nep-cmp New Economics Papers
on Computational Economics
Issue of 2020‒03‒09
thirty papers chosen by
Stan Miles
Thompson Rivers University

  1. An agent-based model of intra day financial markets dynamics By Jacopo Staccioli; Mauro Napoletano
  2. Capturing Key Energy and Emission Trends in CGE Models: Assessment of Status and Remaining Challenges By Taran Faehn; Gabriel Bachner; Robert Beach; Jean Chateau; Shinichiro Fujimori; Madanmohan Ghosh; Meriem Hamdi-Cherif; Elisa Lanzi; Sergey Paltsev; Toon Vandyck; Bruno Cunha; Rafael Garaffa; Karl Steininger
  3. G-Learner and GIRL: Goal Based Wealth Management with Reinforcement Learning By Matthew Dixon; Igor Halperin
  4. Winter is possibly not coming : mitigating financial instability in an agent-based model with interbank market By Lilit Popoyan; Mauro Napoletano; Andrea Roventini
  5. ESG investments: Filtering versus machine learning approaches By Carmine de Franco; Christophe Geissler; Vincent Margot; Bruno Monnier
  6. Model order reduction for parametric high dimensional models in the analysis of financial risk By Andreas Binder; Onkar Jadhav; Volker Mehrmann
  7. Using Reinforcement Learning in the Algorithmic Trading Problem By Evgeny Ponomarev; Ivan Oseledets; Andrzej Cichocki
  8. Corrupted Multidimensional Binary Search: Learning in the Presence of Irrational Agents By Akshay Krishnamurthy; Thodoris Lykouris; Chara Podimata
  9. Implications for Provincial Economies of Meeting China's NDC through an Emission Trading Scheme : A Regional CGE Modeling Analysis By Pang,Jun; Timilsina,Govinda R.
  10. Computing Equilibria of Stochastic Heterogeneous Agent Models Using Decision Rule Histories By Marcelo Veracierto
  11. Deep Learning for Asset Bubbles Detection By Oksana Bashchenko; Alexis Marchal
  12. Safe Counterfactual Reinforcement Learning By Yusuke Narita; Shota Yasui; Kohei Yata
  13. How Much Would China Gain from Power Sector Reforms ? An Analysis Using TIMES and CGE Models By Timilsina,Govinda R.; Pang,Jun; Yang,Xi
  14. Assessing Urban Policies Using a Simulation Model with Formal and Informal Housing : Application to Cape Town, South Africa By Pfeiffer,Basile Fabrice; Rabe,Claus; Selod,Harris; Viguie,Vincent
  15. Modeling Uncertainty in Large Natural Resource Allocation Problems By Cai,Yongyang; Steinbuks,Jevgenijs; Judd,Kenneth L.; Jaegermeyr,Jonas; Hertel,Thomas W.
  16. Optimization by Hybridization of a Genetic Algorithm with the PROMOTHEE Method: Management of Multicriteria Localization By Myriem Alijo; Otman Abdoun; Mostafa Bachran; Amal Bergam
  17. Firms Default Prediction with Machine Learning By Tesi Aliaj; Aris Anagnostopoulos; Stefano Piersanti
  18. Mathematical Foundations of Regression Methods for the approximation of the Forward Initial Margin By Lucia Cipolina Kun
  19. AutoAlpha: an Efficient Hierarchical Evolutionary Algorithm for Mining Alpha Factors in Quantitative Investment By Tianping Zhang; Yuanqi Li; Yifei Jin; Jian Li
  20. Synchronization of endogenous business cycles By Marco Pangallo
  21. Trimming the Sail: A Second-order Learning Paradigm for Stock Prediction By Chi Chen; Li Zhao; Wei Cao; Jiang Bian; Chunxiao Xing
  22. Double/Debiased Machine Learning for Dynamic Treatment Effects By Greg Lewis; Vasilis Syrgkanis
  23. Inventory effects on the price dynamics of VSTOXX futures quantified via machine learning By Daniel Guterding
  24. The global macroeconomic impacts of COVID-19: Seven scenarios By Warwick McKibbin; Roshen Fernando
  25. Cross-sectional Stock Price Prediction using Deep Learning for Actual Investment Management By Masaya Abe; Kei Nakagawa
  26. College Attainment, Income Inequality, and Economic Security: A Simulation Exercise By Brad Hershbein; Melissa Schettini Kearney; Luke W. Pardue
  27. SHIFT: A Highly Realistic Financial Market Simulation Platform By Thiago W. Alves; Ionut Florescu; George Calhoun; Dragos Bozdog
  28. Does a District-Vote Matter for the Behavior of Politicians? A Textual Analysis of Parliamentary Speeches By Born, Andreas; Janssen, Aljoscha
  29. Three Essays in Applied Microeconomics: Of Norms and Networks By Jan Sonntag
  30. How Do Expectations Affect Learning About Fundamentals? Some Experimental Evidence By Kieran Marray; Nikhil Krishna; Jarel Tang

  1. By: Jacopo Staccioli (Scuola Superiore Sant'Anna, Pisa, Italy); Mauro Napoletano (OFCE, Sciences Po, Paris, France)
    Abstract: We build an agent based model of a financial market that is able to jointly reproduce many of the stylized facts at different time-scales. These include properties related to returns (leptokurtosis, absence of linear autocorrelation, volatility clustering), trading volumes (volume clustering, correlation betwenn volume and volatility), and timing of trades (number of price changes, autocorrelation of durations between subsequent trades, heavy tails in their distribution, order-side clustering). With respect to previous contributions we introduce a strict event scheduling borrowed from the Euronext exchange, and an endogenous rule for traders participation. We show that such a rule is crucial to match stylized facts.
    Keywords: Intra-day financial dynmaics, stylized facts, agent-based artificial stock markets, Market microstructure
    JEL: C63 E12 E22 E32 O4
    Date: 2018–10
  2. By: Taran Faehn; Gabriel Bachner; Robert Beach; Jean Chateau; Shinichiro Fujimori; Madanmohan Ghosh; Meriem Hamdi-Cherif; Elisa Lanzi; Sergey Paltsev; Toon Vandyck; Bruno Cunha; Rafael Garaffa; Karl Steininger
    Abstract: Limiting global warming in line with the goals in the Paris Agreement will require substantial technological and behavioural transformations. This challenge drives many of the current modelling trends. This paper undertakes a review of 17 state-of-the-art recursive-dynamic computable general equilibrium (CGE) models and assesses the key methodologies and applied modules they use for representing sectoral energy and emission characteristics and dynamics. The purpose is to provide technical insight into recent advances in the modelling of current and future energy and abatement technologies and how they can be used to make baseline projections and scenarios 20-80 years ahead. In order to represent likely energy system transitions in the decades to come, modern CGE tools have learned from bottom-up studies. We distinguish between three different approaches to baseline quantification: (a) exploiting bottom-up model characteristics to endogenize responses of technology investment and utilization, (b) relying on external information sources to feed the exogenous parameters and variables of the model, and (c) linking the model with more technology-rich, partial models to obtain bottom-up- and pathway-consistent parameters.
    Keywords: computable general equilibrium models, long-term economic projections, energy, technology change, emissions, greenhouse gases
    JEL: C68 O13 O14 O18 Q43 Q54
    Date: 2020
  3. By: Matthew Dixon; Igor Halperin
    Abstract: We present a reinforcement learning approach to goal based wealth management problems such as optimization of retirement plans or target dated funds. In such problems, an investor seeks to achieve a financial goal by making periodic investments in the portfolio while being employed, and periodically draws from the account when in retirement, in addition to the ability to re-balance the portfolio by selling and buying different assets (e.g. stocks). Instead of relying on a utility of consumption, we present G-Learner: a reinforcement learning algorithm that operates with explicitly defined one-step rewards, does not assume a data generation process, and is suitable for noisy data. Our approach is based on G-learning - a probabilistic extension of the Q-learning method of reinforcement learning. In this paper, we demonstrate how G-learning, when applied to a quadratic reward and Gaussian reference policy, gives an entropy-regulated Linear Quadratic Regulator (LQR). This critical insight provides a novel and computationally tractable tool for wealth management tasks which scales to high dimensional portfolios. In addition to the solution of the direct problem of G-learning, we also present a new algorithm, GIRL, that extends our goal-based G-learning approach to the setting of Inverse Reinforcement Learning (IRL) where rewards collected by the agent are not observed, and should instead be inferred. We demonstrate that GIRL can successfully learn the reward parameters of a G-Learner agent and thus imitate its behavior. Finally, we discuss potential applications of the G-Learner and GIRL algorithms for wealth management and robo-advising.
    Date: 2020–02
  4. By: Lilit Popoyan (Institute of Economics (LEM), Scula superiore Sant'Anna, Pisa, Italia); Mauro Napoletano (Sciences Po OFCE, Skema Business School); Andrea Roventini (EMbe DS and Institute of Economics (LEM))
    Keywords: Financial instability, interbank market freezes, monetary policy, macro- prudential policy, Basel III regulation, Tinbergen principle, agent-based model.
    JEL: C63 E52 E6 G01 G21 G28
    Date: 2019–07
  5. By: Carmine de Franco; Christophe Geissler; Vincent Margot; Bruno Monnier
    Abstract: We designed a machine learning algorithm that identifies patterns between ESG profiles and financial performances for companies in a large investment universe. The algorithm consists of regularly updated sets of rules that map regions into the high-dimensional space of ESG features to excess return predictions. The final aggregated predictions are transformed into scores which allow us to design simple strategies that screen the investment universe for stocks with positive scores. By linking the ESG features with financial performances in a non-linear way, our strategy based upon our machine learning algorithm turns out to be an efficient stock picking tool, which outperforms classic strategies that screen stocks according to their ESG ratings, as the popular best-in-class approach. Our paper brings new ideas in the growing field of financial literature that investigates the links between ESG behavior and the economy. We show indeed that there is clearly some form of alpha in the ESG profile of a company, but that this alpha can be accessed only with powerful, non-linear techniques such as machine learning.
    Date: 2020–02
  6. By: Andreas Binder (MathConsult GmbH, Linz, Austria); Onkar Jadhav (MathConsult GmbH, Linz, Austria; Institute of Mathematics, TU Berlin, Berlin, Germany); Volker Mehrmann (Institute of Mathematics, TU Berlin, Berlin, Germany)
    Abstract: This paper presents a model order reduction (MOR) approach for high dimensional problems in the analysis of financial risk. To understand the financial risks and possible outcomes, we have to perform several thousand simulations of the underlying product. These simulations are expensive and create a need for efficient computational performance. Thus, to tackle this problem, we establish a MOR approach based on a proper orthogonal decomposition (POD) method. The study involves the computations of high dimensional parametric convection-diffusion reaction partial differential equations (PDEs). POD requires to solve the high dimensional model at some parameter values to generate a reduced-order basis. We propose an adaptive greedy sampling technique based on surrogate modeling for the selection of the sample parameter set that is analyzed, implemented, and tested on the industrial data. The results obtained for the numerical example of a floater with cap and floor under the Hull-White model indicate that the MOR approach works well for short-rate models.
    Date: 2020–02
  7. By: Evgeny Ponomarev; Ivan Oseledets; Andrzej Cichocki
    Abstract: The development of reinforced learning methods has extended application to many areas including algorithmic trading. In this paper trading on the stock exchange is interpreted into a game with a Markov property consisting of states, actions, and rewards. A system for trading the fixed volume of a financial instrument is proposed and experimentally tested; this is based on the asynchronous advantage actor-critic method with the use of several neural network architectures. The application of recurrent layers in this approach is investigated. The experiments were performed on real anonymized data. The best architecture demonstrated a trading strategy for the RTS Index futures (MOEX:RTSI) with a profitability of 66% per annum accounting for commission. The project source code is available via the following link:
    Date: 2020–02
  8. By: Akshay Krishnamurthy; Thodoris Lykouris; Chara Podimata
    Abstract: Standard game-theoretic formulations for settings like contextual pricing and security games assume that agents act in accordance with a specific behavioral model. In practice however, some agents may not prescribe to the dominant behavioral model or may act in ways that are arbitrarily inconsistent. Existing algorithms heavily depend on the model being (approximately) accurate for all agents and have poor performance in the presence of even a few such arbitrarily irrational agents. \emph{How do we design learning algorithms that are robust to the presence of arbitrarily irrational agents?} We address this question for a number of canonical game-theoretic applications by designing a robust algorithm for the fundamental problem of multidimensional binary search. The performance of our algorithm degrades gracefully with the number of corrupted rounds, which correspond to irrational agents and need not be known in advance. As binary search is the key primitive in algorithms for contextual pricing, Stackelberg Security Games, and other game-theoretic applications, we immediately obtain robust algorithms for these settings. Our techniques draw inspiration from learning theory, game theory, high-dimensional geometry, and convex analysis, and may be of independent algorithmic interest.
    Date: 2020–02
  9. By: Pang,Jun; Timilsina,Govinda R.
    Abstract: This study analyzes the potential impacts of a national emission trading scheme on provincial economies in China of meeting China's emission reduction pledges, the Nationally Determined Contributions announced under the Paris Agreement. The study developed a multiregional, multisectoral, recursive-dynamic computable general equilibrium model and calibrated it with the latest provincial-level social accounting matrices (2012). The study shows that meeting China's Nationally Determined Contributions through an emission trading scheme would reduce almost 30 percent of the emission reduction from the business as usual scenario in 2030. If the baseline is corrected based on information from a bottom-up energy sector model, TIMES, the required reduction of emissions from the baseline in 2030 drops by half, to 15 percent. At the national level, the emission trading scheme would cause a 1.2 to 1.5 percent reduction in gross domestic product from the business as usual scenario in 2030. If the baseline is corrected, the impact on gross domestic product drops by two-thirds. The emission trading scheme would cause some provincial economies to gain and others to lose. The economic impacts are highly sensitive to the allowance allocation rules. Not only the magnitudes, but also the directions of the economic impacts alter when the allocation rules change. The provinces that rely on coal mining or coal-intensive manufacturing industries are found to experience relatively larger economic losses irrespective of the allowance allocation rules.
    Keywords: Energy and Environment,Energy Demand,Energy and Mining,Oil Refining&Gas Industry,Public Sector Administrative&Civil Service Reform,Public Sector Administrative and Civil Service Reform,De Facto Governments,Democratic Government,Energy Policies&Economics,Employment and Shared Growth
    Date: 2019–06–21
  10. By: Marcelo Veracierto (Federal Reserve Bank; Federal Reserve Bank of Chicago)
    Abstract: This paper introduces a general method for computing equilibria with heterogeneous agents and aggregate shocks that is particularly suitable for economies with private information. Instead of the cross-sectional distribution of agents across individual states, the method uses as a state variable a vector of spline coefficients describing a long history of past individual decision rules. Applying the computational method to a Mirrlees RBC economy with known analytical solution recovers the solution perfectly well. This test provides considerable confidence on the accuracy of the method.
    Keywords: private information; business cycles; heterogenous agents; Computational methods
    JEL: E32 C63 E27
    Date: 2020–02–01
  11. By: Oksana Bashchenko; Alexis Marchal
    Abstract: We develop a methodology for detecting asset bubbles using a neural network. We rely on the theory of local martingales in continuous-time and use a deep network to estimate the diffusion coefficient of the price process more accurately than the current estimator, obtaining an improved detection of bubbles. We show the outperformance of our algorithm over the existing statistical method in a laboratory created with simulated data. We then apply the network classification to real data and build a zero net exposure trading strategy that exploits the risky arbitrage emanating from the presence of bubbles in the US equity market from 2006 to 2008. The profitability of the strategy provides an estimation of the economical magnitude of bubbles as well as support for the theoretical assumptions relied on.
    Date: 2020–02
  12. By: Yusuke Narita; Shota Yasui; Kohei Yata
    Abstract: We develop a method for predicting the performance of reinforcement learning and bandit algorithms, given historical data that may have been generated by a different algorithm. Our estimator has the property that its prediction converges in probability to the true performance of a counterfactual algorithm at the fast $\sqrt{N}$ rate, as the sample size $N$ increases. We also show a correct way to estimate the variance of our prediction, thus allowing the analyst to quantify the uncertainty in the prediction. These properties hold even when the analyst does not know which among a large number of potentially important state variables are really important. These theoretical guarantees make our estimator safe to use. We finally apply it to improve advertisement design by a major advertisement company. We find that our method produces smaller mean squared errors than state-of-the-art methods.
    Date: 2020–02
  13. By: Timilsina,Govinda R.; Pang,Jun; Yang,Xi
    Abstract: Many countries have undertaken market-oriented reforms of the power sector over the past four decades. However, the literature has not investigated whether the reforms have contributed to economic development. This study aims to assess the potential macroeconomic impacts of an element of the power sector reform process that China started in 2015. It uses an energy sector TIMES model and a computable general equilibrium model. The study finds that the price of electricity in China would be around 20 percent lower than the country is likely to experience in 2020, if the country follows the market principle to operate the power system. The reduction in the price of electricity would spill over throughout the economy, resulting in an increase in gross domestic product of more than 1 percent in 2020. It would also increase household income, economic welfare, and international trade.
    Keywords: Energy Policies&Economics,Energy Demand,Energy and Mining,Energy and Environment,Transport Services,Power&Energy Conversion,Energy Sector Regulation
    Date: 2019–06–21
  14. By: Pfeiffer,Basile Fabrice; Rabe,Claus; Selod,Harris; Viguie,Vincent
    Abstract: Building on a two-dimensional discrete version of the standard urban economics land-use model, this paper presents a tractable urban land-use simulation model that is adapted to developing country cities, where formal and informal housing submarkets coexist. The dynamic closed-city framework simulates developers'construction decisions and heterogeneous households'housing and location choices at a distance from various employment subcenters, while accounting at the same time for land-use regulations, natural constraints, exogenous amenities, and dynamic scenarios of urban population growth and of State-driven subsidized housing. Designed and calibrated for Cape Town, the model is used to assess the impact of an urban growth boundary and of changes in the scale of subsidized housing schemes, informing a discussion of the potential trade-offs in policy objectives and of policy effectiveness.
    Keywords: Municipal Management and Reform,Urban Housing and Land Settlements,Urban Housing,Urban Governance and Management,Transport Services,Urban Economic Development,City to City Alliances,Urban Economics,National Urban Development Policies&Strategies,Urban Communities,Regional Urban Development,Labor Markets
    Date: 2019–06–27
  15. By: Cai,Yongyang; Steinbuks,Jevgenijs; Judd,Kenneth L.; Jaegermeyr,Jonas; Hertel,Thomas W.
    Abstract: The productivity of the world's natural resources is critically dependent on a variety of highly uncertain factors, which obscure individual investors and governments that seek to make long-term, sometimes irreversible investments in their exploration and utilization. These dynamic considerations are poorly represented in disaggregated resource models, as incorporating uncertainty into large-dimensional problems presents a challenging computational task. This study introduces a novel numerical method to solve large-scale dynamic stochastic natural resource allocation problems that cannot be addressed by conventional methods. The method is illustrated with an application focusing on the allocation of global land resource use under stochastic crop yields due to adverse climate impacts and limits on further technological progress. For the same model parameters, the range of land conversion is considerably smaller for the dynamic stochastic model as compared to deterministic scenario analysis. The scenario analysis can thus significantly overstate the magnitude of expected land conversion under uncertain crop yields.
    Date: 2020–02–20
  16. By: Myriem Alijo; Otman Abdoun; Mostafa Bachran; Amal Bergam
    Abstract: The decision to locate an economic activity of one or several countries is made taking into account numerous parameters and criteria. Several studies have been carried out in this field, but they generally use information in a reduced context. The majority are based solely on parameters, using traditional methods which often lead to unsatisfactory solutions.This work consists in hybridizing through genetic algorithms, economic intelligence (EI) and multicriteria analysis methods (MCA) to improve the decisions of territorial localization. The purpose is to lead the company to locate its activity in the place that would allow it a competitive advantage. This work also consists of identifying all the parameters that can influence the decision of the economic actors and equipping them with tools using all the national and international data available to lead to a mapping of countries, regions or departments favorable to the location. Throughout our research, we have as a goal the realization of a hybrid conceptual model of economic intelligence based on multicriteria on with genetic algorithms in order to optimize the decisions of localization, in this perspective we opted for the method of PROMETHEE (Preference Ranking Organization for Method of Enrichment Evaluation), which has made it possible to obtain the best compromise between the various visions and various points of view.
    Date: 2020–01
  17. By: Tesi Aliaj; Aris Anagnostopoulos; Stefano Piersanti
    Abstract: Academics and practitioners have studied over the years models for predicting firms bankruptcy, using statistical and machine-learning approaches. An earlier sign that a company has financial difficulties and may eventually bankrupt is going in \emph{default}, which, loosely speaking means that the company has been having difficulties in repaying its loans towards the banking system. Firms default status is not technically a failure but is very relevant for bank lending policies and often anticipates the failure of the company. Our study uses, for the first time according to our knowledge, a very large database of granular credit data from the Italian Central Credit Register of Bank of Italy that contain information on all Italian companies' past behavior towards the entire Italian banking system to predict their default using machine-learning techniques. Furthermore, we combine these data with other information regarding companies' public balance sheet data. We find that ensemble techniques and random forest provide the best results, corroborating the findings of Barboza et al. (Expert Syst. Appl., 2017).
    Date: 2020–02
  18. By: Lucia Cipolina Kun
    Abstract: Abundant literature has been published on approximation methods for the forward initial margin. The most popular ones being the family of regression methods. This paper describes the mathematical foundations on which these regression approximation methods lie. We introduce mathematical rigor to show that in essence, all the methods propose variations of approximations for the conditional expectation function, which is interpreted as an orthogonal projection on Hilbert spaces. We show that each method is simply choosing a different functional form to numerically estimate the conditional expectation. We cover in particular the most popular methods in the literature so far, Polynomial approximation, Kernel regressions and Neural Networks.
    Date: 2020–02
  19. By: Tianping Zhang; Yuanqi Li; Yifei Jin; Jian Li
    Abstract: The multi-factor model is a widely used model in quantitative investment. The success of a multi-factor model is largely determined by the effectiveness of the alpha factors used in the model. This paper proposes a new evolutionary algorithm called AutoAlpha to automatically generate effective formulaic alphas from massive stock datasets. Specifically, first we discover an inherent pattern of the formulaic alphas and propose a hierarchical structure to quickly locate the promising part of space for search. Then we propose a new Quality Diversity search based on the Principal Component Analysis (PCA-QD) to guide the search away from the well-explored space for more desirable results. Next, we utilize the warm start method and the replacement method to prevent the premature convergence problem. Based on the formulaic alphas we discover, we propose an ensemble learning-to-rank model for generating the portfolio. The backtests in the Chinese stock market and the comparisons with several baselines further demonstrate the effectiveness of AutoAlpha in mining formulaic alphas for quantitative trading.
    Date: 2020–02
  20. By: Marco Pangallo
    Abstract: Comovement of economic activity across sectors and countries is a defining feature of business cycles. However, standard models that attribute comovement to propagation of exogenous shocks struggle to generate a level of comovement that is as high as in the data. In this paper, we consider models that produce business cycles endogenously, through some form of non-linear dynamics---limit cycles or chaos. These models generate stronger comovement, because they combine shock propagation with synchronization of endogenous dynamics. In particular, we study a demand-driven model in which business cycles emerge from strategic complementarities across sectors in different countries, synchronizing their oscillations through input-output linkages. We first use a combination of analytical methods and extensive numerical simulations to establish a number of theoretical results. We show that the importance that sectors or countries have in setting the common frequency of oscillations depends on their eigenvector centrality in the input-output network, and we develop an eigendecomposition that explores the interplay between non-linear dynamics, shock propagation and network structure. We then calibrate our model to data on 27 sectors and 17 countries, showing that synchronization indeed produces stronger comovement, giving more flexibility to match the data.
    Date: 2020–02
  21. By: Chi Chen; Li Zhao; Wei Cao; Jiang Bian; Chunxiao Xing
    Abstract: Nowadays, machine learning methods have been widely used in stock prediction. Traditional approaches assume an identical data distribution, under which a learned model on the training data is fixed and applied directly in the test data. Although such assumption has made traditional machine learning techniques succeed in many real-world tasks, the highly dynamic nature of the stock market invalidates the strict assumption in stock prediction. To address this challenge, we propose the second-order identical distribution assumption, where the data distribution is assumed to be fluctuating over time with certain patterns. Based on such assumption, we develop a second-order learning paradigm with multi-scale patterns. Extensive experiments on real-world Chinese stock data demonstrate the effectiveness of our second-order learning paradigm in stock prediction.
    Date: 2020–02
  22. By: Greg Lewis; Vasilis Syrgkanis
    Abstract: We consider the estimation of treatment effects in settings when multiple treatments are assigned over time and treatments can have a causal effect on future outcomes. We formulate the problem as a linear state space Markov process with a high dimensional state and propose an extension of the double/debiased machine learning framework to estimate the dynamic effects of treatments. Our method allows the use of arbitrary machine learning methods to control for the high dimensional state, subject to a mean square error guarantee, while still allowing parametric estimation and construction of confidence intervals for the dynamic treatment effect parameters of interest. Our method is based on a sequential regression peeling process, which we show can be equivalently interpreted as a Neyman orthogonal moment estimator. This allows us to show root-n asymptotic normality of the estimated causal effects.
    Date: 2020–02
  23. By: Daniel Guterding
    Abstract: The VSTOXX index tracks the expected 30-day volatility of the EURO STOXX 50 equity index. Futures on the VSTOXX index can, therefore, be used to hedge against economic uncertainty. We investigate the effect of trader inventory on the price of VSTOXX futures through a combination of stochastic processes and machine learning methods. We formulate a simple and efficient pricing methodology for VSTOXX futures, which assumes a Heston-type stochastic process for the underlying EURO STOXX 50 market. Under these dynamics, approximate analytical formulas for the implied volatility smile and the VSTOXX index have recently been derived. We use the EURO STOXX 50 option implied volatilities and the VSTOXX index value to estimate the parameters of this Heston model. Following the calibration, we calculate theoretical VSTOXX future prices and compare them to the actual market prices. While theoretical and market prices are usually in line, we also observe time periods, during which the market price does not agree with our Heston model. We collect a variety of market features that could potentially explain the price deviations and calibrate two machine learning models to the price difference: a regularized linear model and a random forest. We find that both models indicate a strong influence of accumulated trader positions on the VSTOXX futures price.
    Date: 2020–02
  24. By: Warwick McKibbin; Roshen Fernando
    Abstract: The outbreak of coronavirus named COVID-19 has disrupted the Chinese economy and is spreading globally. The evolution of the disease and its economic impact is highly uncertain which makes it difficult for policymakers to formulate an appropriate macroeconomic policy response. In order to better understand possible economic outcomes, this paper explores seven different scenarios of how COVID-19 might evolve in the coming year using a modelling technique developed by Lee and McKibbin (2003) and extended by McKibbin and Sidorenko (2006). It examines the impacts of different scenarios on macroeconomic outcomes and financial markets in a global hybrid DSGE/CGE general equilibrium model.The scenarios in this paper demonstrate that even a contained outbreak could significantly impact the global economy in the short run. These scenarios demonstrate the scale of costs that might be avoided by greater investment in public health systems in all economies but particularly in less developed economies where health care systems are less developed and popultion density is high.
    Keywords: Pandemics, infectious diseases, risk, macroeconomics, DSGE, CGE, G-Cubed
    Date: 2020–03
  25. By: Masaya Abe; Kei Nakagawa
    Abstract: Stock price prediction has been an important research theme both academically and practically. Various methods to predict stock prices have been studied until now. The feature that explains the stock price by a cross-section analysis is called a "factor" in the field of finance. Many empirical studies in finance have identified which stocks having features in the cross-section relatively increase and which decrease in terms of price. Recently, stock price prediction methods using machine learning, especially deep learning, have been proposed since the relationship between these factors and stock prices is complex and non-linear. However, there are no practical examples for actual investment management. In this paper, therefore, we present a cross-sectional daily stock price prediction framework using deep learning for actual investment management. For example, we build a portfolio with information available at the time of market closing and invest at the time of market opening the next day. We perform empirical analysis in the Japanese stock market and confirm the profitability of our framework.
    Date: 2020–02
  26. By: Brad Hershbein; Melissa Schettini Kearney; Luke W. Pardue
    Abstract: We conduct an empirical simulation exercise that gauges the plausible impact of increased rates of college attainment on a variety of measures of income inequality and economic insecurity. Using two different methodological approaches—a distributional approach and a causal parameter approach—we find that increased rates of bachelor’s and associate degree attainment would meaningfully increase economic security for lower-income individuals, reduce poverty and near-poverty, and shrink gaps between the 90th and lower percentiles of the earnings distribution. However, increases in college attainment would not significantly reduce inequality at the very top of the distribution.
    JEL: I24 I26 I30 J21 J24 J31
    Date: 2020–02
  27. By: Thiago W. Alves; Ionut Florescu; George Calhoun; Dragos Bozdog
    Abstract: This paper presents a new financial market simulator that may be used as a tool in both industry and academia for research in market microstructure. It allows multiple automated traders and/or researchers to simultaneously connect to an exchange-like environment, where they are able to asynchronously trade several financial assets at the same time. In its current iteration, this order-driven market implements the basic rules of U.S. equity markets, supporting both market and limit orders, and executing them in a first-in-first-out fashion. We overview the system architecture and we present possible use cases. We demonstrate how a set of automated agents is capable of producing a price process with characteristics similar to the statistics of real price from financial markets. Finally, we detail a market stress scenario and we draw, what we believe to be, interesting conclusions about crash events.
    Date: 2020–02
  28. By: Born, Andreas (Department of Economics); Janssen, Aljoscha (Singapore Management University)
    Abstract: In most democracies, members of parliament are either elected over a party list or by a district. We use a discontinuity in the German parliamentary system to investigate the causal effect of a district-election on an MP’s conformity with her party-line. A district-election does not affect roll call voting behavior causally, possibly due to overall high adherence to party voting. Analyzing the parliamentary speeches of each MP allows us to overcome the high party discipline with regard to parliamentary voting. Using textual analysis and machine learning techniques, we create two measures of closeness of an MP’s speeches to her party. We find that district-elected members of parliament do not differ, in terms of speeches, from those of their party-peers who have been elected through closed party lists. However, both speeches and voting correlate with district characteristics suggesting that district-elections allow districts to select more similar politicians.
    Keywords: Party-line; Textual Analysis; Regression Discontinuity; Parliamentary Speeches; Voting
    JEL: D72
    Date: 2020–02–24
  29. By: Jan Sonntag (Département d'économie)
    Abstract: Cette thèse s’articule autour de deux thèmes : les normes sociales et les réseaux de production. Le premier chapitre porte sur une étude de cas où les normes sociales sont utilisées dans la lutte contre le discours haineux en ligne. A l’aide de méthodes de machine learning, je montre que le fait de dénoncer les opinions haineuses est un moyen de dissuader d'autres discours haineux. Cet effet s’explique par le fait que cette forme de contradiction sert de communiquer la présence d'une norme sociale ou en accentue l'importance. Au-delà de la lutte contre les discriminations, ce chapitre peut nous éclairer sur la façon dont les normes influencent le comportement politique plus généralement. Le deuxième chapitre porte sur le rôle que joue le goût pour l'image sociale pour expliquer l'effet des normes sociales sur le comportement. De nombreuses études montrent que ces goûts affectent le comportement des gens en moyenne, mais nous ne savons pas encore quels individus sont les plus susceptibles d’adapter leur comportement. Je présente une expérience novatrice conçue pour combler ce vide. Elle permet de calculer une mesure individuelle de préoccupation pour l'image, montre qu'il y a une hétérogénéité substantielle et analyse sa corrélation avec d'autres préférences sociales. Le dernier chapitre étudie les réseaux de production. L'intégration verticale des entreprises peut donner lieu à des comportements anticoncurrentiels. J'aborde l'un de ces comportements, appelé verrouillage, par lequel les entreprises verticalement intégrées coupent l'approvisionnement de leurs concurrents en intrants essentiels. J'utilise de nouvelles données sur les réseaux de production pour identifier les fusions et acquisitions entre entreprises verticalement liées. Je montre ces fusions affectent les chaînes d'approvisionnement de leurs concurrents et j’interprète cela comme preuve de verrouillage.
    Keywords: Discours haineux , Normes sociales, Gout pour l’image, Verrouillage de marché; Hate speech, Social norms, Image concerns, Vertical foreclosure
    Date: 2019–12
  30. By: Kieran Marray (Mathematical Institute, University of Oxford; Institute for New Economic Thinking at the Oxford Martin School, University of Oxford); Nikhil Krishna (Trinity College, University of Oxford); Jarel Tang (The Queen's College, University of Oxford)
    Abstract: Individuals' output often depends not just on their ability and actions, but also on external factors or fundamentals, whose effect they cannot separately identify. At the same time, many individuals have incorrect beliefs about their own ability. Heidhues et al. (2018) characterise overconfident and underconfident individuals' equilibrium beliefs and learning process in these situations. They argue overconfident individuals will act sub-optimally because of how they learn. We carry out the first experimental test their theory. Subjects take incorrectly marked tests, and we measure how they learn about the marker's accuracy over time. We use machine learning to identify heterogeneous effects. Overconfident subjects have lower beliefs about the fundamental, as Heidhues et al. predict, and thus would make sub-optimal decisions. But we find no evidence it is because of how they learn.
    Date: 2020–02

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.