|
on Big Data |
| By: | Jingyang Wu; Xinyi Zhang; Fangyixuan Huang; Haochen Zhou; Rohtiash Chandra |
| Abstract: | There has been much interest in accurate cryptocurrency price forecast models by investors and researchers. Deep Learning models are prominent machine learning techniques that have transformed various fields and have shown potential for finance and economics. Although various deep learning models have been explored for cryptocurrency price forecasting, it is not clear which models are suitable due to high market volatility. In this study, we review the literature about deep learning for cryptocurrency price forecasting and evaluate novel deep learning models for cryptocurrency stock price prediction. Our deep learning models include variants of long short-term memory (LSTM) recurrent neural networks, variants of convolutional neural networks (CNNs), and the Transformer model. We evaluate univariate and multivariate approaches for multi-step ahead predicting of cryptocurrencies close-price. Our results show that the univariate LSTM model variants perform best for cryptocurrency predictions. We also carry out volatility analysis on the four cryptocurrencies which reveals significant fluctuations in their prices throughout the COVID-19 pandemic. Additionally, we investigate the prediction accuracy of two scenarios identified by different training sets for the models. First, we use the pre-COVID-19 datasets to model cryptocurrency close-price forecasting during the early period of COVID-19. Secondly, we utilise data from the COVID-19 period to predict prices for 2023 to 2024. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.11431&r= |
| By: | Wolff, Dominik; Echterling, Fabian |
| Abstract: | We analyze machine learning algorithms for stock selection. Our study builds on weekly data for the historical constituents of the S&P500 over the period from January 1999 to March 2021 and builds on typical equity factors, additional firm fundamentals, and technical indicators. A variety of machine learning models are trained on the binary classification task to predict whether a specific stock outperforms or underperforms the cross‐sectional median return over the subsequent week. We analyze weekly trading strategies that invest in stocks with the highest predicted outperformance probability. Our empirical results show substantial and significant outperformance of machine learning‐based stock selection models compared to an equally weighted benchmark. Interestingly, we find more simplistic regularized logistic regression models to perform similarly well compared to more complex machine learning models. The results are robust when applied to the STOXX Europe 600 as alternative asset universe. |
| Date: | 2024–05–28 |
| URL: | https://d.repec.org/n?u=RePEc:dar:wpaper:145491&r= |
| By: | Tänzer, Alina |
| Abstract: | This paper contributes a multivariate forecasting comparison between structural models and Machine-Learning-based tools. Specifically, a fully connected feed forward nonlinear autoregressive neural network (ANN) is contrasted to a well established dynamic stochastic general equilibrium (DSGE) model, a Bayesian vector autoregression (BVAR) using optimized priors as well as Greenbook and SPF forecasts. Model estimation and forecasting is based on an expanding window scheme using quarterly U.S. real-time data (1964Q2:2020Q3) for 8 macroeconomic time series (GDP, inflation, federal funds rate, spread, consumption, investment, wage, hours worked), allowing for up to 8 quarter ahead forecasts. The results show that the BVAR improves forecasts compared to the DSGE model, however there is evidence for an overall improvement of predictions when relying on ANN, or including them in a weighted average. Especially, ANNbased inflation forecasts improve other predictions by up to 50%. These results indicate that nonlinear data-driven ANNs are a useful method when it comes to macroeconomic forecasting. |
| Keywords: | Artificial Intelligence, Machine Learning, Neural Networks, Forecast Comparison/ Competition, Macroeconomic Forecasting, Crises Forecasting, Inflation Forecasting, Interest Rate Forecasting, Production, Saving, Consumption and Investment Forecasting |
| Date: | 2024 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:imfswp:295733&r= |
| By: | Michael Lechner; Jana Mareckova |
| Abstract: | Uncovering causal effects at various levels of granularity provides substantial value to decision makers. Comprehensive machine learning approaches to causal effect estimation allow to use a single causal machine learning approach for estimation and inference of causal mean effects for all levels of granularity. Focusing on selection-on-observables, this paper compares three such approaches, the modified causal forest (mcf), the generalized random forest (grf), and double machine learning (dml). It also provides proven theoretical guarantees for the mcf and compares the theoretical properties of the approaches. The findings indicate that dml-based methods excel for average treatment effects at the population level (ATE) and group level (GATE) with few groups, when selection into treatment is not too strong. However, for finer causal heterogeneity, explicitly outcome-centred forest-based approaches are superior. The mcf has three additional benefits: (i) It is the most robust estimator in cases when dml-based approaches underperform because of substantial selectivity; (ii) it is the best estimator for GATEs when the number of groups gets larger; and (iii), it is the only estimator that is internally consistent, in the sense that low-dimensional causal ATEs and GATEs are obtained as aggregates of finer-grained causal parameters. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.10198&r= |
| By: | Yuji Sakurai; Zhuohui Chen |
| Abstract: | We propose a new machine-learning-based approach for forecasting Value-at-Risk (VaR) named CoFiE-NN where a neural network (NN) is combined with Cornish-Fisher expansions (CoFiE). CoFiE-NN can capture non-linear dynamics of high-order statistical moments thanks to the flexibility of a NN while maintaining interpretability of the outputs by using CoFiE which is a well-known statistical formula. First, we explain CoFiE-NN. Second, we compare the forecasting performance of CoFiE-NN with three conventional models using both Monte Carlo simulation and real data. To do so, we employ Long Short-Term Memory (LSTM) as our main specification of the NN. We then apply the CoFiE-NN for different asset classes, with a focus on foreign exchange markets. We report that CoFiE-NN outperfoms the conventional EGARCH-t model and the Extreme Value Theory model in several statistical criteria for both the simulated data and the real data. Finally, we introduce a new empirical proxy for tail risk named tail risk ratio under CoFiE-NN. We discover that the only 20 percent of tail risk dynamics across 22 currencies is explained by one common factor. This is contrasting to the fact that 60 percent of volatility dynamics across the same currencies is explained by one common factor. |
| Keywords: | Machine learning; Value-at-Risk; Neural Network |
| Date: | 2024–05–10 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imfwpa:2024/099&r= |
| By: | Huiyu Li; Junhua Hu |
| Abstract: | Stock price prediction has always been a difficult task for forecasters. Using cutting-edge deep learning techniques, stock price prediction based on investor sentiment extracted from online forums has become feasible. We propose a novel hybrid deep learning framework for predicting stock prices. The framework leverages the XLNET model to analyze the sentiment conveyed in user posts on online forums, combines these sentiments with the post popularity factor to compute daily group sentiments, and integrates this information with stock technical indicators into an improved BiLSTM-highway model for stock price prediction. Through a series of comparative experiments involving four stocks on the Chinese stock market, it is demonstrated that the hybrid framework effectively predicts stock prices. This study reveals the necessity of analyzing investors' textual views for stock price prediction. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.10584&r= |
| By: | Despotovic, Miroslav (University of Applied Sciences Kufstein, Tirol, Austria); Glatschke, Matthias |
| Abstract: | The inherent "take-make-waste" of the current linear economy is a major contributor to exceeding planetary boundaries. The transition to a circular economy (CE) and the associated challenges and opportunities require fast, innovative solutions. Artificial Intelligence (AI) and Machine Learning (ML) can play a key role in the transition to a CE paradigm by overcoming the challenges of increasing material extraction and use and creating a far more environmentally sustainable future. The objective of this article is to provide a status quo on the use of AI and ML in the transition to CE and to discuss the potential and challenges in this regard. The literature survey on Google Scholar using targeted queries with predefined keywords and search operators revealed that the number of experimental scientific contributions to AI and ML in the CE has increased significantly in recent years. As the number of research articles increased, so did the number of ML methods and algorithms covered in experimental CE publications. In addition, we found that there are 84% more AI and ML-affiliated research articles on CE in Google Scholar since 2020, compared to the total number of entries, and 55% more articles since 2023, compared to the respective articles up to 2023. The status quo of the scientific contributions shows that AI and ML are seen as extremely useful tools for the CE and their use is steadily increasing. |
| Date: | 2024–05–26 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:6qmhf&r= |
| By: | Raeid Saqur; Ken Kato; Nicholas Vinden; Frank Rudzicz |
| Abstract: | We introduce and make publicly available the NIFTY Financial News Headlines dataset, designed to facilitate and advance research in financial market forecasting using large language models (LLMs). This dataset comprises two distinct versions tailored for different modeling approaches: (i) NIFTY-LM, which targets supervised fine-tuning (SFT) of LLMs with an auto-regressive, causal language-modeling objective, and (ii) NIFTY-RL, formatted specifically for alignment methods (like reinforcement learning from human feedback (RLHF)) to align LLMs via rejection sampling and reward modeling. Each dataset version provides curated, high-quality data incorporating comprehensive metadata, market indices, and deduplicated financial news headlines systematically filtered and ranked to suit modern LLM frameworks. We also include experiments demonstrating some applications of the dataset in tasks like stock price movement and the role of LLM embeddings in information acquisition/richness. The NIFTY dataset along with utilities (like truncating prompt's context length systematically) are available on Hugging Face at https://huggingface.co/datasets/raeidsaq ur/NIFTY. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.09747&r= |
| By: | Jiahao Weng; Yan Xie |
| Abstract: | In this study, we constructed daily high-frequency sentiment data and used the VAR method to attempt to predict the next day's implied volatility surface. We utilized 630, 000 text data entries from the East Money Stock Forum from 2014 to 2023 and employed deep learning methods such as BERT and LSTM to build daily market sentiment indicators. By applying FFT and EMD methods for sentiment decomposition, we found that high-frequency sentiment had a stronger correlation with at-the-money (ATM) options' implied volatility, while low-frequency sentiment was more strongly correlated with deep out-of-the-money (DOTM) options' implied volatility. Further analysis revealed that the shape of the implied volatility surface contains richer market sentiment information beyond just market panic. We demonstrated that incorporating this sentiment information can improve the accuracy of implied volatility surface predictions. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.11730&r= |
| By: | Daniel Aromí (IIEP UBA-Conicet/FCE UBA); Daniel Heymann (IIEP UBA-Conicet/FCE UBA) |
| Abstract: | We propose a method to generate “synthetic surveys” that shed light on policymakers’ perceptions and narratives. This exercise is implemented using 80 time-stamped Large Language Models (LLMs) fine-tuned with FOMC meetings’ transcripts. Given a text input, finetuned models identify highly likely responses for the corresponding FOMC meeting. We evaluate this tool in three different tasks: sentiment analysis, evaluation of transparency in Central Bank communication and characterization of policymaking narratives. Our analysis covers the housing bubble and the subsequent Great Recession (2003-2012). For the first task, LLMs are prompted to generate phrases that describe economic conditions. The resulting output is verified to transmit policymakers’ information regarding macroeconomic and financial dynamics. To analyze transparency, we compare the content of each FOMC minutes to content generated synthetically through the corresponding fine-tuned LLM. The evaluation suggests the tone of each meeting is transmitted adequately by the corresponding minutes. In the third task, we show LLMs produce insightul depictions of evolving policymaking narratives. Thisanalysis reveals relevant narratives’ features such as goals, perceived threats, identified macroeconomic drivers, categorizations of the state of the economy and manifestations of emotional states. |
| Keywords: | Monetary policy, large language models, narratives, transparency. |
| Date: | 2024–05 |
| URL: | https://d.repec.org/n?u=RePEc:aoz:wpaper:323&r= |
| By: | Buczak, Philip |
| Abstract: | Ordinal responses commonly occur in the life sciences, e.g., through school grades or rating scales. Where traditionally parametric statistical models have been used, machine learning (ML) methods such as random forest (RF) are increasingly employed for ordinal prediction. As RF does not account for ordinality, several extensions have been proposed. A promising approach lies in assigning optimized numeric scores to the ordinal response categories and using regression RF. However, these optimization procedures are computationally expensive and have been shown to yield only situational benefit. In this work, I propose Frequency Adjusted Borders Ordinal Forest (fabOF), a novel tree ensemble method for ordinal prediction forgoing extensive optimization while offering improved predictive performance in simulation and an illustrative example of student performance. |
| Date: | 2024–05–15 |
| URL: | http://d.repec.org/n?u=RePEc:osf:osfxxx:h8t4p&r= |
| By: | Kasy, Maximilian (University of Oxford) |
| Abstract: | This chapter discusses the regulation of artificial intelligence (AI) from the vantage point of political economy, based on the following premises: (i) AI systems maximize a single, measurable objective. (ii) In society, different individuals have different objectives. AI systems generate winners and losers. (iii) Society-level assessments of AI require trading off individual gains and losses. (iv) AI requires democratic control of algorithms, data, and computational infrastructure, to align algorithm objectives and social welfare. The chapter addresses several debates regarding the ethics and social impact of AI, including (i) fairness, discrimination, and inequality, (ii) privacy, data property rights, and data governance, (iii) value alignment and the impending robot apocalypse, (iv) explainability and accountability for automated decision-making, and (v) automation and the impact of AI on the labor market and on wage inequality. |
| Keywords: | AI, machine learning, regulation, fairness, privacy, value alignment, explain-ability, automation |
| JEL: | P00 O3 |
| Date: | 2024–04 |
| URL: | http://d.repec.org/n?u=RePEc:iza:izadps:dp16948&r= |
| By: | Krist\'of N\'emeth; D\'aniel Hadh\'azi |
| Abstract: | Recent results in the literature indicate that artificial neural networks (ANNs) can outperform the dynamic factor model (DFM) in terms of the accuracy of GDP nowcasts. Compared to the DFM, the performance advantage of these highly flexible, nonlinear estimators is particularly evident in periods of recessions and structural breaks. From the perspective of policy-makers, however, nowcasts are the most useful when they are conveyed with uncertainty attached to them. While the DFM and other classical time series approaches analytically derive the predictive (conditional) distribution for GDP growth, ANNs can only produce point nowcasts based on their default training procedure (backpropagation). To fill this gap, first in the literature, we adapt two different deep learning algorithms that enable ANNs to generate density nowcasts for U.S. GDP growth: Bayes by Backprop and Monte Carlo dropout. The accuracy of point nowcasts, defined as the mean of the empirical predictive distribution, is evaluated relative to a naive constant growth model for GDP and a benchmark DFM specification. Using a 1D CNN as the underlying ANN architecture, both algorithms outperform those benchmarks during the evaluation period (2012:Q1 -- 2022:Q4). Furthermore, both algorithms are able to dynamically adjust the location (mean), scale (variance), and shape (skew) of the empirical predictive distribution. The results indicate that both Bayes by Backprop and Monte Carlo dropout can effectively augment the scope and functionality of ANNs, rendering them a fully compatible and competitive alternative for classical time series approaches. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.15579&r= |
| By: | Colin D. Grab |
| Abstract: | While research of reinforcement learning applied to financial markets predominantly concentrates on finding optimal behaviours, it is worth to realize that the reinforcement learning returns $G_t$ and state value functions themselves are of interest and play a pivotal role in the evaluation of assets. Instead of focussing on the more complex task of finding optimal decision rules, this paper studies and applies the power of distributional state value functions in the context of financial market valuation and machine learning based trading algorithms. Accurate and trustworthy estimates of the distributions of $G_t$ provide a competitive edge leading to better informed decisions and more optimal behaviour. Herein, ideas from predictive knowledge and deep reinforcement learning are combined to introduce a novel family of models called CDG-Model, resulting in a highly flexible framework and intuitive approach with minimal assumptions regarding underlying distributions. The models allow seamless integration of typical financial modelling pitfalls like transaction costs, slippage and other possible costs or benefits into the model calculation. They can be applied to any kind of trading strategy or asset class. The frameworks introduced provide concrete business value through their potential in market valuation of single assets and portfolios, in the comparison of strategies as well as in the improvement of market timing. They can positively impact the performance and enhance the learning process of existing or new trading algorithms. They are of interest from a scientific point-of-view and open up multiple areas of future research. Initial implementations and tests were performed on real market data. While the results are promising, applying a robust statistical framework to evaluate the models in general remains a challenge and further investigations are needed. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.11686&r= |
| By: | Theodoros Zafeiriou; Dimitris Kalles |
| Abstract: | Our study focuses on comparing the performance and resource requirements between different Long Short-Term Memory (LSTM) neural network architectures and an ANN specialized architecture for forex market prediction. We analyze the execution time of the models as well as the resources consumed, such as memory and computational power. Our aim is to demonstrate that the specialized architecture not only achieves better results in forex market prediction but also executes using fewer resources and in a shorter time frame compared to LSTM architectures. This comparative analysis will provide significant insights into the suitability of these two types of architectures for time series prediction in the forex market environment. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.10679&r= |
| By: | Kentaro Hoffman; Stephen Salerno; Jeff Leek; Tyler McCormick |
| Abstract: | Large-scale prediction models (typically using tools from artificial intelligence, AI, or machine learning, ML) are increasingly ubiquitous across a variety of industries and scientific domains. Such methods are often paired with detailed data from sources such as electronic health records, wearable sensors, and omics data (high-throughput technology used to understand biology). Despite their utility, implementing AI and ML tools at the scale necessary to work with this data introduces two major challenges. First, it can cost tens of thousands of dollars to train a modern AI/ML model at scale. Second, once the model is trained, its predictions may become less relevant as patient and provider behavior change, and predictions made for one geographical area may be less accurate for another. These two challenges raise a fundamental question: how often should you refit the AI/ML model to optimally trade-off between cost and relevance? Our work provides a framework for making decisions about when to {\it refit} AI/ML models when the goal is to maintain valid statistical inference (e.g. estimating a treatment effect in a clinical trial). Drawing on portfolio optimization theory, we treat the decision of {\it recalibrating} versus {\it refitting} the model as a choice between ''investing'' in one of two ''assets.'' One asset, recalibrating the model based on another model, is quick and relatively inexpensive but bears uncertainty from sampling and the possibility that the other model is not relevant to current circumstances. The other asset, {\it refitting} the model, is costly but removes the irrelevance concern (though not the risk of sampling error). We explore the balancing act between these two potential investments in this paper. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.13926&r= |
| By: | Yu Cheng; Qin Yang; Liyang Wang; Ao Xiang; Jingyu Zhang |
| Abstract: | In the realm of globalized financial markets, commercial banks are confronted with an escalating magnitude of credit risk, thereby imposing heightened requisites upon the security of bank assets and financial stability. This study harnesses advanced neural network techniques, notably the Backpropagation (BP) neural network, to pioneer a novel model for preempting credit risk in commercial banks. The discourse initially scrutinizes conventional financial risk preemptive models, such as ARMA, ARCH, and Logistic regression models, critically analyzing their real-world applications. Subsequently, the exposition elaborates on the construction process of the BP neural network model, encompassing network architecture design, activation function selection, parameter initialization, and objective function construction. Through comparative analysis, the superiority of neural network models in preempting credit risk in commercial banks is elucidated. The experimental segment selects specific bank data, validating the model's predictive accuracy and practicality. Research findings evince that this model efficaciously enhances the foresight and precision of credit risk management. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.10762&r= |
| By: | Jordan G. Taqi-Eddin |
| Abstract: | Claims of soft-handed prosecutorial policies and increases in crime were precipitating factors in the removal of Chesa Boudin as district attorney of the city and county of San Francisco. However, little research has been conducted to empirically investigate the veracity of these indictments on the former district attorney. Using regression discontinuity design (RDD), I find that the Boudin administration led to a 36\% and 21\% reduction in monthly prosecutions and convictions respectively for all crimes. Moreover, his tenure increased monthly successful case diversions by 58\%. When only looking at violent crimes during this period, the SFDA's office saw a 36\% decrease, 7\% decrease, and 47\% increase in monthly prosecutions, convictions, and successful case diversions respectively. Although, the decrease in monthly convictions was not statistically significant for the violent crimes subset. Additionally, I did identify a potentially causal relationship between lower numbers of prosecutions and higher levels of criminal activity, however, such findings did not meet the standard for statistical significance. Finally, I conclude that using machine learning algorithms, such as neural networks and K-nearest neighbors, in place of ordinary least squares regression for the estimation of the reduced form equation possibly may decrease the size of the standard errors of the parameters in the structural equation. However, future research needs to be conducted in this space to corroborate these initially promising findings. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.11455&r= |
| By: | Lisa Bruttel (University of Potsdam, Berlin School of Economics, CEPA); Maximilian Andres (University of Potsdam, Berlin School of Economics, CEPA) |
| Abstract: | While the economic harm of cartels is caused by their price-increasing effect, sanctioning by courts rather targets at the underlying process of firms reaching a price-fixing agreement. This paper provides experimental evidence on the question whether such sanctioning meets the economic target, i.e., whether evidence of a collusive meeting of the firms and of the content of their communication reliably predicts subsequent prices. We find that already the mere mutual agreement to meet predicts a strong increase in prices. Conversely, express distancing from communication completely nullifies its otherwise price-increasing effect. Using machine learning, we show that communication only increases prices if it is very explicit about how the cartel plans to behave. |
| Keywords: | cartel, collusion, communication, machine learning, experiment |
| JEL: | C92 D43 L44 |
| Date: | 2024–05 |
| URL: | https://d.repec.org/n?u=RePEc:pot:cepadp:77&r= |
| By: | Tom S\"uhr; Samira Samadi; Chiara Farronato |
| Abstract: | Machine learning (ML) models are increasingly used in various applications, from recommendation systems in e-commerce to diagnosis prediction in healthcare. In this paper, we present a novel dynamic framework for thinking about the deployment of ML models in a performative, human-ML collaborative system. In our framework, the introduction of ML recommendations changes the data generating process of human decisions, which are only a proxy to the ground truth and which are then used to train future versions of the model. We show that this dynamic process in principle can converge to different stable points, i.e. where the ML model and the Human+ML system have the same performance. Some of these stable points are suboptimal with respect to the actual ground truth. We conduct an empirical user study with 1, 408 participants to showcase this process. In the study, humans solve instances of the knapsack problem with the help of machine learning predictions. This is an ideal setting because we can see how ML models learn to imitate human decisions and how this learning process converges to a stable point. We find that for many levels of ML performance, humans can improve the ML predictions to dynamically reach an equilibrium performance that is around 92% of the maximum knapsack value. We also find that the equilibrium performance could be even higher if humans rationally followed the ML recommendations. Finally, we test whether monetary incentives can increase the quality of human decisions, but we fail to find any positive effect. Our results have practical implications for the deployment of ML models in contexts where human decisions may deviate from the indisputable ground truth. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.13753&r= |
| By: | Pranjal Rawat |
| Abstract: | In some markets, the visual appearance of a product matters a lot. This paper investigates consumer transactions from a major fashion retailer, focusing on consumer aesthetics. Pretrained multimodal models convert images and text descriptions into high-dimensional embeddings. The value of these embeddings is verified both empirically and by their ability to segment the product space. A discrete choice model is used to decompose the distinct drivers of consumer choice: price, visual aesthetics, descriptive details, and seasonal variations. Consumers are allowed to differ in their preferences over these factors, both through observed variation in demographics and allowing for unobserved types. Estimation and inference employ automatic differentiation and GPUs, making it scalable and portable. The model reveals significant differences in price sensitivity and aesthetic preferences across consumers. The model is validated by its ability to predict the relative success of new designs and purchase patterns. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.10498&r= |
| By: | Yu Xia; Sriram Narayanamoorthy; Zhengyuan Zhou; Joshua Mabry |
| Abstract: | The development of open benchmarking platforms could greatly accelerate the adoption of AI agents in retail. This paper presents comprehensive simulations of customer shopping behaviors for the purpose of benchmarking reinforcement learning (RL) agents that optimize coupon targeting. The difficulty of this learning problem is largely driven by the sparsity of customer purchase events. We trained agents using offline batch data comprising summarized customer purchase histories to help mitigate this effect. Our experiments revealed that contextual bandit and deep RL methods that are less prone to over-fitting the sparse reward distributions significantly outperform static policies. This study offers a practical framework for simulating AI agents that optimize the entire retail customer journey. It aims to inspire the further development of simulation tools for retail AI systems. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.10469&r= |
| By: | Gang Hu; Ming Gu |
| Abstract: | Investment portfolios, central to finance, balance potential returns and risks. This paper introduces a hybrid approach combining Markowitz's portfolio theory with reinforcement learning, utilizing knowledge distillation for training agents. In particular, our proposed method, called KDD (Knowledge Distillation DDPG), consist of two training stages: supervised and reinforcement learning stages. The trained agents optimize portfolio assembly. A comparative analysis against standard financial models and AI frameworks, using metrics like returns, the Sharpe ratio, and nine evaluation indices, reveals our model's superiority. It notably achieves the highest yield and Sharpe ratio of 2.03, ensuring top profitability with the lowest risk in comparable return scenarios. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.05449&r= |
| By: | Hongyang Yang; Boyu Zhang; Neng Wang; Cheng Guo; Xiaoli Zhang; Likun Lin; Junlin Wang; Tianyu Zhou; Mao Guan; Runjia Zhang; Christina Dan Wang |
| Abstract: | As financial institutions and professionals increasingly incorporate Large Language Models (LLMs) into their workflows, substantial barriers, including proprietary data and specialized knowledge, persist between the finance sector and the AI community. These challenges impede the AI community's ability to enhance financial tasks effectively. Acknowledging financial analysis's critical role, we aim to devise financial-specialized LLM-based toolchains and democratize access to them through open-source initiatives, promoting wider AI adoption in financial decision-making. In this paper, we introduce FinRobot, a novel open-source AI agent platform supporting multiple financially specialized AI agents, each powered by LLM. Specifically, the platform consists of four major layers: 1) the Financial AI Agents layer that formulates Financial Chain-of-Thought (CoT) by breaking sophisticated financial problems down into logical sequences; 2) the Financial LLM Algorithms layer dynamically configures appropriate model application strategies for specific tasks; 3) the LLMOps and DataOps layer produces accurate models by applying training/fine-tuning techniques and using task-relevant data; 4) the Multi-source LLM Foundation Models layer that integrates various LLMs and enables the above layers to access them directly. Finally, FinRobot provides hands-on for both professional-grade analysts and laypersons to utilize powerful AI techniques for advanced financial analysis. We open-source FinRobot at \url{https://github.com/AI4Finance-Found ation/FinRobot}. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.14767&r= |
| By: | Gorny, Paul M.; Groos, Eva; Strobel, Christina |
| Abstract: | Regulators of artificial intelligence (AI) emphasize the importance of human autonomy and oversight in AI-assisted decision-making (European Commission, Directorate-General for Communications Networks, Content and Technology, 2021; 117th Congress, 2022). Predictions are the foundation of all AI tools; thus, if AI can predict our decisions, how might these predictions influence our ultimate choices? We examine how salient, personalized AI predictions affect decision outcomes and investigate the role of reactance, i.e., an adverse reaction to a perceived reduction in individual freedom. We trained an AI tool on previous dictator game decisions to generate personalized predictions of dictators’ choices. In our AI treatment, dictators received this prediction before deciding. In a treatment involving human oversight, the decision of whether participants in our experiment were provided with the AI prediction was made by a previous participant (a ‘human overseer’). In the baseline, participants did not receive the prediction. We find that participants sent less to the recipient when they received a personalized prediction but the strongest reduction occurred when the AI’s prediction was intentionally not shared by the human overseer. Our findings underscore the importance of considering human reactions to AI predictions in assessing the accuracy and impact of these tools as well as the potential adverse effects of human oversight. |
| Keywords: | Artificial intelligence, Predictions, Decision-making, Reactance, Free will |
| JEL: | C90 C91 D01 O33 |
| Date: | 2024–05–24 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:121065&r= |
| By: | David Ardia; Keven Bluteau |
| Abstract: | We propose an approach to construct text-based time-series indices in an optimal way--typically, indices that maximize the contemporaneous relation or the predictive performance with respect to a target variable, such as inflation. We illustrate our methodology with a corpus of news articles from the Wall Street Journal by optimizing text-based indices focusing on tracking the VIX index and inflation expectations. Our results highlight the superior performance of our approach compared to existing indices. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.10449&r= |
| By: | Yunfei Peng; Pengyu Wei; Wei Wei |
| Abstract: | We propose a deep learning algorithm for high dimensional optimal stopping problems. Our method is inspired by the penalty method for solving free boundary PDEs. Within our approach, the penalized PDE is approximated using the Deep BSDE framework proposed by \cite{weinan2017deep}, which leads us to coin the term "Deep Penalty Method (DPM)" to refer to our algorithm. We show that the error of the DPM can be bounded by the loss function and $O(\frac{1}{\lambda})+O(\lambda h) +O(\sqrt{h})$, where $h$ is the step size in time and $\lambda$ is the penalty parameter. This finding emphasizes the need for careful consideration when selecting the penalization parameter and suggests that the discretization error converges at a rate of order $\frac{1}{2}$. We validate the efficacy of the DPM through numerical tests conducted on a high-dimensional optimal stopping model in the area of American option pricing. The numerical tests confirm both the accuracy and the computational efficiency of our proposed algorithm. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.11392&r= |
| By: | Maximilian N\"agele; Jan Olle; Thomas F\"osel; Remmy Zen; Florian Marquardt |
| Abstract: | Markov decision processes (MDPs) are used to model a wide variety of applications ranging from game playing over robotics to finance. Their optimal policy typically maximizes the expected sum of rewards given at each step of the decision process. However, a large class of problems does not fit straightforwardly into this framework: Non-cumulative Markov decision processes (NCMDPs), where instead of the expected sum of rewards, the expected value of an arbitrary function of the rewards is maximized. Example functions include the maximum of the rewards or their mean divided by their standard deviation. In this work, we introduce a general mapping of NCMDPs to standard MDPs. This allows all techniques developed to find optimal policies for MDPs, such as reinforcement learning or dynamic programming, to be directly applied to the larger class of NCMDPs. Focusing on reinforcement learning, we show applications in a diverse set of tasks, including classical control, portfolio optimization in finance, and discrete optimization problems. Given our approach, we can improve both final performance and training time compared to relying on standard MDPs. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.13609&r= |