nep-cmp New Economics Papers
on Computational Economics
Issue of 2023‒06‒12
fifteen papers chosen by
Stan Miles
Thompson Rivers University

  1. How to address monotonicity for model risk management? By Dangxing Chen; Weicheng Ye
  2. Deep learning of Value at Risk through generative neural network models : the case of the Variational Auto Encoder By Pierre Brugière; Gabriel Turinici
  3. Autoempleo y Machine Learning: Una aplicación para España By Gutierrez-Lythgoe, Antonio
  4. Hedonic prices and quality adjusted price indices powered by AI By Patrick Bajari; Zhihao Cen; Victor Chernozhukov; Manoj Manukonda; Jin Wang; Ramon Huerta; Junbo Li; Ling Leng; George Monokroussos; Suhas Vijaykunar; Shan Wan
  5. Predicting the Price Movement of Cryptocurrencies Using Linear Law-based Transformation By Marcell T. Kurbucz; P\'eter P\'osfay; Antal Jakov\'ac
  6. Systematic Review on Reinforcement Learning in the Field of Fintech By Nadeem Malibari; Iyad Katib; Rashid Mehmood
  7. Natural Language Processing and Financial Markets: Semi-supervised Modelling of Coronavirus and Economic News By Carlos Moreno Pérez; Marco Minozzo
  8. Online Ensemble of Models for Optimal Predictive Performance with Applications to Sector Rotation Strategy By Jiaju Miao; Pawel Polak
  9. A North-South Agent Based Model of Segmented Labour Markets. The Role of Education and Trade Asymmetries By Lucrezia Fanti; Marcelo C. Pereira; Maria Enrica Virgillito
  10. Evaluating congestion pricing schemes using agent-based passenger and freight microsimulation By Peiyu Jing; Ravi Seshadri; Takanori Sakai; Ali Shamshiripour; Andre Romano Alho; Antonios Lentzakis; Moshe E. Ben-Akiva
  11. Assessing the Economic Costs of Road Traffic-Related Air Pollution in La Reunion By R. Le Frioux; A. de Palma; N. Blond
  12. Innovation in Artificial Intelligence and the Catalyst of Open Data Sharing: Literature Review and Policy implications By Dam, John; Rickon, Henry
  13. Kajian Jurnal-Jurnal Ekonomi dan Sosial dalam Bisnis dengan metode Chat GPT (AI) By , Alexander
  14. PRIME: A Price-Reverting Impact Model of a cryptocurrency Exchange By Christopher J. Cho; Timothy J. Norman; Manuel Nunes
  15. Heterogeneity of Consumption Responses to Income Shocks in the Presence of Nonlinear Persistence By Arellano, Manuel; Blundell, Richard; Bonhomme, Stéphane; Light, Jack

  1. By: Dangxing Chen; Weicheng Ye
    Abstract: In this paper, we study the problem of establishing the accountability and fairness of transparent machine learning models through monotonicity. Although there have been numerous studies on individual monotonicity, pairwise monotonicity is often overlooked in the existing literature. This paper studies transparent neural networks in the presence of three types of monotonicity: individual monotonicity, weak pairwise monotonicity, and strong pairwise monotonicity. As a means of achieving monotonicity while maintaining transparency, we propose the monotonic groves of neural additive models. As a result of empirical examples, we demonstrate that monotonicity is often violated in practice and that monotonic groves of neural additive models are transparent, accountable, and fair.
    Date: 2023–04
  2. By: Pierre Brugière (CEREMADE - CEntre de REcherches en MAthématiques de la DEcision - Université Paris Dauphine-PSL - PSL - Université Paris sciences et lettres - CNRS - Centre National de la Recherche Scientifique); Gabriel Turinici (CEREMADE - CEntre de REcherches en MAthématiques de la DEcision - Université Paris Dauphine-PSL - PSL - Université Paris sciences et lettres - CNRS - Centre National de la Recherche Scientifique)
    Abstract: We present in this paper a method to compute, using generative neural networks, an estimator of the "Value at Risk" for a nancial asset. The method uses a Variational Auto Encoder with a 'energy' (a.k.a. Radon- Sobolev) kernel. The result behaves according to intuition and is in line with more classical methods.
    Date: 2023–04–24
  3. By: Gutierrez-Lythgoe, Antonio
    Abstract: Research in the field of Artificial Intelligence has made considerable progress in recent years, demonstrating its effectiveness in predicting and classifying discrete decisions. However, these advances have been relatively underutilized in economic research due to the lack of links with economic theories that explain the decision-making process of agents. In this paper, we propose a microeconomic framework for decision trees, a machine learning technique, to establish a more solid connection with economic theory and encourage its application in the field of discrete choice. To do so, we rely on data from the 2019 EU-SILC for Spain. Through comparison with a conventional multinomial logit model, we demonstrate the usefulness of this economic perspective for studying the sociodemographic factors associated with self-employment in Spain. The results suggest that incorporating economic foundations can significantly improve the accuracy of predictions and the ability to draw individual sociodemographic profiles for self-employment.
    Keywords: Artificial Intelligence; Machine Learning; Microeconomics; Self-employment; multinomial logit
    JEL: C45 C53 J24 J62 L26
    Date: 2023–05
  4. By: Patrick Bajari; Zhihao Cen; Victor Chernozhukov; Manoj Manukonda; Jin Wang; Ramon Huerta; Junbo Li; Ling Leng; George Monokroussos; Suhas Vijaykunar; Shan Wan
    Abstract: Accurate, real-time measurements of price index changes using electronic records are essential for tracking inflation and productivity in today’s economic environment. We develop empirical hedonic models that can process large amounts of unstructured product data (text, images, prices, quantities) and output accurate hedonic price estimates and derived indices. To accomplish this, we generate abstract product attributes, or “features, ” from text descriptions and images using deep neural networks, and then use these attributes to estimate the hedonic price function. Specifically, we convert textual information about the product to numeric features using large language models based on transformers, trained or fine-tuned using product descriptions, and convert the product image to numeric features using a residual network model. To produce the estimated hedonic price function, we again use a multi-task neural network trained to predict a product’s price in all time periods simultaneously. To demonstrate the performance of this approach, we apply the models to Amazon’s data for first-party apparel sales and estimate hedonic prices. The resulting models have high predictive accuracy, with R2 ranging from 80% to 90%. Finally, we construct the AI-based hedonic Fisher price index, chained at the year-over-year frequency. We contrast the index with the CPI and other electronic indices.
    Date: 2023–04–26
  5. By: Marcell T. Kurbucz; P\'eter P\'osfay; Antal Jakov\'ac
    Abstract: The aim of this paper is to investigate the effect of a novel method called linear law-based feature space transformation (LLT) on the accuracy of intraday price movement prediction of cryptocurrencies. To do this, the 1-minute interval price data of Bitcoin, Ethereum, Binance Coin, and Ripple between 1 January 2019 and 22 October 2022 were collected from the Binance cryptocurrency exchange. Then, 14-hour nonoverlapping time windows were applied to sample the price data. The classification was based on the first 12 hours, and the two classes were determined based on whether the closing price rose or fell after the next 2 hours. These price data were first transformed with the LLT, then they were classified by traditional machine learning algorithms with 10-fold cross-validation. Based on the results, LLT greatly increased the accuracy for all cryptocurrencies, which emphasizes the potential of the LLT algorithm in predicting price movements.
    Date: 2023–04
  6. By: Nadeem Malibari; Iyad Katib; Rashid Mehmood
    Abstract: Applications of Reinforcement Learning in the Finance Technology (Fintech) have acquired a lot of admiration lately. Undoubtedly Reinforcement Learning, through its vast competence and proficiency, has aided remarkable results in the field of Fintech. The objective of this systematic survey is to perform an exploratory study on a correlation between reinforcement learning and Fintech to highlight the prediction accuracy, complexity, scalability, risks, profitability and performance. Major uses of reinforcement learning in finance or Fintech include portfolio optimization, credit risk reduction, investment capital management, profit maximization, effective recommendation systems, and better price setting strategies. Several studies have addressed the actual contribution of reinforcement learning to the performance of financial institutions. The latest studies included in this survey are publications from 2018 onward. The survey is conducted using PRISMA technique which focuses on the reporting of reviews and is based on a checklist and four-phase flow diagram. The conducted survey indicates that the performance of RL-based strategies in Fintech fields proves to perform considerably better than other state-of-the-art algorithms. The present work discusses the use of reinforcement learning algorithms in diverse decision-making challenges in Fintech and concludes that the organizations dealing with finance can benefit greatly from Robo-advising, smart order channelling, market making, hedging and options pricing, portfolio optimization, and optimal execution.
    Date: 2023–04
  7. By: Carlos Moreno Pérez (Banco de España); Marco Minozzo (University of Verona)
    Abstract: This paper investigates the reactions of US financial markets to press news from January 2019 to 1 May 2020. To this end, we deduce the content and sentiment of the news by developing apposite indices from the headlines and snippets of The New York Times, using unsupervised machine learning techniques. In particular, we use Latent Dirichlet Allocation to infer the content (topics) of the articles, and Word Embedding (implemented with the Skip-gram model) and K-Means to measure their sentiment (uncertainty). In this way, we arrive at the definition of a set of daily topic-specific uncertainty indices. These indices are then used to find explanations for the behaviour of the US financial markets by implementing a batch of EGARCH models. In substance, we find that two topic-specific uncertainty indices, one related to COVID-19 news and the other to trade war news, explain the bulk of the movements in the financial markets from the beginning of 2019 to end-April 2020. Moreover, we find that the topic-specific uncertainty index related to the economy and the Federal Reserve is positively related to the financial markets, meaning that our index is able to capture actions of the Federal Reserve during periods of uncertainty.
    Keywords: COVID-19, EGARCH, Latent Dirichlet Allocation, investor attention, uncertainty indices, Word Embedding
    JEL: D81 G15 C58 C45
    Date: 2022–08
  8. By: Jiaju Miao; Pawel Polak
    Abstract: Asset-specific factors are commonly used to forecast financial returns and quantify asset-specific risk premia. Using various machine learning models, we demonstrate that the information contained in these factors leads to even larger economic gains in terms of forecasts of sector returns and the measurement of sector-specific risk premia. To capitalize on the strong predictive results of individual models for the performance of different sectors, we develop a novel online ensemble algorithm that learns to optimize predictive performance. The algorithm continuously adapts over time to determine the optimal combination of individual models by solely analyzing their most recent prediction performance. This makes it particularly suited for time series problems, rolling window backtesting procedures, and systems of potentially black-box models. We derive the optimal gain function, express the corresponding regret bounds in terms of the out-of-sample R-squared measure, and derive optimal learning rate for the algorithm. Empirically, the new ensemble outperforms both individual machine learning models and their simple averages in providing better measurements of sector risk premia. Moreover, it allows for performance attribution of different factors across various sectors, without conditioning on a specific model. Finally, by utilizing monthly predictions from our ensemble, we develop a sector rotation strategy that significantly outperforms the market. The strategy remains robust against various financial factors, periods of financial distress, and conservative transaction costs. Notably, the strategy's efficacy persists over time, exhibiting consistent improvement throughout an extended backtesting period and yielding substantial profits during the economic turbulence of the COVID-19 pandemic.
    Date: 2023–03
  9. By: Lucrezia Fanti (Dipartimento di Politica Economica, DISCE, Università Cattolica del Sacro Cuore, Milano, Italia); Marcelo C. Pereira (Institute of Economics, University of Campinas, Campinas, Brazil); Maria Enrica Virgillito (Institute of Economics, Scuola Superiore Sant’Anna, Pisa, Italia)
    Abstract: Drawing on the labour-augmented K+S agent-based model, this paper develops a two-country North-South ABM wherein the leader and the laggard country interact through the international trade of capital goods. The model aims to address sources of asymmetries and possible converge patterns between two advanced economies that are initially differentiated in terms of the education level they are able to provide. Education is modeled as a national-level policy differently targeting the three usual levels, that is primary, secondary and tertiary. After being educated and entering the labour force, workers face a segmented market, divided into three types of job qualification, and the resulting position levels inside firms, i.e., elementary, technical and professional occupations. The three resulting labour market segments are heterogeneous in terms of both requested education level and offered wages. To address the role of trade and education, we experiment with different education-policy and trade settings. Ultimately, we are interested in understanding the coupling effects of asymmetries in education, which reverberate in segmented labour markets and differentiated growth patterns. Notably, our focus on capital-goods trade, rather than consumption goods, allows us to assess a direct link between productive capabilities in producing complex products and country growth prospects.
    Keywords: Agent-Based Model, Education, International Trade, Technology Gap, Labour Market
    JEL: C63 J3 E24 O1
    Date: 2023–05
  10. By: Peiyu Jing; Ravi Seshadri; Takanori Sakai; Ali Shamshiripour; Andre Romano Alho; Antonios Lentzakis; Moshe E. Ben-Akiva
    Abstract: The distributional impacts of congestion pricing have been widely studied in the literature and the evidence on this is mixed. Some studies find that pricing is regressive whereas others suggest that it can be progressive or neutral depending on the specific spatial characteristics of the urban region, existing activity and travel patterns, and the design of the pricing scheme. Moreover, the welfare and distributional impacts of pricing have largely been studied in the context of passenger travel whereas freight has received relatively less attention. In this paper, we examine the impacts of several third-best congestion pricing schemes on both passenger transport and freight in an integrated manner using a large-scale microsimulator (SimMobility) that explicitly simulates the behavioral decisions of the entire population of individuals and business establishments, dynamic multimodal network performance, and their interactions. Through simulations of a prototypical North American city, we find that a distance-based pricing scheme yields the largest welfare gains, although the gains are a modest fraction of toll revenues (around 30\%). In the absence of revenue recycling or redistribution, distance-based and cordon-based schemes are found to be particularly regressive. On average, lower income individuals lose as a result of the scheme, whereas higher income individuals gain. A similar trend is observed in the context of shippers -- small establishments having lower shipment values lose on average whereas larger establishments with higher shipment values gain. We perform a detailed spatial analysis of distributional outcomes, and examine the impacts on network performance, activity generation, mode and departure time choices, and logistics operations.
    Date: 2023–05
  11. By: R. Le Frioux; A. de Palma; N. Blond (Université de Cergy-Pontoise, THEMA)
    Abstract: This research builds an integrated chain of models to compute the economic costs of population exposure to air pollution from roads. The framework uses data with a high geographical resolution (1 km x 1 km), a mobility module to simulate population movements, and a Gaussian dispersion model-based exposure model to evaluate population air pollution exposure and the related costs. This paper investigates the impact of two policies on La Réunion, a French island.: replacing old vehicles with electric ones and allowing flexible departure times for commuting trips.
    Keywords: dynamic traffic simulation, air pollution, road traffic pollution, population exposure costs, integrated chain of models, electric vehicles.
    JEL: I18 L91 L92 P25 R41 Q5
    Date: 2023
  12. By: Dam, John; Rickon, Henry
    Abstract: This literature review aims to elucidate the nuanced relationship between data openness and innovation within the field of Artificial Intelligence (AI). As the significance of AI continues to expand across various sectors, understanding the role of open data in fostering innovation becomes increasingly critical. Through this review, we systematically explore and analyze the wealth of existing literature on the topic. We address key concepts, theoretical perspectives, and empirical findings, shedding light on the multi-dimensional facets of data openness, including accessibility and usability, and their impact on AI innovation. Furthermore, the review highlights the practical implications and potential strategies to leverage data openness in propelling AI innovation. We also identify existing gaps and limitations in current literature, suggesting avenues for future research. This comprehensive review contributes to the evolving discourse in AI studies, offering valuable insights to researchers, data managers, and AI practitioners alike.
    Date: 2023–05–15
  13. By: , Alexander
    Abstract: Artikel yang dibuat oleh penulis dalam rentang waktu kurang lebih 1 bulan, berhubungan dengan teknologi yang telah berkembang sangat pesat dari awal kemunculannya hingga sekarang, termasuk dengan salah satu inovasi di dunia yaitu Artificial Intelligence (AI), yang mana salah satu produk dari hasil AI tersebut adalah ChatGPT yang dikembangkan oleh OpenAi untuk dapat berinteraksi dan membantu manusia. Salah satunya adalah penulis yang menggunakan AI ini untuk dijadikan metode dalam pengerjaan artikel dalam jangka waktu satu bulan, dimana penulis membandingkan total delapan jurnal untuk menyelesaikan artikel ini. Penulis merasa sangat terbantu dalam mengerjakan dan meninjau keseluruhan jurnal utama penulis milik Aluisius Hery Pratono, S.E., MDM., Ph.D beserta 2 penulis lainnya. Artikel ini telah dibuat oleh penulis dengan tujuan untuk meneliti jurnal-jurnal ekonomi milik Hery Pratono sekaligus untuk mendapatkan pengetahuan yang baru dan menggunakan metode terbarukan untuk menyelesaikannya, pengalaman penulis melakukan analisis dan penulisan menggunakan ChatGPT sebagai metode untuk menganalisa lebih dalam terkait jurnal-jurnal yang telah dipilih sangatlah membantu, menggunakan AI penulis mampu untuk mengetahui isi dan lingkup dari jurnal tersebut kurang dari 10 menit saja. Dengan begitu penulis sadar bahwa ChatGPT sangatlah membantu dalam menyediakan informasi-informasi tambahan yang mendukung isi jurnal penelitian, tentunya dengan biaya yang minim dan waktu yang efisien pula. Artikel ini akan berisikan hasil dari kajian atas jurnal-jurnal ekonomi dan sosial tentang faktor-faktor seperti strategi inovasi, crowdfunding, variabel internal dan eksternal yang berpengaruh pada kemampuan jangka panjang perusahaan, Competitive Advantage pada perusahaan, dan masih banyak lagi.
    Date: 2023–04–12
  14. By: Christopher J. Cho; Timothy J. Norman; Manuel Nunes
    Abstract: In a financial exchange, market impact is a measure of the price change of an asset following a transaction. This is an important element of market microstructure, which determines the behaviour of the market following a trade. In this paper, we first provide a discussion on the market impact observed in the BTC/USD Futures market, then we present a novel multi-agent market simulation that can follow an underlying price series, whilst maintaining the ability to reproduce the market impact observed in the market in an explainable manner. This simulation of the financial exchange allows the model to interact realistically with market participants, helping its users better estimate market slippage as well as the knock-on consequences of their market actions. In turn, it allows various stakeholders such as industrial practitioners, governments and regulators to test their market hypotheses, without deploying capital or destabilising the system.
    Date: 2023–05
  15. By: Arellano, Manuel; Blundell, Richard; Bonhomme, Stéphane; Light, Jack
    Abstract: In this paper we use the enhanced consumption data in the Panel Survey of Income Dynamics (PSID) from 2005-2017 to explore the transmission of income shocks to consumption. We build on the nonlinear quantile framework introduced in Arellano, Blundell and Bonhomme (2017). Our focus is on the estimation of consumption responses to persistent nonlinear income shocks in the presence of unobserved heterogeneity. To reliably estimate heterogeneous responses in our un-balanced panel, we develop Sequential Monte Carlo computational methods. We find substantial heterogeneity in consumption responses, and uncover latent types of households with different life-cycle consumption behavior. Ordering types according to their average log-consumption, we find that low-consumption types respond more strongly to income shocks at the beginning of the life cycle and when their assets are low, as standard life-cycle theory would predict. In contrast, high-consumption types respond less on average, and in a way that changes little with age or assets. We examine various mechanisms that might explain this heterogeneity.
    Keywords: Nonlinear Income Persistence; Consumption Dynamics; Partial Insurance, Heterogeneity; Panel Data
    JEL: C23 D31 D91
    Date: 2023–05–04

This nep-cmp issue is ©2023 by Stan Miles. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.