nep-cmp New Economics Papers
on Computational Economics
Issue of 2020‒03‒16
nineteen papers chosen by
Stan Miles
Thompson Rivers University

  1. Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications By Achref Bachouch; Côme Huré; Nicolas Langrené; Huyen Pham
  2. NAIP toolkit for Malabo domestication: Economic modeling of agricultural growth and investment strategy, case study of Kenya By Fofana, Ismaël; Omolo, Miriam W. O.; Goundan, Anatole; Magne Domgho, Léa Vicky; Collins, Julia; Marti, Estefania
  3. A deep learning approach for computations of exposure profiles for high-dimensional Bermudan options By Kristoffer Andersson; Cornelis Oosterlee
  4. Binary Classification Problems in Economics and 136 Different Ways to Solve Them By Anton Gerunov
  5. Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning By Foresti,Andrea
  6. Double Machine Learning based Program Evaluation under Unconfoundedness By Knaus, Michael C.
  7. Rotemberg and Imperfect Common Knowledge: A Solution Algorithm By Radek Šauer
  8. Ascertaining price formation in cryptocurrency markets with DeepLearning By Fan Fang; Waichung Chung; Carmine Ventre; Michail Basios; Leslie Kanthan; Lingbo Li; Fan Wu
  9. Fast Lower and Upper Estimates for the Price of Constrained Multiple Exercise American Options by Single Pass Lookahead Search and Nearest-Neighbor Martingale By Nicolas Essis-Breton; Patrice Gaillardetz
  10. The Evolution of Inequality of Opportunity in Germany: A Machine Learning Approach By Paolo Brunori; Guido Neidhofer
  11. Distributional Effects of Competition : A Simulation Approach By Rodriguez Castelan,Carlos; Araar,Abdelkrim; Malasquez Carbonel,Eduardo Alonso; Olivieri,Sergio Daniel; Vishwanath,Tara
  12. Which Model for Poverty Predictions? By Paolo Verme
  13. Machine Learning Portfolio Allocation By Michael Pinelis; David Ruppert
  14. Identifying Urban Areas by Combining Human Judgment and Machine Learning : An Application to India By Galdo,Virgilio; Li,Yue-000316086; Rama,Martin G.
  15. Causal mediation analysis with double machine learning By Helmut Farbmacher; Martin Huber; Henrika Langen; Martin Spindler
  16. Industrial Growth in Sub-Saharan Africa: Evidence from Machine Learning with Insights from Nightlight Satellite Images By Christian S. Otchia; Simplice A. Asongu
  17. Estimating the Effect of Central Bank Independence on Inflation Using Longitudinal Targeted Maximum Likelihood Estimation By Philipp Baumann; Michael Schomaker; Enzo Rossi
  18. A New Tool for Robust Estimation and Identification of Unusual Data Points By Christian Garciga; Randal Verbrugge
  19. Network Competition and Team Chemistry in the NBA By William C. Horrace; Hyunseok Jung; Shane Sanders

  1. By: Achref Bachouch (UiO - University of Oslo); Côme Huré (LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - UPD7 - Université Paris Diderot - Paris 7 - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique); Nicolas Langrené (CSIRO - Data61 [Canberra] - ANU - Australian National University - CSIRO - Commonwealth Scientific and Industrial Research Organisation [Canberra]); Huyen Pham (LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - UPD7 - Université Paris Diderot - Paris 7 - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique)
    Abstract: This paper presents several numerical applications of deep learning-based algorithms that have been introduced in [HPBL18]. Numerical and comparative tests using TensorFlow illustrate the performance of our different algorithms, namely control learning by performance iteration (algorithms NNcontPI and ClassifPI), control learning by hybrid iteration (algorithms Hybrid-Now and Hybrid-LaterQ), on the 100-dimensional nonlinear PDEs examples from [EHJ17] and on quadratic backward stochastic differential equations as in [CR16]. We also performed tests on low-dimension control problems such as an option hedging problem in finance, as well as energy storage problems arising in the valuation of gas storage and in microgrid management. Numerical results and comparisons to quantization-type algorithms Qknn, as an efficient algorithm to numerically solve low-dimensional control problems, are also provided; and some corresponding codes are available on
    Keywords: value iteration,Policy iteration algorithm,reinforcement learning,quantization,Deep learning
    Date: 2020
  2. By: Fofana, Ismaël; Omolo, Miriam W. O.; Goundan, Anatole; Magne Domgho, Léa Vicky; Collins, Julia; Marti, Estefania
    Abstract: The Malabo Agenda on Accelerated Agricultural Growth and Transformation has brought technical challengesto the development of agricultural strategiesby expanding the number of commitments and goalsunder the Comprehensive Africa Agriculture Development Programme.In this paper, we describe and apply an economic modeling framework that wasdeveloped to identify the agricultural investment priority areas for a country and to define milestones to track its progress towards the Malabo goals. The framework consists ofa three-layer simulation model that aimstocapturemultiple Malabo commitments and goals. First, the agricultural productivity analysis uses the stochastic meta-frontier technique to assess opportunities to increase agricultural productivity. Second, the economywide analysis uses an agricultural and investment focused computable general equilibrium model to capture the Malabo goalson agricultural growth, intra-Africantrade of agricultural commodities, and public and private agricultural investments.Third, the microeconomic analysis builds upon statistical economic modeling to allow direct measurement and simulation of the Malabo goals on poverty and hunger. The modeling framework is applied to Kenya using the most recent data.TheMalabo Agenda simulation results indicate that Kenya’s current nonagriculture-led growth isnot sufficient to achieving the Malabo overarching goals on poverty and hunger. Agriculture-led growthcomplemented by extendedsocial assistanceis more likely to close the income growth and inequality gaps and contribute to achieving the multiple Malabo commitments and goals by 2025.
    Keywords: KENYA, EAST AFRICA, AFRICA SOUTH OF SAHARA, AFRICA, agricultural productivity, agricultural development, poverty, simulation models, national planning, economic models, agricultural growth, agricultural investment, Computable General Equilibrium (CGE) model,
    Date: 2019
  3. By: Kristoffer Andersson; Cornelis Oosterlee
    Abstract: In this paper, we propose a neural network-based method for approximating expected exposures and potential future exposures of Bermudan options. In a first phase, the method relies on the Deep Optimal Stopping algorithm (DOS) proposed in \cite{DOS}, which learns the optimal stopping rule from Monte-Carlo samples of the underlying risk factors. Cashflow paths are then created by applying the learned stopping strategy on a new set of realizations of the risk factors. Furthermore, in a second phase the risk factors are regressed against the cashflow-paths to obtain approximations of pathwise option values. The regression step is carried out by ordinary least squares as well as neural networks, and it is shown that the latter performs more accurate approximations. The expected exposure is formulated, both in terms of the cashflow-paths and in terms of the pathwise option values and it is shown that a simple Monte-Carlo average yields accurate approximations in both cases. The potential future exposure is estimated by the empirical $\alpha$-percentile. Finally, it is shown that the expected exposures, as well as the potential future exposures can be computed under either, the risk neutral measure, or the real world measure, without having to re-train the neural networks.
    Date: 2020–03
  4. By: Anton Gerunov (Faculty of Economics and Business Administration, Sofia University ÒSt. Kliment Ohridski")
    Abstract: This article investigates the performance of 136 different classification algorithms for economic problems of binary choice. They are applied to model five different choice situations Ð consumer acceptance during a direct marketing campaign, predicting default on credit card debt, credit scoring, forecasting firm insolvency, and modelling online consumer purchases. Algorithms are trained to generate class predictions of a given binary target variable, which are then used to measure their forecast accuracy using the area under a ROC curve. Results show that algorithms of the Random Forest family consistently outperform alternative methods and may be thus suitable for modelling a wide range of discrete choice situations.
    Keywords: Bdiscrete choice, classification, machine learning algorithms, modelling decisions.
    JEL: C35 C44 C45 D81
    Date: 2020–03
  5. By: Foresti,Andrea
    Abstract: This paper presents different deep neural network architectures designed to forecast the distribution of returns on a portfolio of U.S. Treasury securities. A long short-term memory model and a convolutional neural network are tested as the main building blocks of each architecture. The models are then augmented by cross-sectional data and the portfolio's empirical distribution. The paper also presents the fit and generalization potential of each approach.
    Date: 2019–03–21
  6. By: Knaus, Michael C.
    Abstract: This paper consolidates recent methodological developments based on Double Machine Learning (DML) with a focus on program evaluation under unconfoundedness. DML based methods leverage flexible prediction methods to control for confounding in the estimation of (i) standard average effects, (ii) different forms of heterogeneous effects, and (iii) optimal treatment assignment rules. We emphasize that these estimators build all on the same doubly robust score, which allows to utilize computational synergies. An evaluation of multiple programs of the Swiss Active Labor Market Policy shows how DML based methods enable a comprehensive policy analysis. However, we find evidence that estimates of individualized heterogeneous effects can become unstable.
    Keywords: Causal machine learning, conditional average treatment effects, optimal policy learning, individualized treatment rules, multiple treatments
    JEL: C21
    Date: 2020–03
  7. By: Radek Šauer
    Abstract: This paper develops an algorithm that enables to solve macroeconomic models with Rotemberg pricing and imperfect common knowledge. Under the concept of imperfect common knowledge, Rotemberg pricing requires the solution algorithm to take prices explicitly into account. The state space includes the hierarchy of average higher-order expectations as well as the aggregate price level. In addition to determining the usual policy functions of output, inflation, and the nominal interest rate, the algorithm has to search for the policy function of the aggregate price and for the policy function of the firm-specific price.
    Keywords: Rotemberg pricing, dispersed information, heterogenous beliefs, Kalman filter, higher-order expectations
    JEL: C63 D82 E31
    Date: 2020
  8. By: Fan Fang; Waichung Chung; Carmine Ventre; Michail Basios; Leslie Kanthan; Lingbo Li; Fan Wu
    Abstract: The cryptocurrency market is amongst the fastest-growing of all the financial markets in the world. Unlike traditional markets, such as equities, foreign exchange and commodities, cryptocurrency market is considered to have larger volatility and illiquidity. This paper is inspired by the recent success of using deep learning for stock market prediction. In this work, we analyze and present the characteristics of the cryptocurrency market in a high-frequency setting. In particular, we applied a deep learning approach to predict the direction of the mid-price changes on the upcoming tick. We monitored live tick-level data from $8$ cryptocurrency pairs and applied both statistical and machine learning techniques to provide a live prediction. We reveal that promising results are possible for cryptocurrencies, and in particular, we achieve a consistent $78\%$ accuracy on the prediction of the mid-price movement on live exchange rate of Bitcoins vs US dollars.
    Date: 2020–02
  9. By: Nicolas Essis-Breton; Patrice Gaillardetz
    Abstract: This article presents fast lower and upper estimates for a large class of options: the class of constrained multiple exercise American options. Typical options in this class are swing options with volume and timing constraints, and passport options with multiple lookback rights. The lower estimate algorithm uses the artificial intelligence method of lookahead search. The upper estimate algorithm uses the dual approach to option pricing on a nearest-neighbor basis for the martingale space. Probabilistic convergence guarantees are provided. Several numerical examples illustrate the approaches including a swing option with four constraints, and a passport option with 16 constraints.
    Date: 2020–02
  10. By: Paolo Brunori (University of Florence); Guido Neidhofer (ZEW)
    Abstract: We show that measures of inequality of opportunity (IOP) fully consistent with Roemer (1998)'s IOP theory can be straightforwardly estimated by adopting a machine learning approach, and apply our novel method to analyse the development of IOP in Germany during the last three decades. Hereby, we take advantage of information contained in 25 waves of the Socio-Economic Panel. Our analysis shows that in Germany IOP declined immediately after reunification, increased in the first decade of the century, and slightly declined again after 2010. Over the entire period, at the top of the distribution we always find individuals that resided in West-Germany before the fall of the Berlin Wall, whose fathers had a high occupational position, and whose mothers had a high educational degree. East-German residents in 1989, with low educated parents, persistently qualify at the bottom.
    Keywords: Inequality, opportunity, SOEP, Germany.
    JEL: D63 D30 D31
    Date: 2020–01
  11. By: Rodriguez Castelan,Carlos; Araar,Abdelkrim; Malasquez Carbonel,Eduardo Alonso; Olivieri,Sergio Daniel; Vishwanath,Tara
    Abstract: Understanding the economic and social effects of the recent global trends of rising market concentration and market power has become a policy priority, particularly in developing countries where markets are often more concentrated. In this context, since the poor are typically the most affected by lack of competition, new analytical tools to assess the distributional effects of variations in market concentration in a rapid and cost-efficient manner are required. To fill this knowledge gap, this paper introduces a simple simulation method, the Welfare and Competition tool (WELCOM), to estimate with minimum data requirements the direct distributional effects of market concentration through the price channel. Using this simple yet novel tool, this paper also illustrates the simulated distributional effects of reducing concentration in two markets in Mexico that are known for their high level of concentration: mobile telecommunications and corn products. The results show that increasing competition from four to 12 firms in the mobile telecommunications industry and reducing the market share of the oligopoly in corn products from 31.2 percent to 7.8 percent would achieve a combined reduction of 0.8 percentage points in the poverty headcount as well as a decline of 0.32 points in the Gini coefficient.
    Date: 2019–05–02
  12. By: Paolo Verme (World Bank)
    Abstract: OLS models are the predominant choice for poverty predictions in a variety of contexts such as proxy-means tests, poverty mapping or cross-survey impu- tations. This paper compares the performance of econometric and machine learning models in predicting poverty using alternative objective functions and stochastic dominance analysis based on coverage curves. It finds that the choice of an optimal model largely depends on the distribution of incomes and the poverty line. Comparing the performance of different econometric and machine learning models is therefore an important step in the process of optimizing poverty predictions and targeting ratios.
    Keywords: Welfare Modelling; Income Distributions; Poverty Predictions; Imputations.
    JEL: D31 D63 E64 O15
    Date: 2020–02
  13. By: Michael Pinelis; David Ruppert
    Abstract: We find economically and statistically significant gains from using machine learning to dynamically allocate between the market index and the risk-free asset. We model the market price of risk to determine the optimal weights in the portfolio: reward-risk market timing. This involves forecasting the direction of next month's excess return, which gives the reward, and constructing a dynamic volatility estimator that is optimized with a machine learning model, which gives the risk. Reward-risk timing with machine learning provides substantial improvements in investor utility, alphas, Sharpe ratios, and maximum drawdowns, after accounting for transaction costs, leverage constraints, and on a new out-of-sample test set. This paper provides a unifying framework for machine learning applied to both return- and volatility-timing.
    Date: 2020–03
  14. By: Galdo,Virgilio; Li,Yue-000316086; Rama,Martin G.
    Abstract: This paper proposes a methodology for identifying urban areas that combines subjective assessments with machine learning, and applies it to India, a country where several studies see the official urbanization rate as an under-estimate. For a representative sample of cities, towns and villages, as administratively defined, human judgment of Google images is used to determine whether they are urban or rural in practice. Judgments are collected across four groups of assessors, differing in their familiarity with India and with urban issues, following two different protocols. The judgment-based classification is then combined with data from the population census and from satellite imagery to predict the urban status of the sample. The Logit model, and LASSO and random forests methods, are applied. These approaches are then used to decide whether each of the out-of-sample administrative units in India is urban or rural in practice. The analysis does not find that India is substantially more urban than officially claimed. However, there are important differences at more disaggregated levels, with ?other towns? and ?census towns? being more rural, and some southern states more urban, than is officially claimed. The consistency of human judgment across assessors and protocols, the easy availability of crowd-sourcing, and the stability of predictions across approaches, suggest that the proposed methodology is a promising avenue for studying urban issues.
    Date: 2020–02–24
  15. By: Helmut Farbmacher; Martin Huber; Henrika Langen; Martin Spindler
    Abstract: This paper combines causal mediation analysis with double machine learning to control for observed confounders in a data-driven way under a selection-on-observables assumption in a high-dimensional setting. We consider the average indirect effect of a binary treatment operating through an intermediate variable (or mediator) on the causal path between the treatment and the outcome, as well as the unmediated direct effect. Estimation is based on efficient score functions, which possess a multiple robustness property w.r.t. misspecifications of the outcome, mediator, and treatment models. This property is key for selecting these models by double machine learning, which is combined with data splitting to prevent overfitting in the estimation of the effects of interest. We demonstrate that the direct and indirect effect estimators are asymptotically normal and root-n consistent under specific regularity conditions and investigate the finite sample properties of the suggested methods in a simulation study when considering lasso as machine learner. We also provide an empirical application to the U.S. National Longitudinal Survey of Youth, assessing the indirect effect of health insurance coverage on general health operating via routine checkups as mediator, as well as the direct effect. We find a moderate short term effect of health insurance coverage on general health which is, however, not mediated by routine checkups.
    Date: 2020–02
  16. By: Christian S. Otchia (Hyogo, Japan); Simplice A. Asongu (Yaoundé, Cameroon)
    Abstract: This study uses nightlight time data and machine learning techniques to predict industrial development in Africa. The results provide the first evidence on how machine learning techniques and nightlight data can be used to predict economic development in places where subnational data are missing or not precise. Taken together, the research confirms four groups of important determinants of industrial growth: natural resources, agriculture growth, institutions, and manufacturing imports. Our findings indicate that Africa should follow a more multisector approach for development, putting natural resources and agriculture productivity growth at the forefront.
    Keywords: Industrial growth; Machine learning; Africa
    JEL: I32 O15 O40 O55
    Date: 2019–01
  17. By: Philipp Baumann; Michael Schomaker; Enzo Rossi
    Abstract: Whether a country's central bank independence (CBI) status has a lowering effect on inflation is a controversial hypothesis. To date, this question could not be answered satisfactorily because the complex macroeconomics structure that gives rise to the data has not been adequately incorporated into statistical analyses. We have developed a causal model that summarizes the economic process of inflation. Based on this causal model and recent data, we discuss and identify the assumptions under which the effect of CBI on inflation can be identified and estimated. Given these and alternative assumptions we estimate this effect using modern doubly robust effect estimators, i.e. longitudinal targeted maximum likelihood estimators. The estimation procedure incorporated machine learning algorithms and was tailored to address the challenges that come with complex longitudinal macroeconomics data. We could not find strong support for the hypothesis that a central bank that is independent over a long period of time necessarily lowers inflation. Simulation studies evaluate the sensitivity of the proposed methods in complex settings when assumptions are violated, and highlight the importance of working with appropriate learning algorithms for estimation.
    Date: 2020–03
  18. By: Christian Garciga; Randal Verbrugge (Virginia Polytechnic Institute and State University)
    Abstract: Most consistent estimators are what Müller (2007) terms “highly fragile”: prone to total breakdown in the presence of a handful of unusual data points. This compromises inference. Robust estimation is a (seldom-used) solution, but commonly used methods have drawbacks. In this paper, building on methods that are relatively unknown in economics, we provide a new tool for robust estimates of mean and covariance, useful both for robust estimation and for detection of unusual data points. It is relatively fast and useful for large data sets. Our performance testing indicates that our baseline method performs on par with, or better than, two of the currently best available methods, and that it works well on benchmark data sets. We also demonstrate that the issues we discuss are not merely hypothetical, by re-examining a prominent economic study and demonstrating its central results are driven by a set of unusual points.
    Keywords: big data; machine learning; outlier identification; fragility; robust estimation; detMCD; RMVN
    JEL: C3 C4 C5
    Date: 2020–03–05
  19. By: William C. Horrace (Center for Policy Research, Maxwell School, Syracuse University, 426 Eggers Hall, Syracuse, NY 13244); Hyunseok Jung (Department of Economics, University of Arkansas); Shane Sanders (Department of Sports Management, Syracuse University)
    Abstract: We consider a heterogeneous social interaction model where agents interact with peers within their own network but also interact with agents across other (non-peer) networks. To address potential endogeneity in the networks, we assume that each network has a central planner who makes strategic network decisions based on observable and unobservable characteristics of the peers in her charge. The model forms a simultaneous equation system that can be estimated by Quasi-Maximum Likelihood. We apply a restricted version of our model to data on National Basketball Association games, where agents are players, networks are individual teams organized by coaches, and competition is head-to-head. That is, at any time a player only interacts with two networks: their team and the opposing team. We find significant positive within-team peer-effects and both negative and positive opposing-team competitor-effects in NBA games. The former are interpretable as “team chemistries" which enhance the individual performances of players on the same team. The latter are interpretable as “team rivalries," which can either enhance or diminish the individual performance of opposing players.
    Keywords: Spatial Analysis, Peer Effects, Endogeneity, Machine Learning
    JEL: C13 C31 D24
    Date: 2020–03

This nep-cmp issue is ©2020 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.