nep-cmp New Economics Papers
on Computational Economics
Issue of 2022‒02‒21
twenty papers chosen by

  1. A machine learning search for optimal GARCH parameters By Luke De Clerk; Sergey Savl'ev
  2. Explaining Machine Learning by Bootstrapping Partial Dependence Functions and Shapley Values By Thomas R. Cook; Greg Gupton; Zach Modig; Nathan M. Palmer
  3. Socioeconomic disparities and COVID-19: the causal connections By Tannista Banerjee; Ayan Paul; Vishak Srikanth; Inga Str\"umke
  4. The financial network channel of monetary policy transmission: An agent-based model By Michel Alexandre; Gilberto Tadeu Lima; Luca Riccetti; Alberto Russo
  5. Reconstructing production networks using machine learning By Lafond, François; Farmer, J. Doyne; Mungo, Luca; Astudillo-Estévez, Pablo
  6. Deciding Not To Decide By Ellsaesser, Florian; Fioretti, Guido
  7. Digitalization, copyright and innovation in the creative industries: an agent-based model By Alessandro Nuvolari; Arianna Martinelli; Elisa Palagi; Emanuele Russo
  8. Smooth Nested Simulation: Bridging Cubic and Square Root Convergence Rates in High Dimensions By Wenjia Wang; Yanyuan Wang; Xiaowei Zhang
  9. Close Enough? A Large-Scale Exploration of Non-Experimental Approaches to Advertising Measurement By Brett R. Gordon; Robert Moakler; Florian Zettelmeyer
  10. Optimization of Supply Chain Network using Genetic Algorithms based on Bill of materials By Kallina, Dennis; Siegfried, Patrick
  11. Effect of Toxic Review Content on Overall Product Sentiment By Mayukh Mukhopadhyay; Sangeeta Sahney
  12. Algorithm is Experiment: Machine Learning, Market Design, and Policy Eligibility Rules By Narita, Yusuke; Yata, Kohei
  13. Wealth Inequality and Social Mobility: A Simulation-Based Modelling Approach By Yang, Xiaoliang; Zhou, Peng
  14. Exchange rate and Economic Growth - a comparative analysis of the possible relationship between them By Pramanik, Subhajit
  15. Initial assessment of the influence the influence of robustness on the weighted tardiness for a scheduling problem with high demand volatility based on a simulation model By Letonja,, Z.; Furian, N.; Pan, J.; Vössner, S.; Reuter-Oppermann, M.
  16. Pricing Bermudan options using regression trees/random forests By Zineb El Filali Ech-Chafiq; Pierre Henry-Labordere; J\'er\^ome Lelong
  17. A decision-making rule to detect insufficient data quality: an application of statistical learning techniques to the non-performing loans banking data? By Paolo Cimbali; Marco De Leonardis; Alessio Fiume; Barbara La Ganga; Luciana Meoli; Marco Orlandi
  18. AI-driven Market Manipulation and Limits of the EU law enforcement regime to credible deterrence By Azzutti, Alessio
  19. Neural calibration of hidden inhomogeneous Markov chains -- Information decompression in life insurance By Mark Kiermayer; Christian Wei{\ss}
  20. statacons: An SCons-Based Build Tool for Stata By Guiteras, Raymond; Kim, Ahnjeong; Quistorff, Brian; Shumway, Clayson

  1. By: Luke De Clerk; Sergey Savl'ev
    Abstract: Here, we use Machine Learning (ML) algorithms to update and improve the efficiencies of fitting GARCH model parameters to empirical data. We employ an Artificial Neural Network (ANN) to predict the parameters of these models. We present a fitting algorithm for GARCH-normal(1,1) models to predict one of the model's parameters, $\alpha_1$ and then use the analytical expressions for the fourth order standardised moment, $\Gamma_4$ and the unconditional second order moment, $\sigma^2$ to fit the other two parameters; $\beta_1$ and $\alpha_0$, respectively. The speed of fitting of the parameters and quick implementation of this approach allows for real time tracking of GARCH parameters. We further show that different inputs to the ANN namely, higher order standardised moments and the autocovariance of time series can be used for fitting model parameters using the ANN, but not always with the same level of accuracy.
    Date: 2022–01
  2. By: Thomas R. Cook; Greg Gupton; Zach Modig; Nathan M. Palmer
    Abstract: Machine learning and artificial intelligence methods are often referred to as “black boxes” when compared with traditional regression-based approaches. However, both traditional and machine learning methods are concerned with modeling the joint distribution between endogenous (target) and exogenous (input) variables. Where linear models describe the fitted relationship between the target and input variables via the slope of that relationship (coefficient estimates), the same fitted relationship can be described rigorously for any machine learning model by first-differencing the partial dependence functions. Bootstrapping these first-differenced functionals provides standard errors and confidence intervals for the estimated relationships. We show that this approach replicates the point estimates of OLS coefficients and demonstrate how this generalizes to marginal relationships in machine learning and artificial intelligence models. We further discuss the relationship of partial dependence functions to Shapley value decompositions and explore how they can be used to further explain model outputs.
    Keywords: Machine learning; Artificial intelligence; Explainable machine learning; Shapley values; Model interpretation
    JEL: C14 C15 C18
    Date: 2021–11–15
  3. By: Tannista Banerjee; Ayan Paul; Vishak Srikanth; Inga Str\"umke
    Abstract: The analysis of causation is a challenging task that can be approached in various ways. With the increasing use of machine learning based models in computational socioeconomics, explaining these models while taking causal connections into account is a necessity. In this work, we advocate the use of an explanatory framework from cooperative game theory augmented with $do$ calculus, namely causal Shapley values. Using causal Shapley values, we analyze socioeconomic disparities that have a causal link to the spread of COVID-19 in the USA. We study several phases of the disease spread to show how the causal connections change over time. We perform a causal analysis using random effects models and discuss the correspondence between the two methods to verify our results. We show the distinct advantages a non-linear machine learning models have over linear models when performing a multivariate analysis, especially since the machine learning models can map out non-linear correlations in the data. In addition, the causal Shapley values allow for including the causal structure in the variable importance computed for the machine learning model.
    Date: 2022–01
  4. By: Michel Alexandre (Central Bank of Brazil and Institute of Mathematics and Computer Science, University of Sao Paulo, Sao Carlos, Brazil); Gilberto Tadeu Lima (Department of Economics, University of Sao Paulo, Brazil); Luca Riccetti (Department of Economics and Law, University of Macerata, Italy); Alberto Russo (Department of Management, Università Politecnica delle Marche, Ancona, Italy and Department of Economics, Universitat Jaume I, Castellón, Spain)
    Abstract: The purpose of this paper is to contribute to a further understanding of the impact of monetary policy shocks on a financial network, which we dub the “financial network channel of monetary policy transmisión”. To this aim, we develop an agent-based model (ABM) in which banks extend loans to firms. The bank-firm credit network is endogenously time-varying as determined by plausible behavioral assumptions, with both firms and banks being always willing to close a credit deal with the network partner perceived to be less risky. We then assess through simulations how exogenous shocks to the policy interest rate affect some key topological measures of the bank-firm credit network (density, assortativity, size of largest component, and degree distribution). Our simulations show that such topological features of the bank-firm credit network are significantly affected by shocks to the policy interest rate, and this impact varies quantitatively and qualitatively with the sign, magnitude, and duration of the shocks.
    Keywords: Financial network, monetary policy shocks, agent-based modeling
    JEL: C63 E51 E52 G21
    Date: 2022
  5. By: Lafond, François; Farmer, J. Doyne; Mungo, Luca; Astudillo-Estévez, Pablo
    Abstract: The vulnerability of supply chains and their role in the propagation of shocks has been high- lighted multiple times in recent years, including by the recent pandemic. However, while the importance of micro data is increasingly recognised, data at the firm-to-firm level remains scarcely available. In this study, we formulate supply chain networks' reconstruction as a link prediction problem and tackle it using machine learning, specifically Gradient Boosting. We test our approach on three di↵erent supply chain datasets and show that it works very well and outperforms three benchmarks. An analysis of features' importance suggests that the key data underlying our predictions are firms' industry, location, and size. To evaluate the feasibility of reconstructing a network when no production network data is available, we attempt to predict a dataset using a model trained on another dataset, showing that the model's performance, while still better than a random predictor, deteriorates substantially.
    Keywords: Supply chains, Network reconstruction, Link prediction, Machine learning
    JEL: C53 C67 C81
    Date: 2022–01
  6. By: Ellsaesser, Florian; Fioretti, Guido
    Abstract: Sometimes unexpected, novel, unconceivable events enter our lives. The cause-effect mappings that usually guide our behaviour are destroyed. Surprised and shocked by possibilities that we had never imagined, we are unable to make any decision beyond mere routine. Among them there are decisions, such as making investments, that are essential for the long-term survival of businesses as well as the economy at large. We submit that the standard machinery of utility maximization does not apply, but we propose measures inspired by scenario planning and graph analysis, pointing to solutions being explored in machine learning.
    Keywords: Uncertainty, Cognitive Maps, Machine Learning, Scenario Planning, Sense-Making, Bounded Rationality
    JEL: C8 C81 D8 D81
    Date: 2022–01–10
  7. By: Alessandro Nuvolari; Arianna Martinelli; Elisa Palagi; Emanuele Russo
    Abstract: The ambiguity of the empirical results on the relationship between copyright and creativity calls for a better theoretical understanding of the issue, possibly enlarging the analysis to other factors such as technology and copyright enforcement. This paper addresses these complex policy issues by developing an agent-based model (ABM) to study how the interplay between digitization and copyright enforcement affects the production and access to cultural goods. The model includes creators who compete in different submarkets and invest in activities that might lead to the generation of creative outputs in existing submarkets, new (to the creators) submarkets, or in newly 'invented' submarkets. Finally, the model features a copyright system that provides creators with the exclusive right to reproduce their original copies and a pirate market responsible for creating and distributing pirated copies.
    Keywords: Innovation; Intellectual property rights; Creative industries; Copyright; Agent-based models.
    Date: 2022–01–28
  8. By: Wenjia Wang; Yanyuan Wang; Xiaowei Zhang
    Abstract: Nested simulation concerns estimating functionals of a conditional expectation via simulation. In this paper, we propose a new method based on kernel ridge regression to exploit the smoothness of the conditional expectation as a function of the multidimensional conditioning variable. Asymptotic analysis shows that the proposed method can effectively alleviate the curse of dimensionality on the convergence rate as the simulation budget increases, provided that the conditional expectation is sufficiently smooth. The smoothness bridges the gap between the cubic root convergence rate (that is, the optimal rate for the standard nested simulation) and the square root convergence rate (that is, the canonical rate for the standard Monte Carlo simulation). We demonstrate the performance of the proposed method via numerical examples from portfolio risk management and input uncertainty quantification.
    Date: 2022–01
  9. By: Brett R. Gordon; Robert Moakler; Florian Zettelmeyer
    Abstract: Randomized controlled trials (RCTs) have become increasingly popular in both marketing practice and academia. However, RCTs are not always available as a solution for advertising measurement, necessitating the use of observational methods. We present the first large-scale exploration of two observational methods, double/debiased machine learning (DML) and stratified propensity score matching (SPSM). Specifically, we analyze 663 large-scale experiments at Facebook, each of which is described using over 5,000 user- and experiment-level features. Although DML performs better than SPSM, neither method performs well, despite using deep learning models to implement the propensity scores and outcome models. The median absolute percentage point difference in lift is 115%, 107%, and 62% for upper, mid, and lower funnel outcomes, respectively. These are large measurement errors, given that the median RCT lifts are 28%, 19%, and 6% for the funnel outcomes, respectively. We further leverage our large sample of experiments to characterize the circumstances under which each method performs comparatively better. However, broadly speaking, our results suggest that state-of-the-art observational methods are unable to recover the causal effect of online advertising at Facebook. We conclude that observational methods for estimating ad effectiveness may not work until advertising platforms log auction-specific features for modeling.
    Date: 2022–01
  10. By: Kallina, Dennis; Siegfried, Patrick
    Abstract: The integration of genetic algorithms to optimize the networks of value chains could enormously improve the performance of supply chains. For this reason, this paper describes in more detail the application of genetic algorithms in the value chains of the automotive industry. For this purpose, a theoretical model is built up to evaluate whether the application of the model can optimize the value chain. This option is described, analyzed and its restrictions are shown. Instead of looking at the entire network, individual finished goods and their bill of material are used as a basis for optimization, which greatly reduces the complexity of the original problem. The original complexity of the supply chain networks can thus be reduced and considered based on the bill of material.
    Keywords: Supply Chain Network, Genetic Algorithm, Supply Chain Network Optimization
    JEL: F63 L14 R41
    Date: 2021–07–05
  11. By: Mayukh Mukhopadhyay; Sangeeta Sahney
    Abstract: Toxic contents in online product review are a common phenomenon. A content is perceived to be toxic when it is rude, disrespectful, or unreasonable and make individuals leave the discussion. Machine learning algorithms helps the sell side community to identify such toxic patterns and eventually moderate such inputs. Yet, the extant literature provides fewer information about the sentiment of a prospective consumer on the perception of a product after being exposed to such toxic review content. In this study, we collect a balanced data set of review comments from 18 different players segregated into three different sectors from google play-store. Then we calculate the sentence-level sentiment and toxicity score of individual review content. Finally, we use structural equation modelling to quantitatively study the influence of toxic content on overall product sentiment. We observe that comment toxicity negatively influences overall product sentiment but do not exhibit a mediating effect over reviewer score to influence sector-wise relative rating.
    Date: 2022–01
  12. By: Narita, Yusuke; Yata, Kohei
    Abstract: Algorithms produce a growing portion of decisions and recommendations both in policy and business. Such algorithmic decisions are natural experiments (conditionally quasirandomly assigned instruments) since the algorithms make decisions based only on observable input variables. We use this observation to develop a treatment-effect estimator for a class of stochastic and deterministic decision-making algorithms. Our estimator is shown to be consistent and asymptotically normal for well-defined causal effects. A key special case of our estimator is a multidimensional regression discontinuity design. We apply our estimator to evaluate the effect of the Coronavirus Aid, Relief, and Economic Security (CARES) Act, where hundreds of billions of dollars worth of relief funding is allocated to hospitals via an algorithmic rule. Our estimates suggest that the relief funding has little effect on COVID- 19-related hospital activity levels. Naive OLS and IV estimates exhibit substantial selection bias.
    Date: 2022–01
  13. By: Yang, Xiaoliang (Zhongnan University of Economics and Law, Wuhan, China); Zhou, Peng (Cardiff Business School)
    Abstract: We design a series of simulation-based thought experiments to deductively evaluate the causal effects of various factors on wealth inequality (the distribution) and social mobility (dynamics of the distribution). We find that uncertainty per se can lead to a “natural” degree of inequality and returns-related factors contribute more than earnings-related factors. Based on these identified factors, we construct an empirical, hybrid agent-based model to match the observed wealth inequality measures of the G7 countries and China. The estimated model can generate a power-law wealth distribution for the rich and a positively sloped intra-generational Great Gatsby curve. We also demonstrate how this hybrid model can be extended to a wide range of questions such as redistributive effects of tax and finance.
    Keywords: Wealth Inequality; Social Mobility; Agent-Based Model
    JEL: D31 E21 J60
    Date: 2022–02
  14. By: Pramanik, Subhajit
    Abstract: In this article, a comparative analysis has been done on the possibility of a correlation between economic growth and exchange rates. To represent the factor of growth GDP, inflation, growth has been examined in different cases. In the same way for exchange rates, nominal exchange rate, real exchange rate has been analysed based on the specific cases. Here we also see a machine learning approach to find the correlation in both short and long run time periods. Some empirical tests and data analysis was done by many economists have also been clustered here to map the total overview in a better manner.
    Keywords: GDP, Machine Learning, Exchange rates, Nominal exchange rate, Real exchange rate, Inflation, Trade
    JEL: F0 F41 F43 F47
    Date: 2021–04
  15. By: Letonja,, Z.; Furian, N.; Pan, J.; Vössner, S.; Reuter-Oppermann, M.
    Date: 2021
  16. By: Zineb El Filali Ech-Chafiq (DAO); Pierre Henry-Labordere (CMAP); J\'er\^ome Lelong (DAO)
    Abstract: The value of an American option is the maximized value of the discounted cash flows from the option. At each time step, one needs to compare the immediate exercise value with the continuation value and decide to exercise as soon as the exercise value is strictly greater than the continuation value. We can formulate this problem as a dynamic programming equation, where the main difficulty comes from the computation of the conditional expectations representing the continuation values at each time step. In (Longstaff and Schwartz, 2001), these conditional expectations were estimated using regressions on a finite-dimensional vector space (typically a polynomial basis). In this paper, we follow the same algorithm; only the conditional expectations are estimated using Regression trees or Random forests. We discuss the convergence of the LS algorithm when the standard least squares regression is replaced with regression trees. Finally, we expose some numerical results with regression trees and random forests. The random forest algorithm gives excellent results in high dimensions.
    Date: 2021–11
  17. By: Paolo Cimbali (Bank of Italy); Marco De Leonardis (Bank of Italy); Alessio Fiume (Bank of Italy); Barbara La Ganga (Bank of Italy); Luciana Meoli (Bank of Italy); Marco Orlandi (Bank of Italy)
    Abstract: The paper presents a decision-making rule, based on statistical learning techniques, to evaluate and monitor the overall quality of the granular dataset referring to the Non-Performing Loans data collection carried out by the Bank of Italy. The datasets submitted by the reporting agents must display a sufficiently high level of quality before their release to users. The study defines a decision-making rule to distinguish the cases where the corrections applied to the original dataset improve its overall quality from those where the revisions (unexpectedly) make it worse. The decision-making rule is based on a new synthetic data quality indicator, based on past evidence accumulated on data quality management activity, which makes possible the assessment and monitoring of the overall quality of the Non-Performing Loans dataset. The proposed indicator takes into account different metrics that influence the overall quality of the dataset, specifically the number of remarks (potential outliers) detected by the Bank of Italy’s internal procedures, their degree of severity and the expected number of confirmations of underlying data, the latter based on the estimation provided by the logistic regression model.
    Keywords: potential outliers, non-performing loans, data quality, supervised machine learning, logistic regression
    JEL: C18 C81 G21
    Date: 2022–02
  18. By: Azzutti, Alessio
    Abstract: As in many other sectors of EU economies, 'artificial intelligence' (AI) has entered the scene of the financial services industry as a game-changer. Trading on capital markets is undoubtedly one of the most promising AI application domains. A growing number of financial market players have in fact been adopting AI tools within the ramification of algorithmic trading. While AI trading is expected to deliver several efficiency gains, it can also bring unprecedented risks due to the technical specificities and related additional uncertainties of specific 'machine learning' methods. With a focus on new and emerging risks of AI-driven market manipulation, this study critically assesses the ability of the EU anti-manipulation law and enforcement regime to achieve credible deterrence. It argues that AI trading is currently left operating within a (quasi-)lawless market environment with the ultimate risk of jeopardising EU capital markets' integrity and stability. It shows how 'deterrence theory' can serve as a normative framework to think of innovative solutions for fixing the many shortcomings of the current EU legal framework in the fight against AI-driven market manipulation. In concluding, this study suggests improving the existing EU anti-manipulation law and enforcement with a number of policy proposals. Namely, (i) an improved, 'harm-centric' definition of manipulation; (ii) an improved, 'multi-layered' liability regime for AI-driven manipulation; and (iii) a novel, 'hybrid' public-private enforcement institutional architecture through the introduction of market manipulation 'bounty-hunters'.
    Keywords: algorithmic trading,artificial intelligence,market manipulation,market integrity,effective enforcement,credible deterrence
    JEL: G18 G28 G38 K14 K22 K42 O33 O38
    Date: 2022
  19. By: Mark Kiermayer; Christian Wei{\ss}
    Abstract: Markov chains play a key role in a vast number of areas, including life insurance mathematics. Standard actuarial quantities as the premium value can be interpreted as compressed, lossy information about the underlying Markov process. We introduce a method to reconstruct the underlying Markov chain given collective information of a portfolio of contracts. Our neural architecture explainably characterizes the process by explicitly providing one-step transition probabilities. Further, we provide an intrinsic, economic model validation to inspect the quality of the information decompression. Lastly, our methodology is successfully tested for a realistic data set of German term life insurance contracts.
    Date: 2022–01
  20. By: Guiteras, Raymond (North Carolina State University); Kim, Ahnjeong; Quistorff, Brian; Shumway, Clayson
    Abstract: This paper presents statacons, an SCons-based build tool for Stata. Because of the integration of Stata and Python in recent versions of Stata, we are able to adapt SCons for Stata workflows without the use of an external shell or extensive configuration. We discuss the usefulness of build tools generally, provide examples of the use of statacons in Stata workflows, present key elements of the syntax of statacons, and discuss extensions, alternatives, and limitations. Appendices provide installation instructions and recommendations for collaborative workflows.
    Date: 2022–01–04

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.