nep-cmp New Economics Papers
on Computational Economics
Issue of 2022‒09‒05
seventeen papers chosen by
Stan Miles
Thompson Rivers University

  1. Machine learning using Stata/Python By Giovanni Cerulli
  2. Solving the optimal stopping problem with reinforcement learning: an application in financial option exercise By Leonardo Kanashiro Felizardo; Elia Matsumoto; Emilio Del-Moral-Hernandez
  3. Using Machine Learning to Capture Heterogeneity in Trade Agreements By Baier, Scott; Regmi, Narendra
  4. Estimating Consumer Segments and Choices from Limited Information: The Application of Machine Learning Methods By Qin, Fei; Wu, Steven Y.
  5. Machine Learning Methods for Inflation Forecasting in Brazil: new contenders versus classical models By Wagner Piazza Gaglianone; Gustavo Silva Araujo
  6. Quantum Finance: a tutorial on quantum computing applied to the financial market By Askery Canabarro Taysa M. Mendon\c{c}a; Ranieri Nery; George Moreno; Anton S. Albino; Gleydson F. de Jesus; Rafael Chaves
  7. Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification By Mostafa Shabani; Dat Thanh Tran; Juho Kanniainen; Alexandros Iosifidis
  8. Application of machine learning models and interpretability techniques to identify the determinants of the price of bitcoin By José Manuel Carbó; Sergio Gorjón
  9. Quantum-inspired variational algorithms for partial differential equations: Application to financial derivative pricing By Tianchen Zhao; Chuhao Sun; Asaf Cohen; James Stokes; Shravan Veerapaneni
  10. Sitting Next to a Dropout - Academic Success of Students with More Educated Peers By Daniel Goller; Andrea Diem; Stefan C. Wolter
  11. ZEW-EviSTA: A microsimulation model of the German tax and transfer system By Buhlmann, Florian; Hebsaker, Michael; Kreuz, Tobias; Schmidhäuser, Jakob; Siegloch, Sebastian; Stichnoth, Holger
  12. Accurate and consistent calculation of the mean and variance in Monte-Carlo simulations By Jherek Healy
  13. Quantum Quantitative Trading: High-Frequency Statistical Arbitrage Algorithm By Xi-Ning Zhuang; Zhao-Yun Chen; Yu-Chun Wu; Guo-Ping Guo
  14. Multi-horizon Forecasts of Agricultural Commodity Prices using Deep Learning By Bora, Siddhartha S.; Katchova, Ani
  15. Long Story Short: Omitted Variable Bias in Causal Machine Learning By Victor Chernozhukov; Carlos Cinelli; Whitney Newey; Amit Sharma; Vasilis Syrgkanis
  16. Artificial Intelligence : up to here ... and on again By Aarts, Emile
  17. StockBot: Using LSTMs to Predict Stock Prices By Shaswat Mohanty; Anirudh Vijay; Nandagopan Gopakumar

  1. By: Giovanni Cerulli (IRcRES, Rome)
    Abstract: Two related Stata modules, r_ml_stata and c_ml_stata, are presented for
    Date: 2022–07–03
  2. By: Leonardo Kanashiro Felizardo; Elia Matsumoto; Emilio Del-Moral-Hernandez
    Abstract: The optimal stopping problem is a category of decision problems with a specific constrained configuration. It is relevant to various real-world applications such as finance and management. To solve the optimal stopping problem, state-of-the-art algorithms in dynamic programming, such as the least-squares Monte Carlo (LSMC), are employed. This type of algorithm relies on path simulations using only the last price of the underlying asset as a state representation. Also, the LSMC was thinking for option valuation where risk-neutral probabilities can be employed to account for uncertainty. However, the general optimal stopping problem goals may not fit the requirements of the LSMC showing auto-correlated prices. We employ a data-driven method that uses Monte Carlo simulation to train and test artificial neural networks (ANN) to solve the optimal stopping problem. Using ANN to solve decision problems is not entirely new. We propose a different architecture that uses convolutional neural networks (CNN) to deal with the dimensionality problem that arises when we transform the whole history of prices into a Markovian state. We present experiments that indicate that our proposed architecture improves results over the previous implementations under specific simulated time series function sets. Lastly, we employ our proposed method to compare the optimal exercise of the financial options problem with the LSMC algorithm. Our experiments show that our method can capture more accurate exercise opportunities when compared to the LSMC. We have outstandingly higher (above 974\% improvement) expected payoff from these exercise policies under the many Monte Carlo simulations that used the real-world return database on the out-of-sample (test) data.
    Date: 2022–07
  3. By: Baier, Scott; Regmi, Narendra (Mercury Publication)
    Abstract: Abstract not available.
    Date: 2021–03–25
  4. By: Qin, Fei; Wu, Steven Y.
    Keywords: Marketing, Research Methods/Statistical Methods, Agribusiness
    Date: 2022–08
  5. By: Wagner Piazza Gaglianone; Gustavo Silva Araujo
    Abstract: In this paper, we explore machine learning (ML) methods to improve inflation forecasting in Brazil. An extensive out-of-sample forecasting exercise is designed with multiple horizons, a large database of 501 series, and 50 forecasting methods, including new machine learning techniques proposed here, traditional econometric models and forecast combination methods. We also provide tools to identify the key variables to predict inflation, thus helping to open the ML black box. Despite the evidence of no universal best model, the results indicate machine learning methods can, in numerous cases, outperform traditional econometric models in terms of mean-squared error. Moreover, the results indicate the existence of nonlinearities in the inflation dynamics, which are relevant to forecast inflation. The set of top forecasts often includes forecast combinations, tree-based methods (such as random forest and xgboost), breakeven inflation, and survey-based expectations. Altogether, these findings offer a valuable contribution to macroeconomic forecasting, especially, focused on Brazilian inflation.
    Date: 2022–07
  6. By: Askery Canabarro Taysa M. Mendon\c{c}a; Ranieri Nery; George Moreno; Anton S. Albino; Gleydson F. de Jesus; Rafael Chaves
    Abstract: Previously only considered a frontier area of Physics, nowadays quantum computing is one of the fastest growing research field, precisely because of its technological applications in optimization problems, machine learning, information security and simulations. The goal of this article is to introduce the fundamentals of quantum computing, focusing on a promising quantum algorithm and its application to a financial market problem. More specifically, we discuss the portfolio optimization problem using the \textit{Quantum Approximate Optimization Algorithm} (QAOA). We not only describe the main concepts involved but also consider simple practical examples, involving financial assets available on the Brazilian stock exchange, with codes, both classic and quantum, freely available as a Jupyter Notebook. We also analyze in details the quality of the combinatorial portfolio optimization solutions through QAOA using SENAI/CIMATEC's ATOS QLM quantum simulator.
    Date: 2022–08
  7. By: Mostafa Shabani; Dat Thanh Tran; Juho Kanniainen; Alexandros Iosifidis
    Abstract: Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly applied to another market or security due to differences inherent in the market conditions. In addition, as the market evolves through time, it is necessary to update the existing models or train new ones when new data is made available. This scenario, which is inherent in most financial forecasting applications, naturally raises the following research question: How to efficiently adapt a pre-trained model to a new set of data while retaining performance on the old data, especially when the old data is not accessible? In this paper, we propose a method to efficiently retain the knowledge available in a neural network pre-trained on a set of securities and adapt it to achieve high performance in new ones. In our method, the prior knowledge encoded in a pre-trained neural network is maintained by keeping existing connections fixed, and this knowledge is adjusted for the new securities by a set of augmented connections, which are optimized using the new data. The auxiliary connections are constrained to be of low rank. This not only allows us to rapidly optimize for the new task but also reduces the storage and run-time complexity during the deployment phase. The efficiency of our approach is empirically validated in the stock mid-price movement prediction problem using a large-scale limit order book dataset. Experimental results show that our approach enhances prediction performance as well as reduces the overall number of network parameters.
    Date: 2022–07
  8. By: José Manuel Carbó (Banco de España); Sergio Gorjón (Banco de España)
    Abstract: So-called cryptocurrencies are becoming more popular by the day, with a total market capitalization that exceeded $3 trillion at its peak in 2021. Bitcoin has emerged as the most popular among them, with a total valuation that reached an all-time high of $68,000 in November 2021. However, its price has historically been subject to large and abrupt fluctuations, as the sudden drop in the months that followed once again proved. Since bitcoin looks all set to continue growing while largely concentrating its activity in unregulated environments, concerns have been raised among authorities all over the world about its potential impact on financial stability, monetary policy, and the integrity of the financial system. As a result, building a sound and proper regulatory and supervisory framework to address these challenges hinges upon achieving a better understanding of both the critical underlying factors that influence the formation of bitcoin prices and the stability of such factors over time. In this article we analyse which variables determine the price at which bitcoin is traded on the most relevant exchanges. To this end, we use a flexible machine learning model, specifically a Long Short Term Memory (LSTM) neural network, to establish the price of bitcoin as a function of a number of economic, technological and investor attention variables. Our LSTM model replicates reasonably well the behaviour of the price of bitcoin over different periods of time. We then use an interpretability technique known as SHAP to understand which features most influence the LSTM outcome. We conclude that the importance of the different variables in bitcoin price formation changes substantially over the period analysed. Moreover, we find that not only does their influence vary, but also that new explanatory factors often seem to appear over time that, at least for the most part, were initially unknown.
    Keywords: Bitcoin, machine learning, LSTM, interpretability techniques
    JEL: C40 C45 G12 G15
    Date: 2022–04
  9. By: Tianchen Zhao; Chuhao Sun; Asaf Cohen; James Stokes; Shravan Veerapaneni
    Abstract: Variational quantum Monte Carlo (VMC) combined with neural-network quantum states offers a novel angle of attack on the curse-of-dimensionality encountered in a particular class of partial differential equations (PDEs); namely, the real- and imaginary time-dependent Schr\"odinger equation. In this paper, we present a simple generalization of VMC applicable to arbitrary time-dependent PDEs, showcasing the technique in the multi-asset Black-Scholes PDE for pricing European options contingent on many correlated underlying assets.
    Date: 2022–07
  10. By: Daniel Goller; Andrea Diem; Stefan C. Wolter
    Abstract: We investigate the impact of the presence of university dropouts on the academic success of first-time students. Our identification strategy relies on quasi-random variation in the proportion of returning dropouts. The estimated average zero effect of dropouts on first-time students’ success masks treatment heterogeneity and non-linearities. First, we find negative effects on the academic success of their new peers from dropouts re-enrolling in the same subject and, conversely, positive effects of dropouts changing subjects. Second, using causal machine learning methods, we find that the effects vary nonlinearly with different treatment intensities and prevailing treatment levels.
    Keywords: university dropouts, peer effects, better prepared students, causal machine learning
    JEL: A23 C14 I23
    Date: 2022
  11. By: Buhlmann, Florian; Hebsaker, Michael; Kreuz, Tobias; Schmidhäuser, Jakob; Siegloch, Sebastian; Stichnoth, Holger
    Abstract: This article describes ZEW-EviSTA®, the microsimulation model developed and used at ZEW - Centre for European Economic Research in Mannheim. The model simulates the German tax and transfer system using household micro level data. By estimating fiscal effects, labor market outcomes as well as distributional impacts the model allows for a comprehensive ex ante analysis of reform proposals. Heterogeneity analyses targeting specific subgroups of the population are feasible, too. The present article describes which data sources are used for the simulation, how key features of the German tax and transfer system are implemented, which simulation methods are employed to analyze policy changes and how the model is validated against official statistics. Moreover, by providing examples of the outputs which ZEW-EviSTA generates the paper gives an idea of the questions that can be answered using the model.
    Keywords: microsimulation,tax system,tax policy,labour market,labour supply,labourdemand,Germany,policy analysis
    JEL: D58 H20 J22 J23
    Date: 2022
  12. By: Jherek Healy
    Abstract: In parallelized Monte-Carlo simulations, the order of summation is not always the same. When the mean is calculated in running fashion, this may create an artificial randomness in results which ought to be reproducible. This note takes a look at the problem and proposes to combine the running mean and variance algorithm with an accurate and robust summing algorithm in order to increase the accuracy and robustness of the Monte-Carlo estimates.
    Date: 2022–06
  13. By: Xi-Ning Zhuang; Zhao-Yun Chen; Yu-Chun Wu; Guo-Ping Guo
    Abstract: Quantitative trading is an integral part of financial markets with high calculation speed requirements, while no quantum algorithms have been introduced into this field yet. We propose quantum algorithms for high-frequency statistical arbitrage trading in this work by utilizing variable time condition number estimation and quantum linear regression.The algorithm complexity has been reduced from the classical benchmark O(N^2d) to O(sqrt(d)(kappa)^2(log(1/epsilon))^2 )). It shows quantum advantage, where N is the length of trading data, and d is the number of stocks, kappa is the condition number and epsilon is the desired precision. Moreover, two tool algorithms for condition number estimation and cointegration test are developed.
    Date: 2021–04
  14. By: Bora, Siddhartha S.; Katchova, Ani
    Keywords: Marketing, Agricultural Finance, Agricultural and Food Policy
    Date: 2022–08
  15. By: Victor Chernozhukov; Carlos Cinelli; Whitney Newey; Amit Sharma; Vasilis Syrgkanis
    Abstract: We derive general, yet simple, sharp bounds on the size of the omitted variable bias for a broad class of causal parameters that can be identified as linear functionals of the conditional expectation function of the outcome. Such functionals encompass many of the traditional targets of investigation in causal inference studies, such as, for example, (weighted) average of potential outcomes, average treatment effects (including subgroup effects, such as the effect on the treated), (weighted) average derivatives, and policy effects from shifts in covariate distribution -- all for general, nonparametric causal models. Our construction relies on the Riesz-Frechet representation of the target functional. Specifically, we show how the bound on the bias depends only on the additional variation that the latent variables create both in the outcome and in the Riesz representer for the parameter of interest. Moreover, in many important cases (e.g, average treatment effects and avearage derivatives) the bound is shown to depend on easily interpretable quantities that measure the explanatory power of the omitted variables. Therefore, simple plausibility judgments on the maximum explanatory power of omitted variables (in explaining treatment and outcome variation) are sufficient to place overall bounds on the size of the bias. Furthermore, we use debiased machine learning to provide flexible and efficient statistical inference on learnable components of the bounds. Finally, empirical examples demonstrate the usefulness of the approach.
    JEL: C14 C21 C31
    Date: 2022–07
  16. By: Aarts, Emile (Tilburg University, School of Economics and Management)
    Date: 2022
  17. By: Shaswat Mohanty; Anirudh Vijay; Nandagopan Gopakumar
    Abstract: The evaluation of the financial markets to predict their behaviour have been attempted using a number of approaches, to make smart and profitable investment decisions. Owing to the highly non-linear trends and inter-dependencies, it is often difficult to develop a statistical approach that elucidates the market behaviour entirely. To this end, we present a long-short term memory (LSTM) based model that leverages the sequential structure of the time-series data to provide an accurate market forecast. We then develop a decision making StockBot that buys/sells stocks at the end of the day with the goal of maximizing profits. We successfully demonstrate an accurate prediction model, as a result of which our StockBot can outpace the market and can strategize for gains that are ~15 times higher than the most aggressive ETFs in the market.
    Date: 2022–07

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.