|
on Computational Economics |
| By: | Paulo Barbosa; João Cortes; João Amador (ISEG - University of Lisbon and Portugal Trade & Investment; Portugal Trade & Investment; Banco de Portugal and Nova SBE) |
| Abstract: | This paper estimates how distant a firm is from becoming a successful exporter. The empirical exercise uses very rich data for Portuguese firms and assumes that there are non-trivial determinants to distinguish between exporters and non-exporters. An array of machine learning models - Bayesian Additive Regression Tree (BART), Missingness not at Random (BART-MIA), Random Forest, Logit Regression and Neural Networks – are trained to predict firms’ export probability and shed light on the critical factors driving the transition to successful export ventures. Neural Networks outperform the other techniques and remain highly accurate when we change the export definitions and the training and testing strategies. We show that the most influential variables for prediction are labour productivity, firms’ goods and services imports, capital intensity and wages. |
| Keywords: | Machine learning, Forecasting exporters, Trade promotion, Micro level data, Portugal |
| JEL: | F17 C53 C55 L21 |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:mde:wpaper:182 |
| By: | Yuqi Nie; Yaxuan Kong; Xiaowen Dong; John M. Mulvey; H. Vincent Poor; Qingsong Wen; Stefan Zohren |
| Abstract: | Recent advances in large language models (LLMs) have unlocked novel opportunities for machine learning applications in the financial domain. These models have demonstrated remarkable capabilities in understanding context, processing vast amounts of data, and generating human-preferred contents. In this survey, we explore the application of LLMs on various financial tasks, focusing on their potential to transform traditional practices and drive innovation. We provide a discussion of the progress and advantages of LLMs in financial contexts, analyzing their advanced technologies as well as prospective capabilities in contextual understanding, transfer learning flexibility, complex emotion detection, etc. We then highlight this survey for categorizing the existing literature into key application areas, including linguistic tasks, sentiment analysis, financial time series, financial reasoning, agent-based modeling, and other applications. For each application area, we delve into specific methodologies, such as textual analysis, knowledge-based analysis, forecasting, data augmentation, planning, decision support, and simulations. Furthermore, a comprehensive collection of datasets, model assets, and useful codes associated with mainstream applications are presented as resources for the researchers and practitioners. Finally, we outline the challenges and opportunities for future research, particularly emphasizing a number of distinctive aspects in this field. We hope our work can help facilitate the adoption and further development of LLMs in the financial sector. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.11903 |
| By: | Zhouzhou Gu; Mathieu Lauri\`ere; Sebastian Merkel; Jonathan Payne |
| Abstract: | We propose and compare new global solution algorithms for continuous time heterogeneous agent economies with aggregate shocks. First, we approximate the agent distribution so that equilibrium in the economy can be characterized by a high, but finite, dimensional non-linear partial differential equation. We consider different approximations: discretizing the number of agents, discretizing the agent state variables, and projecting the distribution onto a finite set of basis functions. Second, we represent the value function using a neural network and train it to solve the differential equation using deep learning tools. We refer to the solution as an Economic Model Informed Neural Network (EMINN). The main advantage of this technique is that it allows us to find global solutions to high dimensional, non-linear problems. We demonstrate our algorithm by solving important models in the macroeconomics and spatial literatures (e.g. Krusell and Smith (1998), Khan and Thomas (2007), Bilal (2023)). |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.13726 |
| By: | Haibo Wang; Lutfu S. Sua; Bahram Alidaee |
| Abstract: | This study tackles the complexities of global supply chains, which are increasingly vulnerable to disruptions caused by port congestion, material shortages, and inflation. To address these challenges, we explore the application of machine learning methods, which excel in predicting and optimizing solutions based on large datasets. Our focus is on enhancing supply chain security through fraud detection, maintenance prediction, and material backorder forecasting. We introduce an automated machine learning framework that streamlines data analysis, model construction, and hyperparameter optimization for these tasks. By automating these processes, our framework improves the efficiency and effectiveness of supply chain security measures. Our research identifies key factors that influence machine learning performance, including sampling methods, categorical encoding, feature selection, and hyperparameter optimization. We demonstrate the importance of considering these factors when applying machine learning to supply chain challenges. Traditional mathematical programming models often struggle to cope with the complexity of large-scale supply chain problems. Our study shows that machine learning methods can provide a viable alternative, particularly when dealing with extensive datasets and complex patterns. The automated machine learning framework presented in this study offers a novel approach to supply chain security, contributing to the existing body of knowledge in the field. Its comprehensive automation of machine learning processes makes it a valuable contribution to the domain of supply chain management. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.13166 |
| By: | Natalia Roszyk (University of Warsaw, Faculty of Economic Sciences, Quantitative Finance Research Group); Robert Ślepaczuk (University of Warsaw, Faculty of Economic Sciences, Quantitative Finance Research Group, Department of Quantitative Finance and Machine Learning) |
| Abstract: | Predicting the S&P 500 index's volatility is crucial for investors and financial analysts as it helps in assessing market risk and making informed investment decisions. Volatility represents the level of uncertainty or risk related to the size of changes in a security's value, making it an essential indicator for financial planning. This study explores four methods to improve the accuracy of volatility forecasts for the S&P 500: the established GARCH model, known for capturing historical volatility patterns; an LSTM network that utilizes past volatility and log returns; a hybrid LSTM-GARCH model that combines the strengths of both approaches; and an advanced version of the hybrid model that also factors in the VIX index to gauge market sentiment. This analysis is based on a daily dataset that includes data for S&P 500 and VIX index, covering the period from January 3, 2000, to December 21, 2023. Through rigorous testing and comparison, we found that machine learning approaches, particularly the hybrid LSTM models, significantly outperform the traditional GARCH model. The inclusion of the VIX index in the hybrid model further enhances its forecasting ability by incorporating real-time market sentiment. The results of this study offer valuable insights for achieving more accurate volatility predictions, enabling better risk management and strategic investment decisions in the volatile environment of the S&P 500. |
| Keywords: | volatility forecasting, LSTM-GARCH, S&P 500 index, hybrid forecasting models, VIX index, machine learning, financial time series analysis, walk-forward process, hyperparameters tuning, deep learning, recurrent neural networks |
| JEL: | C4 C45 C55 C65 G11 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:war:wpaper:2024-13 |
| By: | Liyang Wang; Yu Cheng; Ao Xiang; Jingyu Zhang; Haowei Yang |
| Abstract: | This paper explores the application of Natural Language Processing (NLP) in financial risk detection. By constructing an NLP-based financial risk detection model, this study aims to identify and predict potential risks in financial documents and communications. First, the fundamental concepts of NLP and its theoretical foundation, including text mining methods, NLP model design principles, and machine learning algorithms, are introduced. Second, the process of text data preprocessing and feature extraction is described. Finally, the effectiveness and predictive performance of the model are validated through empirical research. The results show that the NLP-based financial risk detection model performs excellently in risk identification and prediction, providing effective risk management tools for financial institutions. This study offers valuable references for the field of financial risk management, utilizing advanced NLP techniques to improve the accuracy and efficiency of financial risk detection. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.09765 |
| By: | Ayato Kitadai; Sinndy Dayana Rico Lugo; Yudai Tsurusaki; Yusuke Fukasawa; Nariaki Nishino |
| Abstract: | Economic experiments offer a controlled setting for researchers to observe human decision-making and test diverse theories and hypotheses; however, substantial costs and efforts are incurred to gather many individuals as experimental participants. To address this, with the development of large language models (LLMs), some researchers have recently attempted to develop simulated economic experiments using LLMs-driven agents, called generative agents. If generative agents can replicate human-like decision-making in economic experiments, the cost problem of economic experiments can be alleviated. However, such a simulation framework has not been yet established. Considering the previous research and the current evolutionary stage of LLMs, this study focuses on the reasoning ability of generative agents as a key factor toward establishing a framework for such a new methodology. A multi-agent simulation, designed to improve the reasoning ability of generative agents through prompting methods, was developed to reproduce the result of an actual economic experiment on the ultimatum game. The results demonstrated that the higher the reasoning ability of the agents, the closer the results were to the theoretical solution than to the real experimental result. The results also suggest that setting the personas of the generative agents may be important for reproducing the results of real economic experiments. These findings are valuable for the future definition of a framework for replacing human participants with generative agents in economic experiments when LLMs are further developed. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.11426 |
| By: | Philipp Schwarz; Oliver Schacht; Sven Klaassen; Daniel Gr\"unbaum; Sebastian Imhof; Martin Spindler |
| Abstract: | In this paper, we present a data-driven model for estimating optimal rework policies in manufacturing systems. We consider a single production stage within a multistage, lot-based system that allows for optional rework steps. While the rework decision depends on an intermediate state of the lot and system, the final product inspection, and thus the assessment of the actual yield, is delayed until production is complete. Repair steps are applied uniformly to the lot, potentially improving some of the individual items while degrading others. The challenge is thus to balance potential yield improvement with the rework costs incurred. Given the inherently causal nature of this decision problem, we propose a causal model to estimate yield improvement. We apply methods from causal machine learning, in particular double/debiased machine learning (DML) techniques, to estimate conditional treatment effects from data and derive policies for rework decisions. We validate our decision model using real-world data from opto-electronic semiconductor manufacturing, achieving a yield improvement of 2 - 3% during the color-conversion process of white light-emitting diodes (LEDs). |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.11308 |
| By: | Ruohan Zhan; Shichao Han; Yuchen Hu; Zhenling Jiang |
| Abstract: | Recommender systems are essential for content-sharing platforms by curating personalized content. To evaluate updates of recommender systems targeting content creators, platforms frequently engage in creator-side randomized experiments to estimate treatment effect, defined as the difference in outcomes when a new (vs. the status quo) algorithm is deployed on the platform. We show that the standard difference-in-means estimator can lead to a biased treatment effect estimate. This bias arises because of recommender interference, which occurs when treated and control creators compete for exposure through the recommender system. We propose a "recommender choice model" that captures how an item is chosen among a pool comprised of both treated and control content items. By combining a structural choice model with neural networks, the framework directly models the interference pathway in a microfounded way while accounting for rich viewer-content heterogeneity. Using the model, we construct a double/debiased estimator of the treatment effect that is consistent and asymptotically normal. We demonstrate its empirical performance with a field experiment on Weixin short-video platform: besides the standard creator-side experiment, we carry out a costly blocked double-sided randomization design to obtain a benchmark estimate without interference bias. We show that the proposed estimator significantly reduces the bias in treatment effect estimates compared to the standard difference-in-means estimator. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.14380 |
| By: | Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany); Aviral K. Tiwari (Indian Institute of Management Bodh Gaya, Bodh Gaya, India) |
| Abstract: | We use random forests, a machine-learning technique, to formally examine the link between real gasoline prices and presidential approval ratings of the United States (US). Random forests make it possible to study this link in a completely data-driven way, such that nonlinearities in the data can easily be detected and a large number of control variables, in line with the extant literature, can be considered. Our empirical findings show that the link between real gasoline prices and the presidential approval ratings is indeed nonlinear, and that the former even has predictive value in an out-of-sample exercise for the latter. We argue that our findings are in line with the so-called pocketbook mechanism, which stipulates that the presidential approval ratings depend on gasoline prices because the latter have sizable impact on personal economic situations of voters. |
| Keywords: | Presidential approval ratings, Gasoline price, Random forests, Forecasting |
| JEL: | C22 C53 Q40 Q43 |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:pre:wpaper:202427 |
| By: | Samuel Atkins; Ali Fathi; Sammy Assefa |
| Abstract: | A corporate bond trader in a typical sell side institution such as a bank provides liquidity to the market participants by buying/selling securities and maintaining an inventory. Upon receiving a request for a buy/sell price quote (RFQ), the trader provides a quote by adding a spread over a \textit{prevalent market price}. For illiquid bonds, the market price is harder to observe, and traders often resort to available benchmark bond prices (such as MarketAxess, Bloomberg, etc.). In \cite{Bergault2023ModelingLI}, the concept of \textit{Fair Transfer Price} for an illiquid corporate bond was introduced which is derived from an infinite horizon stochastic optimal control problem (for maximizing the trader's expected P\&L, regularized by the quadratic variation). In this paper, we consider the same optimization objective, however, we approach the estimation of an optimal bid-ask spread quoting strategy in a data driven manner and show that it can be learned using Reinforcement Learning. Furthermore, we perform extensive outcome analysis to examine the reasonableness of the trained agent's behavior. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.12983 |
| By: | Eric AVENEL (Univ Rennes, CNRS, CREM – UMR6211, F-35000 Rennes France) |
| Abstract: | The successive Cournot oligopoly model presented in Salinger (1988) is very popular in the literature on vertical relations. There is however a problem in this model, since the assumption of elastic supply on the intermediate market is inconsistent with the assumption that upstream firms choose their output before downstream firms place their orders. I show that dropping the assumption of elastic supply on the intermediate market and complementing the model with a well chosen allocation rule - the competitive rule of Cho and Tang (2014) - restores the validity of the results in Salinger (1988) and the subsequent contributions using the same model. |
| Keywords: | Cournot competition, successive oligopoly, allocation rule. |
| JEL: | L13 |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:tut:cremwp:2024-02 |
| By: | Mihaela Nistor |
| Abstract: | Keynote Remarks at the XLoD Global – New York Conference, New York City. |
| Keywords: | risk management; artificial intelligence (AI) |
| Date: | 2024–06–11 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fednsp:98431 |
| By: | Cantone, Giulio Giacomo |
| Abstract: | Similarity between two categories is a number between 0 and 1 that abstractally represent how much the two categories overlap, objectively or subjectively. When two categories overlap, the error of classification of one to other is less severe. For example, misclassifying a wolf for dog is a less severe error than misclassifying a wolf for a cat, because wolf are more similar to dogs than cats. Nevertheless, canonical estimation of matrices of similarities for taxonomies of categories is expensive. In this protocol it is suggested why and how to estimate a similarity matrix from one or multiple Large Language Models. |
| Date: | 2024–06–06 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:d9egt |
| By: | Carlo Drago (University Niccolò Cusano) |
| Abstract: | Within the more relevant data science topics, text mining is an important and active research area that offers various ways to extract information and insights from text data. Its continued use and improvement could drive innovation in several areas and improve our ability to interpret, evaluate, and utilize the vast amounts of unstructured text produced in the digital age. Extracting insightful information from text data through text mining in healthcare and business holds great promise. Text mining in business can provide insightful information by analyzing large amounts of text data, including research papers, news, and Fnancial reports. It can help analyze market sentiment, identify emerging trends, and more accurately predict economic indicators by economists. For example, economists can Fnd terms or phrases that reQect investment behavior and sentiment changes by applying text-mining methods to Fnancial news. Text mining can provide essential insights into health economics by examining various textual data, including patient surveys, clinical trials, medical records, and health policy. Researchers and policymakers can use it to understand healthcare utilization patterns better, identify the variables that inQuence patient outcomes, and evaluate the effectiveness of different healthcare treatments. Text mining can examine electronic health data and identify trends in disease incidence, treatment effectiveness, and healthcare utilization. In this presentation, I will illustrate the instruments currently available in Stata to facilitate several text- mining methods. |
| Date: | 2024–05–09 |
| URL: | https://d.repec.org/n?u=RePEc:boc:isug24:10 |
| By: | Olivier Guéant (UP1 - Université Paris 1 Panthéon-Sorbonne) |
| Date: | 2022–11–25 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-04590381 |
| By: | Linn Engstr\"om; Sigrid K\"allblad; Johan Karlsson |
| Abstract: | We introduce an efficient computational framework for solving a class of multi-marginal martingale optimal transport problems, which includes many robust pricing problems of large financial interest. Such problems are typically computationally challenging due to the martingale constraint, however, by extending the state space we can identify them with problems that exhibit a certain sequential martingale structure. Our method exploits such structures in combination with entropic regularisation, enabling fast computation of optimal solutions and allowing us to solve problems with a large number of marginals. We demonstrate the method by using it for computing robust price bounds for different options, such as lookback options and Asian options. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.09959 |
| By: | Baciu, Dan Costa (Architektur Studio Bellerive) |
| Abstract: | In a previous article, we studied how a newly planned light rail in Tel Aviv may affect experienced urban diversity. Our method involved computing isochrones before and after the completion of the light rail, and, based on isochrones and urban data, estimating how the introduction of the light rail was expected to change how people experienced urban diversity. Technically, the estimation process was performed through diversity computations and data processing with Neural Networks. As part of the present conference contribution, we shift the focus to Wellington, NZ. We study and compare multiple initiatives to increase urban mobility in Wellington, estimating how each of them may impact the urban diversity that can be experienced in the city. We compare in particular the light rail project abandoned in late 2023 with options to increase mobility through bike lanes. We also envision a system of autonomous vehicles to perform share rides and compare its effects with those of the other two options. While the options that we discuss remain hypothetical, they allow us to open a discussion on how changes in urban mobility effectuated through enhancement of different modes of transportation that work at different speeds may affect urban diversity, specifically in Wellington. |
| Date: | 2024–06–17 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:w87yb |
| By: | Matheus V. X. Ferreira; Aadityan Ganesh; Jack Hourigan; Hannah Huh; S. Matthew Weinberg; Catherine Yu |
| Abstract: | Cryptographic Self-Selection is a paradigm employed by modern Proof-of-Stake consensus protocols to select a block-proposing "leader." Algorand [Chen and Micali, 2019] proposes a canonical protocol, and Ferreira et al. [2022] establish bounds $f(\alpha, \beta)$ on the maximum fraction of rounds a strategic player can lead as a function of their stake $\alpha$ and a network connectivity parameter $\beta$. While both their lower and upper bounds are non-trivial, there is a substantial gap between them (for example, they establish $f(10\%, 1) \in [10.08\%, 21.12\%]$), leaving open the question of how significant of a concern these manipulations are. We develop computational methods to provably nail $f(\alpha, \beta)$ for any desired $(\alpha, \beta)$ up to arbitrary precision, and implement our method on a wide range of parameters (for example, we confirm $f(10\%, 1) \in [10.08\%, 10.15\%]$). Methodologically, estimating $f(\alpha, \beta)$ can be phrased as estimating to high precision the value of a Markov Decision Process whose states are countably-long lists of real numbers. Our methodological contributions involve (a) reformulating the question instead as computing to high precision the expected value of a distribution that is a fixed-point of a non-linear sampling operator, and (b) provably bounding the error induced by various truncations and sampling estimations of this distribution (which appears intractable to solve in closed form). One technical challenge, for example, is that natural sampling-based estimates of the mean of our target distribution are \emph{not} unbiased estimators, and therefore our methods necessarily go beyond claiming sufficiently-many samples to be close to the mean. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.15282 |