nep-cmp New Economics Papers
on Computational Economics
Issue of 2022‒11‒21
nineteen papers chosen by
Stan Miles
Thompson Rivers University

  1. Whatever it Takes to Understand a Central Banker – Embedding their Words Using Neural Networks. By Zahner, Johannes; Baumgärtner, Martin
  2. Using Deep Learning to Find the Next Unicorn: A Practical Synthesis By Lele Cao; Vilhelm von Ehrenheim; Sebastian Krakowski; Xiaoxue Li; Alexandra Lutz
  3. Cyber-Risk Forecasting using Machine Learning Models and Generalized Extreme Value Distributions By Jules Sadefo Kamdem; Danielle Selambi
  4. Dissecting the explanatory power of ESG features on equity returns by sector, capitalization, and year with interpretable machine learning By Jeremi Assael; Laurent Carlier; Damien Challet
  5. Why Do Men Keep Swiping Right? Two-Sided Search in Swipe-Based Dating Platforms By Hernandez Senosiain, Patricio
  6. Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis By Luca Galimberti; Giulia Livieri; Anastasis Kratsios
  7. Fractal landscape dynamics in dense emulsions and stock prices By Clary Rodriguez-Cruz; Mehdi Molaei; Amruthesh Thirumalaiswamy; Klebert Feitosa; Vinothan N. Manoharan; Shankar Sivarajan; Daniel H. Reich; Robert A. Riggleman; John C. Crocker
  8. Identifiability and Generalizability from Multiple Experts in Inverse Reinforcement Learning By Paul Rolland; Luca Viano; Norman Schürhoff; Boris Nikolov; Volkan Cevher
  9. Inter-regional System Of Analysis For East Asia: A Manual By Yuventus Effendi; Budy Resosudarmo
  10. Tweeting for Money: Social Media and Mutual Fund Flows By Javier Gil-Bazo; Juan F. Imbet
  11. Learning to simulate realistic limit order book markets from data as a World Agent By Andrea Coletta; Aymeric Moulin; Svitlana Vyetrenko; Tucker Balch
  12. American options in the Volterra Heston model By Etienne Chevalier; Sergio Pulido; Elizabeth Zúñiga
  13. Learning Poverty : Measures and Simulations By Azevedo,Joao Pedro Wagner De
  14. The impact of big winners on passive and active investment strategies By Maxime Markov
  15. Endogenous Innovation Scale and Patent Policy in a Monetary Schumpeterian Growth Model By Yu, Po-yang; Lai, Ching-Chong
  16. Moving from Linear to Conic Markets for Electricity By Anubhav Ratha; Pierre Pinson; Hélène Le Cadre; Ana Virag; Jalal Kazempour
  17. Factor price divergence in Heckscher-Ohlin model when countries have different technologies: a simple numerical illustration By Spirin, Victor
  18. Exploring the stability of solar geoengineering agreements By Niklas V. Lehmann
  19. The Effects of Admitting Immigrants: A Look at Japan’s School and Pension Systems By Jinno, Masatoshi; Yasuoka, Masaya

  1. By: Zahner, Johannes; Baumgärtner, Martin
    JEL: C45 C53 E52 Z13
    Date: 2022
  2. By: Lele Cao; Vilhelm von Ehrenheim; Sebastian Krakowski; Xiaoxue Li; Alexandra Lutz
    Abstract: Startups often represent newly established business models associated with disruptive innovation and high scalability. They are commonly regarded as powerful engines for economic and social development. Meanwhile, startups are heavily constrained by many factors such as limited financial funding and human resources. Therefore the chance for a startup to eventually succeed is as rare as ``spotting a unicorn in the wild''. Venture Capital (VC) strives to identify and invest in unicorn startups during their early stages, hoping to gain a high return. To avoid entirely relying on human domain expertise and intuition, investors usually employ data-driven approaches to forecast the success probability of startups. Over the past two decades, the industry has gone through a paradigm shift moving from conventional statistical approaches towards becoming machine-learning (ML) based. Notably, the rapid growth of data volume and variety is quickly ushering in deep learning (DL), a subset of ML, as a potentially superior approach in terms capacity and expressivity. In this work, we carry out a literature review and synthesis on DL-based approaches, covering the entire DL life cycle. The objective is a) to obtain a thorough and in-depth understanding of the methodologies for startup evaluation using DL, and b) to distil valuable and actionable learning for practitioners. To the best of our knowledge, our work is the first of this kind.
    Date: 2022–10
  3. By: Jules Sadefo Kamdem (MRE - Montpellier Recherche en Economie - UM - Université de Montpellier); Danielle Selambi (African Institute for Mathematical Sciences (AIMS-Cameroon))
    Abstract: In this paper, we estimate the cost of a data breach using the number of compromised records. The number of such records is predicted by means of a machine learning model, particularly the Random Forest. We further analyse the fat tail phenomena which capture the underlying dynamics in the number of affected records. The objective is to calculate the maximum loss in order to answer the question of the insurability of cyber risk. Our results show that the total number of affected records follow a Frechet distribution, and we then estimate the Generalized Extreme Value (GEV) parameters to calculate the value at risk (VaR). This analysis is critical because it gives an idea of the maximum loss that can be generated by an enterprise data breach. These results are usable in anticipating the premiums for cyber risk coverage in the insurance markets.
    Keywords: Cyber insurance,Cyber risk,Machine Learning,Regression Trees,Random Forest,Generalized Extreme Value
    Date: 2022–10–13
  4. By: Jeremi Assael (BNPP CIB GM Lab - BNP Paribas CIB Global Markets Data & AI Lab, MICS - Mathématiques et Informatique pour la Complexité et les Systèmes - CentraleSupélec - Université Paris-Saclay); Laurent Carlier (BNPP CIB GM Lab - BNP Paribas CIB Global Markets Data & AI Lab); Damien Challet (MICS - Mathématiques et Informatique pour la Complexité et les Systèmes - CentraleSupélec - Université Paris-Saclay)
    Abstract: We systematically investigate the links between price returns and ESG features in the European market. We propose a cross-validation scheme with random company-wise validation to mitigate the relative initial lack of quantity and quality of ESG data, which allows us to use most of the latest and best data to both train and validate our models. Boosted trees successfully explain a part of 1 annual price returns not accounted by the market factor. We check with benchmark features that ESG features do contain significantly more information than basic fundamental features alone. The most relevant sub-ESG feature encodes controversies. Finally, we find opposite effects of better ESG scores on the price returns of small and large capitalization companies: better ESG scores are generally associated with larger price returns for the latter, and reversely for the former.
    Keywords: ESG features,sustainable investing,interpretable machine learning,model selection,asset management,equity returns
    Date: 2022–09–29
  5. By: Hernandez Senosiain, Patricio (University of Warwick)
    Abstract: In today’s love market, swipe-based dating platforms (SBDPs) such as Tinder or Bumble have a well-established presence, but novel platform features can add significant complexities to the user’s search problem in ways that have been largely under-studied in previous literature. This paper formulates a model of two-sided search within SBDPs, where agents with heterogeneous preferences seek multipleromantic partners whilst facing intertemporal action constraints. Using numerical methods, I approximate stationary equilibria and perform comparative statics onvarious exogenous parameters that help explain stylised empirical facts. Finally, agent-based simulations are used to asses the structure of stationary equilibria as well as its attainability under myopic best-response dynamics.
    Keywords: Optimal Search ; Two Sided Matching ; Agent-Based Modeling JEL Classification: C78 ; D83 ; C63
    Date: 2022
  6. By: Luca Galimberti; Giulia Livieri; Anastasis Kratsios
    Abstract: Deep learning (DL) is becoming indispensable to contemporary stochastic analysis and finance; nevertheless, it is still unclear how to design a principled DL framework for approximating infinite-dimensional causal operators. This paper proposes a "geometry-aware" solution to this open problem by introducing a DL model-design framework that takes a suitable infinite-dimensional linear metric spaces as inputs and returns a universal sequential DL models adapted to these linear geometries: we call these models Causal Neural Operators (CNO). Our main result states that the models produced by our framework can uniformly approximate on compact sets and across arbitrarily finite-time horizons H\"older or smooth trace class operators which causally map sequences between given linear metric spaces. Consequentially, we deduce that a single CNO can efficiently approximate the solution operator to a broad range of SDEs, thus allowing us to simultaneously approximate predictions from families of SDE models, which is vital to computational robust finance. We deduce that the CNO can approximate the solution operator to most stochastic filtering problems, implying that a single CNO can simultaneously filter a family of partially observed stochastic volatility models.
    Date: 2022–10
  7. By: Clary Rodriguez-Cruz; Mehdi Molaei; Amruthesh Thirumalaiswamy; Klebert Feitosa; Vinothan N. Manoharan; Shankar Sivarajan; Daniel H. Reich; Robert A. Riggleman; John C. Crocker
    Abstract: Many soft and biological materials display so-called 'soft glassy' dynamics; their constituents undergo anomalous random motion and intermittent cooperative rearrangements. Stock prices show qualitatively similar dynamics, whose origins also remain poorly understood. Recent simulations of a foam have revealed that such motion is due to the system evolving in a high-dimensional configuration space via energy minimization on a slowly changing, fractal energy landscape. Here we show that the salient geometrical features of such energy landscapes can be explored and quantified not only in simulation but empirically using real-world, high-dimensional data. In a mayonnaise-like dense emulsion, the experimentally observed motion of oil droplets shows that the fractal geometry of the configuration space paths and energy landscape gives rise to the anomalous random motion and cooperative rearrangements, confirming corresponding simulations in detail. Our empirical approach allows the same analyses to be applied to the component stock prices of the Standard and Poor's 500 Index. This analysis yields remarkably similar results, revealing that stock return dynamics also appear due to prices moving on a similar, slowly evolving, high-dimensional fractal landscape.
    Date: 2022–10
  8. By: Paul Rolland (Ecole Polytechnique Fédérale de Lausanne); Luca Viano (Ecole Polytechnique Fédérale de Lausanne); Norman Schürhoff (Swiss Finance Institute - HEC Lausanne); Boris Nikolov (University of Lausanne; Swiss Finance Institute; European Corporate Governance Institute (ECGI)); Volkan Cevher (Ecole Polytechnique Fédérale de Lausanne)
    Abstract: While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert’s behavior. It is well known that, in general, various reward functions can lead to the same optimal policy, and hence, IRL is ill-defined. However, [1] showed that, if we observe two or more experts with different discount factors or acting in different environments, the reward function can under certain conditions be identified up to a constant. This work starts by showing an equivalent identifiability statement from multiple experts in tabular MDPs based on a rank condition, which is easily verifiable and is shown to be also necessary. We then extend our result to various different scenarios, i.e., we characterize reward identifiability in the case where the reward function can be represented as a linear combination of given features, making it more interpretable, or when we have access to approximate transition matrices. Even when the reward is not identifiable, we provide conditions characterizing when data on multiple experts in a given environment allows to generalize and train an optimal agent in a new environment. Our theoretical results on reward identifiability and generalizability are validated in various numerical experiments.
    Date: 2022–10
  9. By: Yuventus Effendi (Indonesian Ministry of Finance, Republic of Indonesia, Jakarta, Indonesia); Budy Resosudarmo (Indonesia Project, Arndt-Corden Department of Economics, Crawford School of Public Policy, Australian National University, Canberra, Australia)
    Abstract: This paper provides detail of the inter-regional system of analysis of East Asia (IRSA-EA). IRSA-EA is a static and multi-country computable general equilibrium (CGE) model. IRSA-EA has a flexible production structure that allows substitutions among electricity and energy intermediate inputs. Hence, the model can simulate the impacts of changes in energy and electricity prices. Also, the model incorporates several recycling mechanisms to simulate the impacts of renewable electricity development and decarbonisation in the East Asia region. This paper provides a technical guide for the IRSA-EA model that will be useful to analyse the socio-economic and environmental impacts of policy instruments in the subsequent two papers.
    Keywords: Climate change, computable general equilibrium model, East Asian economy
    JEL: O21
    Date: 2022–10
  10. By: Javier Gil-Bazo; Juan F. Imbet
    Abstract: We investigate whether asset management firms use social media to persuade investors. Combining a database of almost 1.6 million Twitter posts by U.S. mutual fund families with textual analysis, we find that flows of money to mutual funds respond positively to tweets with a positive tone. Consistently with the persuasion hypothesis, positive tweets work best when they convey advice or views on the market and when investor sentiment is higher. Using a high-frequency approach, we are able to identify a short-lived impact of families' tweets on ETF share prices. Finally, we reject the alternative hypothesis that asset management companies use social media to alleviate information asymmetries by either lowering search costs or disclosing privately observed information.
    Keywords: social media, Twitter, persuasion, mutual funds, mutual fund, flows, machine learning, textual analysis
    JEL: G11 G23 D83
    Date: 2022–10
  11. By: Andrea Coletta; Aymeric Moulin; Svitlana Vyetrenko; Tucker Balch
    Abstract: Multi-agent market simulators usually require careful calibration to emulate real markets, which includes the number and the type of agents. Poorly calibrated simulators can lead to misleading conclusions, potentially causing severe loss when employed by investment banks, hedge funds, and traders to study and evaluate trading strategies. In this paper, we propose a world model simulator that accurately emulates a limit order book market -- it requires no agent calibration but rather learns the simulated market behavior directly from historical data. Traditional approaches fail short to learn and calibrate trader population, as historical labeled data with details on each individual trader strategy is not publicly available. Our approach proposes to learn a unique "world" agent from historical data. It is intended to emulate the overall trader population, without the need of making assumptions about individual market agent strategies. We implement our world agent simulator models as a Conditional Generative Adversarial Network (CGAN), as well as a mixture of parametric distributions, and we compare our models against previous work. Qualitatively and quantitatively, we show that the proposed approaches consistently outperform previous work, providing more realism and responsiveness.
    Date: 2022–09
  12. By: Etienne Chevalier (LaMME - Laboratoire de Mathématiques et Modélisation d'Evry - UEVE - Université d'Évry-Val-d'Essonne - ENSIIE - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement); Sergio Pulido (LaMME - Laboratoire de Mathématiques et Modélisation d'Evry - UEVE - Université d'Évry-Val-d'Essonne - ENSIIE - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement); Elizabeth Zúñiga (LaMME - Laboratoire de Mathématiques et Modélisation d'Evry - UEVE - Université d'Évry-Val-d'Essonne - ENSIIE - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement)
    Abstract: We price American options using kernel-based approximations of the Volterra Heston model. We choose these approximations because they allow simulation-based techniques for pricing. We prove the convergence of American option prices in the approximating sequence of models towards the prices in the Volterra Heston model. A crucial step in the proof is to exploit the affine structure of the model in order to establish explicit formulas and convergence results for the conditional Fourier--Laplace transform of the log price and an adjusted version of the forward variance. We illustrate with numerical examples our convergence result and the behavior of American option prices with respect to certain parameters of the model.
    Date: 2022–04–27
  13. By: Azevedo,Joao Pedro Wagner De
    Abstract: COVID-19-related school closures are pushing countries off track from achieving their learning goals. This paper builds on the concept of learning poverty and draws on axiomatic properties from social choice literature to propose and motivate a distribution-sensitive measures of learning poverty. Numerical, empirical, and practical reasons for the relevance and usefulness of these complementary inequality sensitive aggregations for simulating the effects of COVID-19 are presented. In a post-COVID-19 scenario of no remediation and low mitigation effectiveness for the effects of school closures, the simulations show that learning poverty increases from 53 to 63 percent. Most of this increase seems to occur in lower-middle-income and upper-middle-income countries, especially in East Asia and the Pacific, Latin America, and South Asia. The countries that had the highest levels of learning poverty before COVID-19 (predominantly in Africa and the low-income country group) might have the smallest absolute and relative increases in learning poverty, reflecting how great the learning crisis was in those countries before the pandemic. Measures of learning poverty and learning deprivation sensitive to changes in distribution, such as gap and severity measures, show differences in learning loss regional rankings. Africa stands to lose the most. Countries with higher inequality among the learning poor, as captured by the proposed learning poverty severity measure, would need far greater adaptability to respond to broader differences in student needs.
    Keywords: null
    Date: 2020–10–21
  14. By: Maxime Markov
    Abstract: We systematically study the impact of big winners on the performance of active and passive (index) investment strategies. We show that active managers face significant chances of under-performance due to the risk of missing big winners. We present both numerical and analytical techniques to study the phenomena.
    Date: 2022–10
  15. By: Yu, Po-yang; Lai, Ching-Chong
    Abstract: This paper develops a monetary R&D-driven endogenous growth model featuring endogenous innovation scales and the price-marginal cost markup. To endogenize the step size of quality improvement, we propose a trade-off mechanism between the risk of innovation failure and the benefit of innovation success in R&D firms. Several findings emerge from the analysis. First, a rise in the nominal interest rate decreases economic growth; however, its relationship with social welfare is ambiguous. Second, either strengthening patent protection or raising the professional knowledge of R&D firms leads to an ambiguous effect on economic growth. Third, the Friedman rule of a zero nominal interest rate fails to be optimal in view of the social welfare maximum. Finally, our numerical analysis indicates that the extent of patent protection and the level of an R&D firm’s professional knowledge play a crucial role in determining the optimal interest rate.
    Keywords: Intellectual property rights; Economic growth; Endogenous innovation scales; Endogenous markups; Inflation
    JEL: E41 L11 O30 O40
    Date: 2022–10–17
  16. By: Anubhav Ratha (DTU Electrical Engineering [Lyngby] - DTU - Danmarks Tekniske Universitet = Technical University of Denmark); Pierre Pinson (Imperial College London); Hélène Le Cadre (Inria Lille - Nord Europe - Inria - Institut National de Recherche en Informatique et en Automatique); Ana Virag (VITO - Flemish Institute for Technological Research); Jalal Kazempour (DTU Electrical Engineering [Lyngby] - DTU - Danmarks Tekniske Universitet = Technical University of Denmark)
    Abstract: We propose a new forward electricity market framework that admits heterogeneous market participants with second-order cone strategy sets, who accurately express the nonlinearities in their costs and constraints through conic bids, and a network operator facing conic operational constraints. In contrast to the prevalent linear-programming-based electricity markets, we highlight how the inclusion of second-order cone constraints improves uncertainty-, asset-, and network-awareness of the market, which is key to the successful transition towards an electricity system based on weather-dependent renewable energy sources. We analyze our general market-clearing proposal using conic duality theory to derive efficient spatially-differentiated prices for the multiple commodities, comprised of energy and flexibility services. Under the assumption of perfect competition, we prove the equivalence of the centrally-solved market-clearing optimization problem to a competitive spatial price equilibrium involving a set of rational and self-interested participants and a price setter. Finally, under common assumptions, we prove that moving towards conic markets does not incur the loss of desirable economic properties of markets, namely market efficiency, cost recovery, and revenue adequacy. Our numerical studies focus on the specific use case of uncertainty-aware market design and demonstrate that the proposed conic market brings advantages over existing alternatives within the linear programming market framework.
    Keywords: OR in energy,spatial equilibrium,mechanism design,electricity markets,conic economics
    Date: 2022–10–06
  17. By: Spirin, Victor
    Abstract: One of the main criticisms of the modern trade theories is that they are based on the assumption of equivalent technologies in the trading countries. These theories explicitly assume that the trading partners possess identical technologies, and the difference in the amount of goods produced is solely due to the differences in factor endowments. In effect, opening to trade between two countries with different factor endowments is an optimization problem that redistributes labor and capital between the types of goods produced to maximize the world output. In this optimization problem both trade participants benefit from free trade, and it is possible to make everybody win. But if the two countries possess different technologies, the result is quite opposite. The optimization problem leads to the destruction of capital in the country with less efficient technology. While the main conclusions of the theory – the owners of export-oriented factor of production win and capital-abundant country will export capital-intensive goods and vice versa – will hold, the country with less efficient pre-trade technology will lose the technology altogether, and the total output of that country will fall as a result of free trade.
    Keywords: Free trade, Heckscher-Ohlin model, Vanek-Reinert effect, International economics.
    JEL: F6 F62 F63
    Date: 2022–10–16
  18. By: Niklas V. Lehmann
    Abstract: A simple model is introduced to study the cooperative behavior of nations regarding solar geoengineering. The results of this model are explored through numerical methods. A general finding is that cooperation and coordination between nations on solar geoengineering is very much incentivized. Furthermore, the stability of solar geoengineering agreements between nations crucially depends on the perceived riskiness of solar geoengineering. If solar geoengineering is perceived as riskier, the stability of the most stable solar geoengineering agreements is reduced. However, the stability of agreements is completely independent of countries preferences.
    Date: 2022–10
  19. By: Jinno, Masatoshi; Yasuoka, Masaya
    Abstract: This paper investigates the effects of admitting immigrants to Japan on the welfare of native Japanese residents. The paper considers the imperfect substitutability between native and immigrant laborers in line with the pension and education systems. It is argued that immigration may have indirect negative effects, for example, imposing the additional burden of educating immigrant children who require additional support to master the Japanese culture, customs, and language. This research uses numerical data analysis of Japan. The findings indicate that admitting immigrants, even when they are not perfectly complementary, might increase the wage level and the utility of the natives. There are also direct implications on the type of pension system that is available for natives and immigrants. This study recommends that the defined replacement rate pension system is preferable for natives when there is a relatively substitutable relationship between natives and immigrants.
    Keywords: Immigrants, Burden of schooling, Pension, Substitutability, Complementarity.
    JEL: H52 H55 J61
    Date: 2022–10–27

This nep-cmp issue is ©2022 by Stan Miles. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.