value |
| JEL: | C40 C52 |
| Date: | 2022–11–22 |
| URL: | https://d.repec.org/n?u=RePEc:ebg:heccah:1463 |
| By: | Jon Danielsson; Andreas Uthemann |
| Abstract: | The rapid adoption of artificial intelligence (AI) is transforming the financial industry. AI will either increase systemic financial risk or act to stabilise the system, depending on endogenous responses, strategic complementarities, the severity of events it faces and the objectives it is given. AI's ability to master complexity and respond rapidly to shocks means future crises will likely be more intense than those we have seen so far. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.17048 |
| By: | Bhaskarjit Sarmah; Benika Hall; Rohan Rao; Sunil Patel; Stefano Pasquali; Dhagash Mehta |
| Abstract: | Extraction and interpretation of intricate information from unstructured text data arising in financial applications, such as earnings call transcripts, present substantial challenges to large language models (LLMs) even using the current best practices to use Retrieval Augmented Generation (RAG) (referred to as VectorRAG techniques which utilize vector databases for information retrieval) due to challenges such as domain specific terminology and complex formats of the documents. We introduce a novel approach based on a combination, called HybridRAG, of the Knowledge Graphs (KGs) based RAG techniques (called GraphRAG) and VectorRAG techniques to enhance question-answer (Q&A) systems for information extraction from financial documents that is shown to be capable of generating accurate and contextually relevant answers. Using experiments on a set of financial earning call transcripts documents which come in the form of Q&A format, and hence provide a natural set of pairs of ground-truth Q&As, we show that HybridRAG which retrieves context from both vector database and KG outperforms both traditional VectorRAG and GraphRAG individually when evaluated at both the retrieval and generation stages in terms of retrieval accuracy and answer generation. The proposed technique has applications beyond the financial domain |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.04948 |
| By: | Jianqing Fan; Weining Wang; Yue Zhao |
| Abstract: | High-dimensional covariates often admit linear factor structure. To effectively screen correlated covariates in high-dimension, we propose a conditional variable screening test based on non-parametric regression using neural networks due to their representation power. We ask the question whether individual covariates have additional contributions given the latent factors or more generally a set of variables. Our test statistics are based on the estimated partial derivative of the regression function of the candidate variable for screening and a observable proxy for the latent factors. Hence, our test reveals how much predictors contribute additionally to the non-parametric regression after accounting for the latent factors. Our derivative estimator is the convolution of a deep neural network regression estimator and a smoothing kernel. We demonstrate that when the neural network size diverges with the sample size, unlike estimating the regression function itself, it is necessary to smooth the partial derivative of the neural network estimator to recover the desired convergence rate for the derivative. Moreover, our screening test achieves asymptotic normality under the null after finely centering our test statistics that makes the biases negligible, as well as consistency for local alternatives under mild conditions. We demonstrate the performance of our test in a simulation study and two real world applications. |
| Date: | 2024–08–21 |
| URL: | https://d.repec.org/n?u=RePEc:azt:cemmap:17/24 |
| By: | Brian Jabarian |
| Abstract: | In this article, we explore the transformative potential of integrating generative AI, particularly Large Language Models (LLMs), into behavioral and experimental economics to enhance internal validity. By leveraging AI tools, researchers can improve adherence to key exclusion restrictions and in particular ensure the internal validity measures of mental models, which often require human intervention in the incentive mechanism. We present a case study demonstrating how LLMs can enhance experimental design, participant engagement, and the validity of measuring mental models. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.12032 |
| By: | Yuheng Zheng; Zihan Ding |
| Abstract: | This paper establishes a new and comprehensive theoretical analysis for the application of reinforcement learning (RL) in high-frequency market making. We bridge the modern RL theory and the continuous-time statistical models in high-frequency financial economics. Different with most existing literature on methodological research about developing various RL methods for market making problem, our work is a pilot to provide the theoretical analysis. We target the effects of sampling frequency, and find an interesting tradeoff between error and complexity of RL algorithm when tweaking the values of the time increment $\Delta$ $-$ as $\Delta$ becomes smaller, the error will be smaller but the complexity will be larger. We also study the two-player case under the general-sum game framework and establish the convergence of Nash equilibrium to the continuous-time game equilibrium as $\Delta\rightarrow0$. The Nash Q-learning algorithm, which is an online multi-agent RL method, is applied to solve the equilibrium. Our theories are not only useful for practitioners to choose the sampling frequency, but also very general and applicable to other high-frequency financial decision making problems, e.g., optimal executions, as long as the time-discretization of a continuous-time markov decision process is adopted. Monte Carlo simulation evidence support all of our theories. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.21025 |
| By: | Ugo Bolletta; Laurens Cherchye; Thomas Demuynck; Bram De Rock; Luca Paolo Merlino |
| Abstract: | We propose a method to identify individuals’ marriage markets assuming that observed marriages are stable. We aim to learn about (the relative importance of) the individual’s observable characteristics defining these markets. First, we use a nonparametric revealed preference approach to construct inner and outer bound approximations of these markets from observed marriages. We then use machine learning to estimate arobust boundary between them (as a linear function of individual characteristics). We demonstrate the usefulness of our method using Dutch household data and quantify the trade-off between the characteristics such as age, education and wages defining individuals’ marriage markets. |
| Keywords: | marriage market, identification, revealed preferences, machine learning, support vector machine (SVM). |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:eca:wpaper:2013/376857 |
| By: | Sergiy Tkachuk; Szymon {\L}ukasik; Anna Wr\'oblewska |
| Abstract: | In the rapidly evolving domain of large-scale retail data systems, envisioning and simulating future consumer transactions has become a crucial area of interest. It offers significant potential to fortify demand forecasting and fine-tune inventory management. This paper presents an innovative application of Generative Adversarial Networks (GANs) to generate synthetic retail transaction data, specifically focusing on a novel system architecture that combines consumer behavior modeling with stock-keeping unit (SKU) availability constraints to address real-world assortment optimization challenges. We diverge from conventional methodologies by integrating SKU data into our GAN architecture and using more sophisticated embedding methods (e.g., hyper-graphs). This design choice enables our system to generate not only simulated consumer purchase behaviors but also reflects the dynamic interplay between consumer behavior and SKU availability -- an aspect often overlooked, among others, because of data scarcity in legacy retail simulation models. Our GAN model generates transactions under stock constraints, pioneering a resourceful experimental system with practical implications for real-world retail operation and strategy. Preliminary results demonstrate enhanced realism in simulated transactions measured by comparing generated items with real ones using methods employed earlier in related studies. This underscores the potential for more accurate predictive modeling. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.03655 |
| By: | Dawid, Herbert; Harting, Philipp; Hoog, Sander van der; Neugart, Michael |
| Abstract: | The Eurace@Unibi model is a multi-region macroeconomic simulation model that has been developed with the goal to provide a platform with strong micro-foundations for economic policy analysis in a variety of policy domains. The model builds on work carried out during the European project EURACE ("An agent-based software platform for European economic policy design with heterogeneous interacting agents"), which was funded from 2006 to 2009 as part of the European Union's 6th Framework Programme. Since then, it has been substantially extended and further developed. |
| Date: | 2024–08–12 |
| URL: | https://d.repec.org/n?u=RePEc:dar:wpaper:149219 |
| By: | Jaehyuk Choi; Lilian Hu; Yue Kuen Kwok |
| Abstract: | We propose an efficient and reliable simulation scheme for the stochastic-alpha-beta-rho (SABR) model. The two challenges of the SABR simulation lie in sampling (i) the integrated variance conditional on terminal volatility and (ii) the terminal price conditional on terminal volatility and integrated variance. For the first sampling procedure, we analytically derive the first four moments of the conditional average variance, and sample it from the moment-matched shifted lognormal approximation. For the second sampling procedure, we approximate the conditional terminal price as a constant-elasticity-of-variance (CEV) distribution. Our CEV approximation preserves the martingale condition and precludes arbitrage, which is a key advantage over Islah's approximation used in most SABR simulation schemes in the literature. Then, we adopt the exact sampling method of the CEV distribution based on the shifted-Poisson-mixture Gamma random variable. Our enhanced procedures avoid the tedious Laplace inversion algorithm for sampling integrated variance and non-efficient inverse transform sampling of the forward price in some of the earlier simulation schemes. Numerical results demonstrate our simulation scheme to be highly efficient, accurate, and reliable. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.01898 |
| By: | Margherita Borella; Francisco A. Bullano; Mariacristina De Nardi; Benjamin Krueger; Elena Manresa |
| Abstract: | While health affects many economic outcomes, its dynamics are still poorly understood. We use k means clustering, a machine learning technique, and data from the Health and Retirement Study to identify health types during middle and old age. We identify five health types: the vigorous resilient, the fair-health resilient, the fair-health vulnerable, the frail resilient, and the frail vulnerable. They are characterized by different starting health and health and mortality trajectories. Our five health types account for 84% of the variation in health trajectories and are not explained by observable characteristics, such as age, marital status, education, gender, race, health-related behaviors, and health insurance status, but rather, by one’s past health dynamics. We also show that health types are important drivers of health and mortality heterogeneity and dynamics. Our results underscore the importance of better understanding health type formation and of modeling it appropriately to properly evaluate the effects of health on people’s decisions and the implications of policy reforms. |
| JEL: | I1 |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:32799 |
| By: | Klatt, Nikolina |
| Abstract: | How do judicial decisions influence political discourse, particularly in areas as contentious as abortion rights? This study investigates how the overturning of Roe v. Wade affected the narrative strategies of U.S. representatives on social media, focusing on variations by party affiliation and geography. While there is literature on the influence of judicial decisions on public opinion and policy, the effect on political narratives remains underexplored. To address this gap, the study analyzes 5, 293 tweets from U.S. representatives in 2022 by supervised text classification and statistical modeling to identify shifts in narrative strategies. The study found the leaked opinion draft acted as a catalyst, which prompted an increase in stories of decline-narratives that emphasize a worsening situation-particularly for Republicans. This study provides empirical evidence of how political narratives evolve in response to landmark judicial changes and insights into the strategic use of narratives by political actors in digital communication. |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:wzbtod:301155 |
| By: | Norbert Pfeifer (University of Graz, Austria); Miriam Steurer (University of Graz, Austria) |
| Abstract: | Penalized regression splines provide a flexible way to model spatial variation in real estate prices. However, when extrapolating to areas without data support, splines tend to "overshoot" and produce highly implausible estimates. Such data-poor locations are often of particular interest in urban economics (e.g., parks or beaches), as they can be used to infer the value of amenities. We introduce a spline construction method that addresses this overshooting problem by introducing helper point values in data gap areas prior to estimating the penalized regression spline surface. We estimate these helper point values using a decision-tree-based algorithm (XGBoost) that can effectively cluster and average local price levels. We find that the introduction of helper points eliminates the overshooting behavior in data gap areas, while preserving the flexibility of the spline surface elsewhere. We illustrate our approach using data for new apartment transactions in Vienna, Austria in 2020. |
| Keywords: | Real Estate Prices, Price Surface, Penalized Regression Splines, Spatial Machine Learning. |
| JEL: | C14 C43 C45 R31 C51 |
| Date: | 2024–04 |
| URL: | https://d.repec.org/n?u=RePEc:grz:wpaper:2024-11 |