|
on Computational Economics |
| By: | Alicia Vidler; Toby Walsh |
| Abstract: | We introduce a novel hybrid approach that augments Agent-Based Models (ABMs) with behaviors generated by Large Language Models (LLMs) to simulate human trading interactions. We call our model TraderTalk. Leveraging LLMs trained on extensive human-authored text, we capture detailed and nuanced representations of bilateral conversations in financial trading. Applying this Generative Agent-Based Model (GABM) to government bond markets, we replicate trading decisions between two stylised virtual humans. Our method addresses both structural challenges, such as coordinating turn-taking between realistic LLM-based agents, and design challenges, including the interpretation of LLM outputs by the agent model. By exploring prompt design opportunistically rather than systematically, we enhance the realism of agent interactions without exhaustive overfitting or model reliance. Our approach successfully replicates trade-to-order volume ratios observed in related asset markets, demonstrating the potential of LLM-augmented ABMs in financial simulations |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.21280 |
| By: | Saber Talazadeh; Dragan Perakovic |
| Abstract: | Stock trend forecasting, a challenging problem in the financial domain, involves ex-tensive data and related indicators. Relying solely on empirical analysis often yields unsustainable and ineffective results. Machine learning researchers have demonstrated that the application of random forest algorithm can enhance predictions in this context, playing a crucial auxiliary role in forecasting stock trends. This study introduces a new approach to stock market prediction by integrating sentiment analysis using FinGPT generative AI model with the traditional Random Forest model. The proposed technique aims to optimize the accuracy of stock price forecasts by leveraging the nuanced understanding of financial sentiments provided by FinGPT. We present a new methodology called "Sentiment-Augmented Random Forest" (SARF), which in-corporates sentiment features into the Random Forest framework. Our experiments demonstrate that SARF outperforms conventional Random Forest and LSTM models with an average accuracy improvement of 9.23% and lower prediction errors in pre-dicting stock market movements. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.07143 |
| By: | Jesús Fernández-Villaverde; Galo Nuño; Jesse Perla |
| Abstract: | We argue that deep learning provides a promising avenue for taming the curse of dimensionality in quantitative economics. We begin by exploring the unique challenges posed by solving dynamic equilibrium models, especially the feedback loop between individual agents' decisions and the aggregate consistency conditions required by equilibrium. Following this, we introduce deep neural networks and demonstrate their application by solving the stochastic neoclassical growth model. Next, we compare deep neural networks with traditional solution methods in quantitative economics. We conclude with a survey of neural network applications in quantitative economics and offer reasons for cautious optimism. |
| JEL: | C61 C63 E27 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:33117 |
| By: | Yi Zheng; Zehao Li; Peng Jiang; Yijie Peng |
| Abstract: | We study the dynamic pricing and replenishment problems under inconsistent decision frequencies. Different from the traditional demand assumption, the discreteness of demand and the parameter within the Poisson distribution as a function of price introduce complexity into analyzing the problem property. We demonstrate the concavity of the single-period profit function with respect to product price and inventory within their respective domains. The demand model is enhanced by integrating a decision tree-based machine learning approach, trained on comprehensive market data. Employing a two-timescale stochastic approximation scheme, we address the discrepancies in decision frequencies between pricing and replenishment, ensuring convergence to local optimum. We further refine our methodology by incorporating deep reinforcement learning (DRL) techniques and propose a fast-slow dual-agent DRL algorithm. In this approach, two agents handle pricing and inventory and are updated on different scales. Numerical results from both single and multiple products scenarios validate the effectiveness of our methods. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.21109 |
| By: | Arya Chakraborty; Auhona Basu |
| Abstract: | The financial domain presents a complex environment for stock market prediction, characterized by volatile patterns and the influence of multifaceted data sources. Traditional models have leveraged either Convolutional Neural Networks (CNN) for spatial feature extraction or Long Short-Term Memory (LSTM) networks for capturing temporal dependencies, with limited integration of external textual data. This paper proposes a novel Two-Level Conv-LSTM Neural Network integrated with a Large Language Model (LLM) for comprehensive stock advising. The model harnesses the strengths of Conv-LSTM for analyzing time-series data and LLM for processing and understanding textual information from financial news, social media, and reports. In the first level, convolutional layers are employed to identify local patterns in historical stock prices and technical indicators, followed by LSTM layers to capture the temporal dynamics. The second level integrates the output with an LLM that analyzes sentiment and contextual information from textual data, providing a holistic view of market conditions. The combined approach aims to improve prediction accuracy and provide contextually rich stock advising. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.12807 |
| By: | Koen Ponse; Aske Plaat; Niki van Stein; Thomas M. Moerland |
| Abstract: | Accurate economic simulations often require many experimental runs, particularly when combined with reinforcement learning. Unfortunately, training reinforcement learning agents in multi-agent economic environments can be slow. This paper introduces EconoJax, a fast simulated economy, based on the AI economist. EconoJax, and its training pipeline, are completely written in JAX. This allows EconoJax to scale to large population sizes and perform large experiments, while keeping training times within minutes. Through experiments with populations of 100 agents, we show how real-world economic behavior emerges through training within 15 minutes, in contrast to previous work that required several days. To aid and inspire researchers to build more rich and dynamic economic simulations, we open-source EconoJax on Github at: https://github.com/ponseko/econojax. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.22165 |
| By: | Kei Nakagawa; Masanori Hirano; Yugo Fujimoto |
| Abstract: | This study aims to evaluate the sentiment of financial texts using large language models~(LLMs) and to empirically determine whether LLMs exhibit company-specific biases in sentiment analysis. Specifically, we examine the impact of general knowledge about firms on the sentiment measurement of texts by LLMs. Firstly, we compare the sentiment scores of financial texts by LLMs when the company name is explicitly included in the prompt versus when it is not. We define and quantify company-specific bias as the difference between these scores. Next, we construct an economic model to theoretically evaluate the impact of sentiment bias on investor behavior. This model helps us understand how biased LLM investments, when widespread, can distort stock prices. This implies the potential impact on stock prices if investments driven by biased LLMs become dominant in the future. Finally, we conduct an empirical analysis using Japanese financial text data to examine the relationship between firm-specific sentiment bias, corporate characteristics, and stock performance. |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2411.00420 |
| By: | Sotiris Tsolacos; Tatiana Franus |
| Abstract: | In this paper we study the performance of a range of methodologies to forecast real estate prices. We compare the forecast accuracy of econometric and time series models to machine learning algorithms. The target series is the yield impact a metric which is based on changes in yields (cap rates) and a prime determinant of capital value or price changes (appreciation returns). We focus on the main sectors – offices, retail and industrials – in the UK and we perform the analysis with monthly data taken from MSCI. Using monthly MSCI data results in a sample that begins in 1987. The econometric and time series models include ARMA, ARMAX, stepwise and Lasso regressions. Machine learning methods include random forest, XGBoost, and support vector machines. We use a large set of economic, financial and survey data to predict movements in yield impact. We assess the forecast performance of the selected methodologies over different time horizons, one, three, six, and twelve months. The forecast evaluation follows conventional forecast evaluation metrics. This includes basic measures such as the mean error, mean absolute error and RMSE and more sophisticated measures such Diebold-Mariano tests. We are particularly interested in forecasting gains arising from the combination of forecasts from different methods.The results have significant practical value. The forecast assessment can pick up directional changes and be used for price discovery. Real estate data in the private market are produced with a lag (even monthly data) and early information about changes in prices are valuable to real estate investors and lenders. The study aims to identify the methods or the combination of methods with the best predictive ability and focus investor attention to these methods. |
| Keywords: | econometric models; forecasting assessment; Machine Learning; Property pricing |
| JEL: | R3 |
| Date: | 2024–01–01 |
| URL: | https://d.repec.org/n?u=RePEc:arz:wpaper:eres2024-251 |
| By: | Ji Ma |
| Abstract: | As Large Language Model (LLM)-based agents increasingly undertake real-world tasks and engage with human society, how well do we understand their behaviors? This study (1) investigates how LLM agents' prosocial behaviors -- a fundamental social norm -- can be induced by different personas and benchmarked against human behaviors; and (2) introduces a behavioral approach to evaluate the performance of LLM agents in complex decision-making scenarios. We explored how different personas and experimental framings affect these AI agents' altruistic behavior in dictator games and compared their behaviors within the same LLM family, across various families, and with human behaviors. Our findings reveal substantial variations and inconsistencies among LLMs and notable differences compared to human behaviors. Merely assigning a human-like identity to LLMs does not produce human-like behaviors. Despite being trained on extensive human-generated data, these AI agents cannot accurately predict human decisions. LLM agents are not able to capture the internal processes of human decision-making, and their alignment with human behavior is highly variable and dependent on specific model architectures and prompt formulations; even worse, such dependence does not follow a clear pattern. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.21359 |
| By: | Yuan Gao; Dokyun Lee; Gordon Burtch; Sina Fazelpour |
| Abstract: | Recent studies suggest large language models (LLMs) can exhibit human-like reasoning, aligning with human behavior in economic experiments, surveys, and political discourse. This has led many to propose that LLMs can be used as surrogates or simulations for humans in social science research. However, LLMs differ fundamentally from humans, relying on probabilistic patterns, absent the embodied experiences or survival objectives that shape human cognition. We assess the reasoning depth of LLMs using the 11-20 money request game. Nearly all advanced approaches fail to replicate human behavior distributions across many models. Causes of failure are diverse and unpredictable, relating to input language, roles, and safeguarding. These results advise caution when using LLMs to study human behavior or as surrogates or simulations. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.19599 |
| By: | Ruyi Tao; Kaiwei Liu; Xu Jing; Jiang Zhang |
| Abstract: | Predicting company growth is crucial for strategic adjustment, operational decision-making, risk assessment, and loan eligibility reviews. Traditional models for company growth often focus too much on theory, overlooking practical forecasting, or they rely solely on time series forecasting techniques, ignoring interpretability and the inherent mechanisms of company growth. In this paper, we propose a machine learning-based prediction framework that incorporates an econophysics model for company growth. Our model captures both the intrinsic growth mechanisms of companies led by scaling laws and the fluctuations influenced by random factors and individual decisions, demonstrating superior predictive performance compared with methods that use time series techniques alone. Its advantages are more pronounced in long-range prediction tasks. By explicitly modeling the baseline growth and volatility components, our model is more interpretable. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.17587 |
| By: | Michel F. C. Haddad; Martin Huber; Lucas Z. Zhang |
| Abstract: | We propose a difference-in-differences (DiD) method for a time-varying continuous treatment and multiple time periods. Our framework assesses the average treatment effect on the treated (ATET) when comparing two non-zero treatment doses. The identification is based on a conditional parallel trend assumption imposed on the mean potential outcome under the lower dose, given observed covariates and past treatment histories. We employ kernel-based ATET estimators for repeated cross-sections and panel data adopting the double/debiased machine learning framework to control for covariates and past treatment histories in a data-adaptive manner. We also demonstrate the asymptotic normality of our estimation approach under specific regularity conditions. In a simulation study, we find a compelling finite sample performance of undersmoothed versions of our estimators in setups with several thousand observations. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.21105 |