nep-cmp New Economics Papers
on Computational Economics
Issue of 2022‒11‒14
fifteen papers chosen by
Stan Miles
Thompson Rivers University

  1. DyFEn: Agent-Based Fee Setting in Payment Channel Networks By Kiana Asgari; Aida Afshar Mohammadian; Mojtaba Tefagh
  2. Classification based credit risk analysis: The case of Lending Club By Aadi Gupta; Priya Gulati; Siddhartha P. Chakrabarty
  3. Biased or Limited: Modeling Sub-Rational Human Investors in Financial Markets By Penghang Liu; Kshama Dwarakanath; Svitlana S Vyetrenko
  4. DeepVol: Volatility Forecasting from High-Frequency Data with Dilated Causal Convolutions By Fernando Moreno-Pino; Stefan Zohren
  5. Applying Machine Learning and Geolocation Techniques to Social Media Data (Twitter) to Develop a Resource for Urban Planning By Milusheva,Svetoslava Petkova; Marty,Robert Andrew; Bedoya Arguelles,Guadalupe; Williams,Sarah Elizabeth; Resor,Elizabeth Landsdowne; Legovini,Arianna
  6. Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements By Breinlich,Holger; Corradi,Valentina; Rocha,Nadia; Ruta,Michele; Santos Silva,J.M.C.; Zylkin,Tom
  7. MIRAGRODEP with endogenous tariffs 1.0: Documentation By Bouët, Antoine; Laborde Debucquet, David; Traoré, Fousseini
  8. Learners in the loop: hidden human skills in machine intelligence By Paola Tubaro
  9. Artificial Intelligence, Ethics, and Intergenerational Responsibility By Victor Klockmann; Alicia von Schenk; Marie Claire Villeval
  10. Human-algorithm interaction: Algorithmic pricing in hybrid laboratory markets By Normann, Hans-Theo; Sternberg, Martin
  11. Welfare estimations from imagery. A test of domain experts ability to rate poverty from visual inspection of satellite imagery By Wahab Ibrahim; Ola Hall
  12. Boundary-safe PINNs extension: Application to non-linear parabolic PDEs in counterparty credit risk By Joel P. Villarino; \'Alvaro Leitao; Jos\'e A. Garc\'ia-Rodr\'iguez
  13. MIRAGRODEP 2.0: Documentation By Bouët, Antoine; Laborde Debucquet, David; Robichaud, Veronique; Traore, Fousseini; Tokgoz, Simla
  14. Optimizing portfolios in the illiquid, unlisted market of SME crowdlending By Bastien Lextrait
  15. Mental Accounting and the Marginal Propensity to Consume By Bernard, René

  1. By: Kiana Asgari; Aida Afshar Mohammadian; Mojtaba Tefagh
    Abstract: In recent years, with the development of easy to use learning environments, implementing and reproducible benchmarking of reinforcement learning algorithms has been largely accelerated by utilizing these frameworks. In this article, we introduce the Dynamic Fee learning Environment (DyFEn), an open-source real-world financial network model. It can provide a testbed for evaluating different reinforcement learning techniques. To illustrate the promise of DyFEn, we present a challenging problem which is a simultaneous multi-channel dynamic fee setting for off-chain payment channels. This problem is well-known in the Bitcoin Lightning Network and has no effective solutions. Specifically, we report the empirical results of several commonly used deep reinforcement learning methods on this dynamic fee setting task as a baseline for further experiments. To the best of our knowledge, this work proposes the first virtual learning environment based on a simulation of blockchain and distributed ledger technologies, unlike many others which are based on physics simulations or game platforms.
    Date: 2022–10
  2. By: Aadi Gupta; Priya Gulati; Siddhartha P. Chakrabarty
    Abstract: In this paper, we performs a credit risk analysis, on the data of past loan applicants of a company named Lending Club. The calculation required the use of exploratory data analysis and machine learning classification algorithms, namely, Logistic Regression and Random Forest Algorithm. We further used the calculated probability of default to design a credit derivative based on the idea of a Credit Default Swap, to hedge against an event of default. The results on the test set are presented using various performance measures.
    Date: 2022–10
  3. By: Penghang Liu; Kshama Dwarakanath; Svitlana S Vyetrenko
    Abstract: Multi-agent market simulation is an effective tool to investigate the impact of various trading strategies in financial markets. One way of designing a trading agent in simulated markets is through reinforcement learning where the agent is trained to optimize its cumulative rewards (e.g., maximizing profits, minimizing risk, improving equitability). While the agent learns a rational policy that optimizes the reward function, in reality, human investors are sub-rational with their decisions often differing from the optimal. In this work, we model human sub-rationality as resulting from two possible causes: psychological bias and computational limitation. We first examine the relationship between investor profits and their degree of sub-rationality, and create hand-crafted market scenarios to intuitively explain the sub-rational human behaviors. Through experiments, we show that our models successfully capture human sub-rationality as observed in the behavioral finance literature. We also examine the impact of sub-rational human investors on market observables such as traded volumes, spread and volatility. We believe our work will benefit research in behavioral finance and provide a better understanding of human trading behavior.
    Date: 2022–10
  4. By: Fernando Moreno-Pino; Stefan Zohren
    Abstract: Volatility forecasts play a central role among equity risk measures. Besides traditional statistical models, modern forecasting techniques, based on machine learning, can readily be employed when treating volatility as a univariate, daily time-series. However, econometric studies have shown that increasing the number of daily observations with high-frequency intraday data helps to improve predictions. In this work, we propose DeepVol, a model based on Dilated Causal Convolutions to forecast day-ahead volatility by using high-frequency data. We show that the dilated convolutional filters are ideally suited to extract relevant information from intraday financial data, thereby naturally mimicking (via a data-driven approach) the econometric models which incorporate realised measures of volatility into the forecast. This allows us to take advantage of the abundance of intraday observations, helping us to avoid the limitations of models that use daily data, such as model misspecification or manually designed handcrafted features, whose devise involves optimising the trade-off between accuracy and computational efficiency and makes models prone to lack of adaptation into changing circumstances. In our analysis, we use two years of intraday data from NASDAQ-100 to evaluate DeepVol's performance. The reported empirical results suggest that the proposed deep learning-based approach learns global features from high-frequency data, achieving more accurate predictions than traditional methodologies, yielding to more appropriate risk measures.
    Date: 2022–09
  5. By: Milusheva,Svetoslava Petkova; Marty,Robert Andrew; Bedoya Arguelles,Guadalupe; Williams,Sarah Elizabeth; Resor,Elizabeth Landsdowne; Legovini,Arianna
    Abstract: With all the recent attention focused on big data, it is easy to overlook that basic vital statistics remain difficult to obtain in most of the world. This project set out to test whether an openly available dataset (Twitter) could be transformed into a resource for urban planning and development. The hypothesis is tested by creating road traffic crash location data, which are scarce in most resource-poor environments but essential for addressing the number one cause of mortality for children over age five and young adults. The research project scraped 874,588 traffic-related tweets in Nairobi, Kenya, applied a machine learning model to capture the occurrence of a crash, and developed an improved geoparsing algorithm to identify its location. The project geolocated 32,991 crash reports in Twitter for 2012-20 and clustered them into 22,872 unique crashes to produce one of the first crash maps for Nairobi. A motorcycle delivery service was dispatched in real-time to verify a subset of crashes, showing 92 percent accuracy. Using a spatial clustering algorithm, portions of the road network (less than 1 percent) were identified where 50 percent of the geolocated crashes occurred. Even with limitations in the representativeness of the data, the results can provide urban planners useful information to target road safety improvements where resources are limited.
    Keywords: ICT Applications,Disease Control&Prevention,Public Health Promotion,Road Safety,Intelligent Transport Systems,Transport Services,Crime and Society
    Date: 2020–12–04
  6. By: Breinlich,Holger; Corradi,Valentina; Rocha,Nadia; Ruta,Michele; Santos Silva,J.M.C.; Zylkin,Tom
    Abstract: Modern trade agreements contain a large number of provisions besides tariff reductions, inareas as diverse as services trade, competition policy, trade-related investment measures, or public procurement.Existing research has struggled with overfitting and severe multicollinearity problems when trying to estimate theeffects of these provisions on trade flows. This paper builds on recent developments in the machine learning andvariable selection literature to propose novel data-driven methods for selecting the most important provisions andquantifying their impact on trade flows. The proposed methods have the advantage of not requiring ad hocassumptions on how to aggregate individual provisions and offer improved selection accuracy over the standard lasso.The analysis finds that provisions related to technical barriers to trade, antidumping, trade facilitation,subsidies, and competition policy are associated with enhancing the trade-increasing effect of trade agreements.
    Keywords: International Trade and Trade Rules,De Facto Governments,Economics and Finance of Public Institution Development,State Owned Enterprise Reform,Public Sector Administrative and Civil Service Reform,Public Sector Administrative & Civil Service Reform,Democratic Government,Competition Policy,Competitiveness and Competition Policy,Trade Facilitation,Health and Sanitation
    Date: 2021–04–13
  7. By: Bouët, Antoine; Laborde Debucquet, David; Traoré, Fousseini
    Abstract: MIRAGRODEP with endogenous tariffs is a recursive dynamic multi-region, multi-sector Computable General Equilibrium (CGE) model based on MIRAGRODEP which in turn is based on MIRAGE (Modelling International Relations Under Applied General Equilibrium). It constitutes an extension of the MIRAGRODEP model that allows the user to perform analysis involving endogenous tariffs such as designing optimal common external tariffs (CET) in customs unions. The model is particularly suitable for trade policy analysis that require designing optimal levels of tariffs for regional trade agreements.
    Keywords: AFRICA, AFRICA SOUTH OF SAHARA, CENTRAL AFRICA, EAST AFRICA, NORTH AFRICA, SOUTHERN AFRICA, WEST AFRICA, tariffs, trade, trade policies, computable general equilibrium models,common external tariffs (CET), modelling international relations under applied general equilibrium (MIRAGE )
    Date: 2022
  8. By: Paola Tubaro (CREST - Centre de Recherche en Économie et Statistique - ENSAI - Ecole Nationale de la Statistique et de l'Analyse de l'Information [Bruz] - X - École polytechnique - ENSAE Paris - École Nationale de la Statistique et de l'Administration Économique - CNRS - Centre National de la Recherche Scientifique, LSQ - Laboratoire de sociologie quantitative - Centre de Recherche en Économie et STatistique (CREST), MSH Paris-Saclay - Maison des Sciences de l'Homme - Paris Saclay - UVSQ - Université de Versailles Saint-Quentin-en-Yvelines - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique - ENS Paris Saclay - Ecole Normale Supérieure Paris-Saclay, LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique, TAU - TAckling the Underspecified - Inria Saclay - Ile de France - Inria - Institut National de Recherche en Informatique et en Automatique - LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique)
    Abstract: Today's artificial intelligence, largely based on data-intensive machine learning algorithms, relies heavily on the digital labour of invisibilized and precarized humans-in-the-loop who perform multiple functions of data preparation, verification of results, and even impersonation when algorithms fail. Using original quantitative and qualitative data, the present article shows that these workers are highly educated, engage significant (sometimes advanced) skills in their activity, and earnestly learn alongside machines. However, the loop is one in which human workers are at a disadvantage as they experience systematic misrecognition of the value of their competencies and of their contributions to technology, the economy, and ultimately society. This situation hinders negotiations with companies, shifts power away from workers, and challenges the traditional balancing role of the salary institution.
    Keywords: misrecognition,Spanish-speaking countries,Digital labour platforms,artificial intelligence,skills,learning
    Date: 2022
  9. By: Victor Klockmann (Goethe-University Frankfurt am Main, University of Würzburg = Universität Würzburg , Max Planck Institute for Human Development - Max-Planck-Gesellschaft); Alicia von Schenk (Goethe-University Frankfurt am Main, University of Würzburg = Universität Würzburg , Max Planck Institute for Human Development - Max-Planck-Gesellschaft); Marie Claire Villeval (GATE Lyon Saint-Étienne - Groupe d'analyse et de théorie économique - ENS Lyon - École normale supérieure - Lyon - UL2 - Université Lumière - Lyon 2 - UCBL - Université Claude Bernard Lyon 1 - Université de Lyon - UJM - Université Jean Monnet [Saint-Étienne] - Université de Lyon - CNRS - Centre National de la Recherche Scientifique)
    Abstract: In the future, artificially intelligent algorithms will make more and more decisions on behalf of humans that involve humans' social preferences. They can learn these preferences through the repeated observation of human behavior in social encounters. In such a context, do individuals adjust the selfishness or prosociality of their behavior when it is common knowledge that their actions produce various externalities through the training of an algorithm? In an online experiment, we let participants' choices in dictator games train an algorithm. Thereby, they create an externality on future decision making of an intelligent system that affects future participants. We show that individuals who are aware of the consequences of their training on the payoffs of a future generation behave more prosocially, but only when they bear the risk of being harmed themselves by future algorithmic choices. In that case, the externality of artificially intelligence training increases the share of egalitarian decisions in the present.
    Keywords: Artificial Intelligence,Morality,Prosociality,Generations,Externalities
    Date: 2022
  10. By: Normann, Hans-Theo; Sternberg, Martin
    Abstract: This paper investigates pricing in laboratory markets when human players interact with an algorithm. We compare the degree of competition when exclusively humans interact to the case of one firm delegating its decisions to an algorithm, an n-player generalization of tit-for-tat. We further vary whether participants know about the presence of the algorithm. When one of three firms in a market is an algorithm, we observe significantly higher prices compared to human-only markets. Firms employing an algorithm earn significantly less profit than their rivals. (Un)certainty about the actual presence of an algorithm does not significantly affect collusion, although humans do seem to perceive algorithms as more disruptive.
    Keywords: algorithms,collusion,human-computer interaction,labora-tory experiments
    JEL: C90 L41
    Date: 2022
  11. By: Wahab Ibrahim; Ola Hall
    Abstract: The present study uses domain experts to estimate welfare levels and indicators from high-resolution satellite imagery. We use the wealth quintiles from the 2015 Tanzania DHS dataset as ground truth data. We analyse the performance of the visual estimation of relative wealth at the cluster level and compare these with wealth rankings from the DHS survey of 2015 for that country using correlations, ordinal regressions and multinomial logistic regressions. Of the 608 clusters, 115 received the same ratings from human experts and the independent DHS rankings. For 59 percent of the clusters, experts ratings were slightly lower. On the one hand, significant positive predictors of wealth are the presence of modern roofs and wider roads. For instance, the log odds of receiving a rating in a higher quintile on the wealth rankings is 0.917 points higher on average for clusters with buildings with slate or tile roofing compared to those without. On the other hand, significant negative predictors included poor road coverage, low to medium greenery coverage, and low to medium building density. Other key predictors from the multinomial regression model include settlement structure and farm sizes. These findings are significant to the extent that these correlates of wealth and poverty are visually readable from satellite imagery and can be used to train machine learning models in poverty predictions. Using these features for training will contribute to more transparent ML models and, consequently, explainable AI.
    Date: 2022–10
  12. By: Joel P. Villarino; \'Alvaro Leitao; Jos\'e A. Garc\'ia-Rodr\'iguez
    Abstract: The goal of this work is to develop deep learning numerical methods for solving option XVA pricing problems given by non-linear PDE models. A novel strategy for the treatment of the boundary conditions is proposed, which allows to get rid of the heuristic choice of the weights for the different addends that appear in the loss function related to the training process. It is based on defining the losses associated to the boundaries by means of the PDEs that arise from substituting the related conditions into the model equation itself. Further, automatic differentiation is employed to obtain accurate approximation of the partial derivatives.
    Date: 2022–10
  13. By: Bouët, Antoine; Laborde Debucquet, David; Robichaud, Veronique; Traore, Fousseini; Tokgoz, Simla
    Abstract: MIRAGRODEP is a recursive-dynamic, multi-region, multi-sector computable general equilibrium model, devoted to trade and agricultural policy analysis. It is developed for AGRODEP and draws upon the MIRAGE model built by CEPII. It incorporates specific features such as foreign direct investment and runs with a tariff aggregation module that allows the user to capture the exclusion effects at a detailed level and the variance of tariffs. The model also includes a submodule allowing to test different closures for the public sector as well as the inefficiency of the tax collection system. MIRAGRODEP 2.0 includes an improved demand system. Social Accounting Matrix (SAM) and trade data in MIRAGRODEP are based on the GTAP database. Additional sources such as MacMap are used for protection data. This technical note presents an expanded documentation, with instructions on how to run the model and an illustrative application.
    Keywords: Computable General Equilibrium (CGE) model, mathematical models, trade policies, agricultural policies, tariffs, public sector, Social Accounting Matrices (SAM), foreign direct investment
    Date: 2022
  14. By: Bastien Lextrait
    Abstract: Portfolio construction for SME crowdloans is challenging. This market is illiquid, unlisted and with scarce historical data of asset development. Consequently, traditional portfolio optimization techniques cannot be applied as is since risks can only be assessed individually and covariance matrices are not available. We propose a new portfolio optimization framework based on estimated risk clustering rather than asset variance-covariance matrix. We first establish risk profiles for each company through SHAP-decomposing its estimated risk. We use correlation-like metrics to compare risk profiles to one another and group similar risk profiles together using hierarchical clustering. We then apply quadratic optimization on the generated groups to minimize risk variance. We simulate investments using real data to quantify our strategy’s return, based on the SMEs market share neglected by banks. Our method overperforms traditional mean-variance optimization adapted at best on our sample, as well as 1/N naive investment strategy which has regularly proven its efficiency. Our method rewards any risk-averse investor profile with higher returns.
    Keywords: Portfolio optimization, crowdlending, SMEs, SHAP values, hierarchical clustering
    JEL: G11 G23 C38
    Date: 2022
  15. By: Bernard, René
    Abstract: This paper studies how consumers respond to unexpected, transitory income shocks and why. In a randomized control trial, I elicit marginal propensities to consume (MPC) out of different hypothetical income shock scenarios, varying the payment mode, the shock size, and the source of income. The results show respondents exhibit a higher MPC when exposed to a windfall paid out in cash or without any specification of the payment mode, respectively, compared to a windfall deposited in an instant-access savings account, suggesting consumers violate fungibility. Further, the MPC falls with the shock size, whereas it does not vary with the source of income. Using causal machine learningmethods to explore treatment heterogeneity, I find that low liquidity, self-control problems, and a lack of cognitive sophistication contribute to MPC heterogeneity. The results are broadly in line with mental accounting theory.
    Keywords: Randomized control trial,marginal propensity to consume,fiscal policy,mental accounting,causal forest
    JEL: C90 D12 D14 D15 D91
    Date: 2022

This nep-cmp issue is ©2022 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.