nep-cmp New Economics Papers
on Computational Economics
Issue of 2018‒07‒30
thirteen papers chosen by
Stan Miles
Thompson Rivers University

  1. Financial Trading as a Game: A Deep Reinforcement Learning Approach By Chien Yi Huang
  2. "Bitcoin Technical Trading with Articial Neural Network" By Masafumi Nakano; Akihiko Takahashi; Soichiro Takahashi
  3. The Energy Efficiency Rebound Effect in General Equilibrium By Christoph Böhringer; Nicholas Rivers
  4. Compensating households from carbon tax regressivity and fuel poverty: a microsimulation study By Audrey Berry
  5. Nonparametric model calibration for derivatives By Frédéric Abergel; Rémy Tachet Des Combes; Riadh Zaatour
  6. Generic machine learning inference on heterogenous treatment effects in randomized experiments By Victor Chernozhukov; Mert Demirer; Esther Duflo; Ivan Fernandez-Val
  7. Simulating the Macroeconomic Effects of Unconventional Monetary Policies By Hess Chung; Cynthia L. Doniger; Cristina Fuentes-Albero; Bernd Schlusche; Wei Zheng
  8. Trade and welfare effects of a potential free trade agreement between Japan and the United States By Walter, Timo
  9. The behaviour of betting and currency markets on the night of the EU referendum By Tom Auld; Oliver Linton
  10. When are credit gap estimates reliable? By Elena Deryugina; Alexey Ponomarenko; Anna Rozhkova
  11. The effect of genetic algorithm learning with a classifier system in limit order markets By Lijian Wei; Xiong Xiong; Wei Zhang; Xue-Zhong He; Yongjie Zhang
  12. Exact and robust conformal inference methods for predictive machine learning with dependent data By Victor Chernozhukov; Kaspar Wüthrich; Yinchu Zhu
  13. Should Central Banks Prick Asset Price Bubbles? An Analysis Based on a Financial Accelerator Model with an Agent-Based Financial Market By Alexey Vasilenko

  1. By: Chien Yi Huang
    Abstract: An automatic program that generates constant profit from the financial market is lucrative for every market practitioner. Recent advance in deep reinforcement learning provides a framework toward end-to-end training of such trading agent. In this paper, we propose an Markov Decision Process (MDP) model suitable for the financial trading task and solve it with the state-of-the-art deep recurrent Q-network (DRQN) algorithm. We propose several modifications to the existing learning algorithm to make it more suitable under the financial trading setting, namely 1. We employ a substantially small replay memory (only a few hundreds in size) compared to ones used in modern deep reinforcement learning algorithms (often millions in size.) 2. We develop an action augmentation technique to mitigate the need for random exploration by providing extra feedback signals for all actions to the agent. This enables us to use greedy policy over the course of learning and shows strong empirical performance compared to more commonly used epsilon-greedy exploration. However, this technique is specific to financial trading under a few market assumptions. 3. We sample a longer sequence for recurrent neural network training. A side product of this mechanism is that we can now train the agent for every T steps. This greatly reduces training time since the overall computation is down by a factor of T. We combine all of the above into a complete online learning algorithm and validate our approach on the spot foreign exchange market.
    Date: 2018–07
  2. By: Masafumi Nakano (Graduate School of Economics, Faculty of Economics, The University of Tokyo); Akihiko Takahashi (Faculty of Economics, The University of Tokyo); Soichiro Takahashi (Graduate School of Economics, Faculty of Economics, The University of Tokyo)
    Abstract: This paper explores Bitcoin intraday technical trading based on artificial neural networks for the return prediction. In particular, our deep learning method successfully discovers trading signals through a seven layered neural network structure for given input data of technical indicators, which are calculated by the past time-series data over every 15 minutes. Under feasible settings of execution costs, the numerical experiments demonstrate that our approach significantly improves the performance of a buy-and-hold strategy. Especially, our model performs well for a challenging period from December 2017 to January 2018, during which Bitcoin suffers from substantial minus returns. Furthermore, various sensitivity analysis is implemented for the change of the number of layers, activation functions, input data and output classification to confirm the robustness of our approach.
    Date: 2018–07
  3. By: Christoph Böhringer; Nicholas Rivers
    Abstract: We develop a stylized general equilibrium model to decompose the rebound effect of energy efficiency improvements into its partial and general equilibrium components. In our theoretical analysis, we identify key drivers of the general equilibrium rebound effect, including a composition channel, an energy price channel, a labor supply channel, and a growth channel. Based on numerical simulations with both the stylized model as well as a large-scale computable general equilibrium model of the global economy, we show that both general and partial equilibrium components of the rebound effect can be substantial. Our benchmark parameterization suggests a total rebound effect due to an exogenous energy efficiency improvement in the US manufacturing sector of 67% with roughly two-thirds occurring through the partial equilibrium rebound channel and the remaining one-third occurring through the general equilibrium rebound channel.
    Keywords: energy efficiency, climate change, rebound effect, general equilibrium
    JEL: C68 D58 Q43 Q55
    Date: 2018
  4. By: Audrey Berry (CIRED - Centre International de Recherche sur l'Environnement et le Développement - CNRS - Centre National de la Recherche Scientifique - ENPC - École des Ponts ParisTech - AgroParisTech - EHESS - École des hautes études en sciences sociales - CIRAD - Centre de Coopération Internationale en Recherche Agronomique pour le Développement)
    Abstract: For households, taxing carbon raises the cost of the energy they use to heat their home and to travel. This paper studies the distributional impacts of the recently introduced French carbon tax and the design of compensation measures. Using a microsimulation model built on a representative sample of the French population from 2012, I simulate for each household the taxes levied on its consumption of energy for housing and transport. Without recycling, the carbon tax is regressive and increases fuel poverty. However, I show how compensation measures can offset these impacts. A flat cash transfer offsets tax regressivity by redistributing
    Keywords: Carbon tax,Distributional impacts,Fuel poverty,Revenue recycling,Microsimulation
    Date: 2018–01–23
  5. By: Frédéric Abergel (FiQuant - Chaire de finance quantitative - Ecole Centrale Paris - CentraleSupélec); Rémy Tachet Des Combes (FiQuant - Chaire de finance quantitative - Ecole Centrale Paris - CentraleSupélec); Riadh Zaatour (MAS - Mathématiques Appliquées aux Systèmes - EA 4037 - Ecole Centrale Paris)
    Abstract: Consistently fitting vanilla option surfaces is an important issue in derivative modelling. In this paper, we consider three different models: local and stochastic volatility, local correlation, hybrid local volatility with stochastic rates, and address their exact, nonparametric calibration. This calibration process requires solving a nonlinear partial integro-differential equation. A modified alternating direction implicit algorithm is used, and its theoretical and numerical analysis is performed.
    Date: 2017
  6. By: Victor Chernozhukov (Institute for Fiscal Studies and MIT); Mert Demirer (Institute for Fiscal Studies); Esther Duflo (Institute for Fiscal Studies); Ivan Fernandez-Val (Institute for Fiscal Studies and Boston University)
    Abstract: We propose strategies to estimate and make inference on key features of heterogeneous effects in randomized experiments. These key features include best linear predictors of the effects using machine learning proxies, average effects sorted by impact groups, and average characteristics of most and least impacted units. The approach is valid in high dimensional settings, where the effects are proxied by machine learning methods. We post-process these proxies into the estimates of the key features. Our approach is generic, it can be used in conjunction with penalized methods, deep and shallow neural networks, canonical and new random forests, boosted trees, and ensemble methods. Our approach is agnostic and does not make unrealistic or hard-to-check assumptions; we don’t require conditions for consistency of the ML methods. Estimation and inference relies on repeated data splitting to avoid overfitting and achieve validity. For inference, we take medians of p-values and medians of confidence intervals, resulting from many different data splits, and then adjust their nominal level to guarantee uniform validity. This variational inference method is shown to be uniformly valid and quantifies the uncertainty coming from both parameter estimation and data splitting. The inference method could be of substantial independent interest in many machine learning applications. An empirical application to the impact of micro-credit on economic development illustrates the use of the approach in randomized experiments. An additional application to the impact of the gender discrimination on wages illustrates the potential use of the approach in observational studies, where machine learning methods can be used to condition flexibly on very high-dimensional controls.
    Keywords: Agnostic Inference, Machine Learning, Confidence Intervals, Causal Effects, Variational P-values and Confidence Intervals, Uniformly Valid Inference, Quantification of Uncertainty, Sample Splitting, Multiple Splitting, Assumption-Freeness
    Date: 2017–12–30
  7. By: Hess Chung; Cynthia L. Doniger; Cristina Fuentes-Albero; Bernd Schlusche; Wei Zheng
    Abstract: In this note, we describe a method for calculating simulation results and demonstrate the benefits of the integrated model by analyzing a policy that entails an endogenous balance sheet response.
    Date: 2018–07–20
  8. By: Walter, Timo
    Abstract: This paper deals with the trade and welfare effects of a potential bilateral trade agreement between the US and Japan. A possible agreement is currently being discussed between Washington and Tokyo, although, there is also the alternative for the US government joining Trans-Pacific Partnership (TPP). Based on the theoretical model of Caliendo and Parro (2015) I analyse the welfare gains of such a bilateral free trade agreement (FTA) in the style of Aichele et al. (2014). In particular, I simulate three scenarios with different levels of integration: The reduction of tariffs only, the scenario of a shallow FTA, and a deep FTA. In addition, the paper compares the trade and welfare changes of a deep FTA to the welfare effects of TPP. The findings are that Japan has the highest welfare gains with a FTA (0.085%), whilst the United States benefits the most from TPP with a welfare gain of 0.05%.
    Keywords: Trade agreements,Gravity model,Counterfactual equilibrium,Intermediate goods,Input-output linkages,Japan,United States
    JEL: F13 F14 F17
    Date: 2018
  9. By: Tom Auld (Institute for Fiscal Studies); Oliver Linton (Institute for Fiscal Studies and University of Cambridge)
    Abstract: We study the behaviour of the Betfair betting market and the sterling/dollar exchange rate (futures price) during 24 June 2016, the night of the EU referendum. We investigate how the two markets responded to the announcement of the voting results. We employ a Bayesian updating methodology to update prior opinion about the likelihood of the final outcome of the vote. We then relate the voting model to the real time evolution of the market determined prices. We find that although both markets appear to be inefficient in absorbing the new information contained in vote outcomes, the betting market is apparently less inefficient than the FX market. The different rates of convergence to fundamental value between the two markets leads to highly profitable arbitrage opportunities.
    Keywords: EU Referendum, Prediction Markets, Machine Learning, Efficient Markets Hypothesis, Pairs Trading, Cointegration, Bayesian Methods, Exchange Rates
    Date: 2018–01–10
  10. By: Elena Deryugina (Bank of Russia, Russian Federation); Alexey Ponomarenko (Bank of Russia, Russian Federation); Anna Rozhkova (Bank of Russia, Russian Federation)
    Abstract: We evaluate the reliability of credit gap measures estimated over time samples of different lengths. We augment our empirical analysis (which turned out to be somewhat inconclusive) with Monte Carlo experiments. For this purpose we build an agent-based model that realistically reproduces credit cycles and use it to generate the artificial data set. We found that 12-15 years of available data is sufficient for the estimation of reliable credit gaps (i.e. the reliability of credit gap estimates will not improve substantially as more data are added to the sample).
    Keywords: credit gap, credit cycle, countercyclical capital buffer, agent-based models
    JEL: C63 E37 E44 E51
    Date: 2018–07
  11. By: Lijian Wei (Business School, Sun Yat-Sen University); Xiong Xiong (College of Management and Economics, Tianjin University); Wei Zhang (College of Management and Economics, Tianjin University); Xue-Zhong He (Finance Discipline Group, University of Technology Sydney); Yongjie Zhang (College of Management and Economics, Tianjin University)
    Abstract: By introducing a genetic algorithm with a classifier system as a learning mechanism for uninformed traders into a dynamic limit order market with asymmetric information, this paper examines the effect of the learning on traders’ trading behavior, market liquidity and efficiency. We show that the learning is effective and valuable with respect to information acquisition, forecasting, buy–sell order choice accuracies, and profit opportunity for uninformed traders. It improves information dissemination efficiency and reduces the information advantage of informed traders and hence the value of the private information. In particular, the learning and information become more valuable with higher volatility, less informed traders, and longer information lag. Furthermore, the learning makes not only uninformed but also informed traders submit more limit orders and hence increases market liquidity supply.
    Keywords: Limit order book; Asymmetric information; Genetic algorithm learning; Classifier system; Order submission
    JEL: G14 C63 D82
    Date: 2017–01–01
  12. By: Victor Chernozhukov (Institute for Fiscal Studies and MIT); Kaspar Wüthrich (Institute for Fiscal Studies); Yinchu Zhu (Institute for Fiscal Studies)
    Abstract: We extend conformal inference to general settings that allow for time series data. Our proposal is developed as a randomization method and accounts for potential serial dependence by including block structures in the permutation scheme. As a result, the proposed method retains the exact, model-free validity when the data are i.i.d. or more generally exchangeable, similar to usual conformal inference methods. When exchangeability fails, as is the case for common time series data, the proposed approach is approximately valid under weak assumptions on the conformity score.
    Keywords: Conformal inference, permutation and randomization, dependent data, groups
    Date: 2018–03–02
  13. By: Alexey Vasilenko (Bank of Russia, Russian Federation;National Research University Higher School of Economics, Laboratory for Macroeconomic Analysis; University of Toronto, Joseph L Rotman School of Management.)
    Abstract: This paper studies whether and how the central bank should prick asset price bubbles, if the effect of interest rate policy on bubbles can significantly vary across periods. For this purpose, I first construct a financial accelerator model with an agent-based financial market that can endogenously generate bubbles and account for their impact on the real sector of the economy. Then, I calculate the effect of different nonlinear interest rate rules for pricking asset price bubbles on social welfare and financial stability. The results demonstrate that pricking asset price bubbles can enhance social welfare and reduce the volatility of output and inflation, especially if asset price bubbles are caused by credit expansion. Pricking bubbles is also desirable when the central bank can additionally implement an effective communication policy to prick bubbles, for example, effective verbal interventions aimed at the expectations of agents in the financial market.
    Keywords: monetary policy, asset price bubble, New Keynesian macroeconomics, agent-based financial market.
    JEL: E44 E52 E58 G01 G02
    Date: 2018–06

This nep-cmp issue is ©2018 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.