nep-cmp New Economics Papers
on Computational Economics
Issue of 2022‒01‒10
twenty papers chosen by
Stan Miles
Thompson Rivers University

  1. Generative Adversarial Network (GAN) and Enhanced Root Mean Square Error (ERMSE): Deep Learning for Stock Price Movement Prediction By Ashish Kumar; Abeer Alsadoon; P. W. C. Prasad; Salma Abdullah; Tarik A. Rashid; Duong Thu Hang Pham; Tran Quoc Vinh Nguyen
  2. Expert Aggregation for Financial Forecasting By Bri\`ere Marie; Alasseur Cl\'emence; Joseph Mikael; Carl Remlinger
  3. Recent Advances in Reinforcement Learning in Finance By Ben Hambly; Renyuan Xu; Huining Yang
  4. High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning By Uta Pigorsch; Sebastian Sch\"afer
  5. Development of an Ensemble of Models for Predicting Socio-Economic Indicators of the Russian Federation using IRT-Theory and Bagging Methods By Kitova, Olga; Savinova, Victoria
  6. Fast Sampling from Time-Integrated Bridges using Deep Learning By Leonardo Perotti; Lech A. Grzelak
  7. Improved Method of Stock Trading under Reinforcement Learning Based on DRQN and Sentiment Indicators ARBR By Peng Zhou; Jingling Tang
  8. Forecasting Social Unrest: A Machine Learning Approach By Sandile Hlatshwayo; Chris Redl
  9. Using Polls to Forecast Popular Vote Share for US Presidential Elections 2016 and 2020: An Optimal Forecast Combination Based on Ensemble Empirical Model By Easaw, Joshy; Fang, Yongmei; Heravi, Saeed
  10. Model-based Recursive Partitioning to Estimate Unfair Health Inequalities in the United Kingdom Household Longitudinal Study By Paolo Brunori; Apostolos Davillas; Andrew Jones; Giovanna Scarchilli
  11. Forex Trading Volatility Prediction using NeuralNetwork Models By Shujian Liao; Jian Chen; Hao Ni
  12. A Review on Graph Neural Network Methods in Financial Applications By Jianian Wang; Sheng Zhang; Yanghua Xiao; Rui Song
  13. Simple Allocation Rules and Optimal Portfolio Choice Over the Lifecycle By Victor Duarte; Julia Fonseca; Aaron S. Goodman; Jonathan A. Parker
  14. Quantum algorithm for stochastic optimal stopping problems By Jo\~ao F. Doriguello; Alessandro Luongo; Jinge Bao; Patrick Rebentrost; Miklos Santha
  15. AI-enabled Automation, Trade, and the Future of Engineering Services By Klügl, Franziska; Kyvik Nordås, Hildegunn
  16. Structural Sieves By Konrad Menzel
  17. Safe Havens, Machine Learning, and the Sources of Geopolitical Risk: A Forecasting Analysis Using Over a Century of Data By Rangan Gupta; Sayar Karmakar; Christian Pierdzioch
  18. Reinforcement learning for options on target volatility funds By Roberto Daluiso; Emanuele Nastasi; Andrea Pallavicini; Stefano Polo
  19. Intuitive Mathematical Economics Series. General Equilibrium Models and the Gradient Field Method By Tomás Marinozzi; Leandro Nallar; Sergio Pernice
  20. Fair learning with bagging By Jean-David Fermanian; Dominique Guégan

  1. By: Ashish Kumar; Abeer Alsadoon; P. W. C. Prasad; Salma Abdullah; Tarik A. Rashid; Duong Thu Hang Pham; Tran Quoc Vinh Nguyen
    Abstract: The prediction of stock price movement direction is significant in financial circles and academic. Stock price contains complex, incomplete, and fuzzy information which makes it an extremely difficult task to predict its development trend. Predicting and analysing financial data is a nonlinear, time-dependent problem. With rapid development in machine learning and deep learning, this task can be performed more effectively by a purposely designed network. This paper aims to improve prediction accuracy and minimizing forecasting error loss through deep learning architecture by using Generative Adversarial Networks. It was proposed a generic model consisting of Phase-space Reconstruction (PSR) method for reconstructing price series and Generative Adversarial Network (GAN) which is a combination of two neural networks which are Long Short-Term Memory (LSTM) as Generative model and Convolutional Neural Network (CNN) as Discriminative model for adversarial training to forecast the stock market. LSTM will generate new instances based on historical basic indicators information and then CNN will estimate whether the data is predicted by LSTM or is real. It was found that the Generative Adversarial Network (GAN) has performed well on the enhanced root mean square error to LSTM, as it was 4.35% more accurate in predicting the direction and reduced processing time and RMSE by 78 secs and 0.029, respectively. This study provides a better result in the accuracy of the stock index. It seems that the proposed system concentrates on minimizing the root mean square error and processing time and improving the direction prediction accuracy, and provides a better result in the accuracy of the stock index.
    Date: 2021–11
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2112.03946&r=
  2. By: Bri\`ere Marie; Alasseur Cl\'emence; Joseph Mikael; Carl Remlinger
    Abstract: Machine learning algorithms dedicated to financial time series forecasting have gained a lot of interest over the last few years. One difficulty lies in the choice between several algorithms, as their estimation accuracy may be unstable through time. In this paper, we propose to apply an online aggregation-based forecasting model combining several machine learning techniques to build a portfolio which dynamically adapts itself to market conditions. We apply this aggregation technique to the construction of a long-short-portfolio of individual stocks ranked on their financial characteristics and we demonstrate how aggregation outperforms single algorithms both in terms of performances and of stability.
    Date: 2021–11
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2111.15365&r=
  3. By: Ben Hambly; Renyuan Xu; Huining Yang
    Abstract: The rapid changes in the finance industry due to the increasing amount of data have revolutionized the techniques on data processing and data analysis and brought new theoretical and computational challenges. In contrast to classical stochastic control theory and other analytical approaches for solving financial decision-making problems that heavily reply on model assumptions, new developments from reinforcement learning (RL) are able to make full use of the large amount of financial data with fewer model assumptions and to improve decisions in complex financial environments. This survey paper aims to review the recent developments and use of RL approaches in finance. We give an introduction to Markov decision processes, which is the setting for many of the commonly used RL approaches. Various algorithms are then introduced with a focus on value and policy based methods that do not require any model assumptions. Connections are made with neural networks to extend the framework to encompass deep RL algorithms. Our survey concludes by discussing the application of these RL algorithms in a variety of decision-making problems in finance, including optimal execution, portfolio optimization, option pricing and hedging, market making, smart order routing, and robo-advising.
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2112.04553&r=
  4. By: Uta Pigorsch; Sebastian Sch\"afer
    Abstract: This paper proposes a Deep Reinforcement Learning algorithm for financial portfolio trading based on Deep Q-learning. The algorithm is capable of trading high-dimensional portfolios from cross-sectional datasets of any size which may include data gaps and non-unique history lengths in the assets. We sequentially set up environments by sampling one asset for each environment while rewarding investments with the resulting asset's return and cash reservation with the average return of the set of assets. This enforces the agent to strategically assign capital to assets that it predicts to perform above-average. We apply our methodology in an out-of-sample analysis to 48 US stock portfolio setups, varying in the number of stocks from ten up to 500 stocks, in the selection criteria and in the level of transaction costs. The algorithm on average outperforms all considered passive and active benchmark investment strategies by a large margin using only one hyperparameter setup for all portfolios.
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2112.04755&r=
  5. By: Kitova, Olga; Savinova, Victoria
    Abstract: This article describes the application of the bagging method to build a forecast model for the socio-economic indicators of the Russian Federation. This task is one of the priorities within the framework of the Federal Project "Strategic Planning", which implies the creation of a unified decision support system capable of predicting socio-economic indicators. This paper considers the relevance of the development of forecasting models, examines and analyzes the work of researchers on this topic. The authors carried out computational experiments for 40 indicators of the socio-economic sphere of the Russian Federation. For each indicator, a linear multiple regression equation was constructed. For the constructed equations, verification was carried out and indicators with the worst accuracy and quality of the forecast were selected. For these indicators, neural network modeling was carried out. Multilayer perceptrons were chosen as the architecture of neural networks. Next, an analysis of the accuracy and quality of neural network models was carried out. Indicators that could not be predicted with a sufficient level of accuracy were selected for the bagging procedure. Bagging was used for weighted averaging of prediction results for neural networks of various configurations. Item Response Theory (IRT) elements were used to determine the weights of the models.
    Keywords: Socio-economic Indicators of the Russian Federation, Forecasting, Bagging, Multiple Linear Regression, Neural Networks, Item Response Theory
    JEL: C45
    Date: 2021–11–25
    URL: http://d.repec.org/n?u=RePEc:pra:mprapa:110824&r=
  6. By: Leonardo Perotti; Lech A. Grzelak
    Abstract: We propose a methodology to sample from time-integrated stochastic bridges, namely random variables defined as $\int_{t_1}^{t_2} f(Y(t))dt$ conditioned on $Y(t_1)\!=\!a$ and $Y(t_2)\!=\!b$, with $a,b\in R$. The Stochastic Collocation Monte Carlo sampler and the Seven-League scheme are applied for this purpose. Notably, the distribution of the time-integrated bridge is approximated utilizing a polynomial chaos expansion built on a suitable set of stochastic collocation points. Furthermore, artificial neural networks are employed to learn the collocation points. The result is a robust, data-driven procedure for the Monte Carlo sampling from conditional time-integrated processes, which guarantees high accuracy and generates thousands of samples in milliseconds. Applications, with a focus on finance, are presented here as well.
    Date: 2021–11
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2111.13901&r=
  7. By: Peng Zhou; Jingling Tang
    Abstract: With the application of artificial intelligence in the financial field, quantitative trading is considered to be profitable. Based on this, this paper proposes an improved deep recurrent DRQN-ARBR model because the existing quantitative trading model ignores the impact of irrational investor behavior on the market, making the application effect poor in an environment where the stock market in China is non-efficiency. By changing the fully connected layer in the original model to the LSTM layer and using the emotion indicator ARBR to construct a trading strategy, this model solves the problems of the traditional DQN model with limited memory for empirical data storage and the impact of observable Markov properties on performance. At the same time, this paper also improved the shortcomings of the original model with fewer stock states and chose more technical indicators as the input values of the model. The experimental results show that the DRQN-ARBR algorithm proposed in this paper can significantly improve the performance of reinforcement learning in stock trading.
    Date: 2021–11
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2111.15356&r=
  8. By: Sandile Hlatshwayo; Chris Redl
    Abstract: We produce a social unrest risk index for 125 countries covering a period of 1996 to 2020. The risk of social unrest is based on the probability of unrest in the following year derived from a machine learning model drawing on over 340 indicators covering a wide range of macro-financial, socioeconomic, development and political variables. The prediction model correctly forecasts unrest in the following year approximately two-thirds of the time. Shapley values indicate that the key drivers of the predictions include high levels of unrest, food price inflation and mobile phone penetration, which accord with previous findings in the literature.
    Keywords: Social unrest, machine learning.
    Date: 2021–11–05
    URL: http://d.repec.org/n?u=RePEc:imf:imfwpa:2021/263&r=
  9. By: Easaw, Joshy (Cardiff Business School); Fang, Yongmei (College of Mathematics and Informatics, South China Agricultural University, China); Heravi, Saeed (Cardiff Business School)
    Abstract: This study introduces the Ensemble Empirical Mode Decomposition (EEMD) technique to forecasting popular vote share. The technique is useful when using polling data, which is pertinent when none of the main candidates is the incumbent. Our main interest in this study is the short- and long-term forecasting and, thus, we consider from the short forecast horizon of 1-day to three months ahead. The EEMD technique is used to decompose the election data for the two most recent US presidential elections; 2016 and 2020 US. Three models, Support Vector Machine (SVM), Neural Network (NN) and ARIMA models are then used to predict the decomposition components. The final hybrid model is then constructed by comparing the prediction performance of the decomposition components. The predicting performance of the combination model are compared with the benchmark individual models, SVM, NN, and ARIMA. In addition, this compared to the single prediction market IOWA Electronic Markets. The results indicated that the prediction performance of EEMD combined model is better than that of individual models.
    Keywords: Forecasting Popular Votes Shares; Electoral Poll; Forecast combination, Hybrid model; Support Vector Machine
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:cdf:wpaper:2021/34&r=
  10. By: Paolo Brunori (London School of Economics , International Inequality Institute & University of Bari); Apostolos Davillas (University of East Anglia, Norwich Medical School); Andrew Jones (University of York); Giovanna Scarchilli (University of Trento & University of Modena and Reggio Emilia)
    Abstract: We measure unfair health inequality in the UK using a novel data-driven empirical approach. We explain health variability as the result of circumstances beyond individual control and health-related behaviours. We do this using model-based recursive partitioning, a supervised machine learning algorithm. Unlike usual tree-based algorithms, model-based recursive partitioning does identify social groups with different expected levels of health but also unveils the heterogeneity of the relationship linking behaviors and health outcomes across groups. The empirical application is conducted using the UK Household Longitudinal Study. We show that unfair inequality is a substantial fraction of the total explained health variability. This finding holds no matter which exact definition of fairness is adopted: using both the fairness gap and direct unfairness measures, each evaluated at different reference values for circumstances or effort.
    Keywords: Health inequality, machine learning, UK Household Longitudinal Study
    JEL: I14 D63
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:inq:inqwps:ecineq2021-596&r=
  11. By: Shujian Liao; Jian Chen; Hao Ni
    Abstract: In this paper, we investigate the problem of predicting the future volatility of Forex currency pairs using the deep learning techniques. We show step-by-step how to construct the deep-learning network by the guidance of the empirical patterns of the intra-day volatility. The numerical results show that the multiscale Long Short-Term Memory (LSTM) model with the input of multi-currency pairs consistently achieves the state-of-the-art accuracy compared with both the conventional baselines, i.e. autoregressive and GARCH model, and the other deep learning models.
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2112.01166&r=
  12. By: Jianian Wang; Sheng Zhang; Yanghua Xiao; Rui Song
    Abstract: Keeping the individual features and the complicated relations, graph data are widely utilized and investigated. Being able to capture the structural information by updating and aggregating nodes' representations, graph neural network (GNN) models are gaining popularity. In the financial context, the graph is constructed based on real-world data, which leads to complex graph structure and thus requires sophisticated methodology. In this work, we provide a comprehensive review of GNN models in recent financial context. We first categorize the commonly-used financial graphs and summarize the feature processing step for each node. Then we summarize the GNN methodology for each graph type, application in each area, and propose some potential research areas.
    Date: 2021–11
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2111.15367&r=
  13. By: Victor Duarte; Julia Fonseca; Aaron S. Goodman; Jonathan A. Parker
    Abstract: We develop a machine-learning solution algorithm to solve for optimal portfolio choice in a detailed and quantitatively-accurate lifecycle model that includes many features of reality modelled only separately in previous work. We use the quantitative model to evaluate the consumption-equivalent welfare losses from using simple rules for portfolio allocation across stocks, bonds, and liquid accounts instead of the optimal portfolio choices. We find that the consumption-equivalent losses from using an age-dependent rule as embedded in current target-date/lifecycle funds (TDFs) are substantial, around 2 to 3 percent of consumption, despite the fact that TDF rules mimic average optimal behavior by age closely until shortly before retirement. Our model recommends higher average equity shares in the second half of life than the portfolio of the typical TDF, so that the typical TDF portfolio does not improve on investing an age-independent 2/3 share in equity. Finally, optimal equity shares have substantial heterogeneity, particularly by wealth level, state of the business cycle, and dividend-price ratio, implying substantial gains to further customization of advice or TDFs in these dimensions.
    JEL: C61 D15 E21 G11 G51
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:nbr:nberwo:29559&r=
  14. By: Jo\~ao F. Doriguello; Alessandro Luongo; Jinge Bao; Patrick Rebentrost; Miklos Santha
    Abstract: The famous least squares Monte Carlo (LSM) algorithm combines linear least square regression with Monte Carlo simulation to approximately solve problems in stochastic optimal stopping theory. In this work, we propose a quantum LSM based on quantum access to a stochastic process, on quantum circuits for computing the optimal stopping times, and on quantum Monte Carlo techniques. For this algorithm we elucidate the intricate interplay of function approximation and quantum Monte Carlo algorithms. Our algorithm achieves a nearly quadratic speedup in the runtime compared to the LSM algorithm under some mild assumptions. Specifically, our quantum algorithm can be applied to American option pricing and we analyze a case study for the common situation of Brownian motion and geometric Brownian motion processes.
    Date: 2021–11
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2111.15332&r=
  15. By: Klügl, Franziska (Örebro University School of Business); Kyvik Nordås, Hildegunn (Örebro University School of Business)
    Abstract: This paper studies the role of trade for the joint uptake of AI-enabled automation in manufacturing and engineering. It develops an agent-based model (ABM) where the agents are heterogeneous manufacturers and engineering firms. The model features two technology-related business models: engineering as a face-to-face consultancy service and engineering as automated software. Switching to the software technology is costly for both manufacturers and engineers, but the cost declines with the number of firms having made the leap due to network effects. The simulations start with a scenario where all firms are in the consultancy business model and trace out the path of software adoption over time. The software adoption rate follows an S-shaped curve for manufacturers and a boom and bust cycle for engineers. Trade affects the cut-off productivity rate at which manufacturers switch technology, the shape of the adoption rate curve, and the incentives for engineers to develop software. In a two-country model with a high and low-wage country, the low wage country adopts software early and import consultancy services from the high-wage country, a pattern similar to China’s trade and AI development.
    Keywords: Technology adoption; Automation; Trade; Agent Based Modelling
    JEL: C63 F16 O33
    Date: 2021–12–23
    URL: http://d.repec.org/n?u=RePEc:hhs:oruesi:2021_016&r=
  16. By: Konrad Menzel
    Abstract: This paper explores the use of deep neural networks for semiparametric estimation of economic models of maximizing behavior in production or discrete choice. We argue that certain deep networks are particularly well suited as a nonparametric sieve to approximate regression functions that result from nonlinear latent variable models of continuous or discrete optimization. Multi-stage models of this type will typically generate rich interaction effects between regressors ("inputs") in the regression function so that there may be no plausible separability restrictions on the "reduced-form" mapping form inputs to outputs to alleviate the curse of dimensionality. Rather, economic shape, sparsity, or separability restrictions either at a global level or intermediate stages are usually stated in terms of the latent variable model. We show that restrictions of this kind are imposed in a more straightforward manner if a sufficiently flexible version of the latent variable model is in fact used to approximate the unknown regression function.
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2112.01377&r=
  17. By: Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Sayar Karmakar (Department of Statistics, University of Florida, 230 Newell Drive, Gainesville, FL, 32601, USA); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany)
    Abstract: We use monthly data covering a century-long sample period (1915-2021) to study whether geopolitical risk helps to forecast subsequent gold returns and gold volatility. We account not only for geopolitical threats and acts, but also for 39 country-specific sources of geopolitical risk. The response of subsequent returns and volatility is heterogeneous across countries and nonlinear. We find that accounting for geopolitical risk at the country level improves forecast accuracy especially when we use random forests to estimate our forecasting models. As an extension, we report empirical evidence on the predictive value of the country-level sources of geopolitical risk for two other candidate safe-haven assets, oil and silver, over the sample periods 1900–2021 and 1915–2021, respectively. Our results have important implications for the portfolio decisions of investors who seek a safe haven in times of heightened geopolitical tensions.
    Keywords: Gold, Geopolitical Risk, Forecasting, Returns, Volatility, Random Forests
    JEL: C22 D80 H56 Q02
    Date: 2022–01
    URL: http://d.repec.org/n?u=RePEc:pre:wpaper:202201&r=
  18. By: Roberto Daluiso; Emanuele Nastasi; Andrea Pallavicini; Stefano Polo
    Abstract: In this work we deal with the funding costs rising from hedging the risky securities underlying a target volatility strategy (TVS), a portfolio of risky assets and a risk-free one dynamically rebalanced in order to keep the realized volatility of the portfolio on a certain level. The uncertainty in the TVS risky portfolio composition along with the difference in hedging costs for each component requires to solve a control problem to evaluate the option prices. We derive an analytical solution of the problem in the Black and Scholes (BS) scenario. Then we use Reinforcement Learning (RL) techniques to determine the fund composition leading to the most conservative price under the local volatility (LV) model, for which an a priori solution is not available. We show how the performances of the RL agents are compatible with those obtained by applying path-wise the BS analytical strategy to the TVS dynamics, which therefore appears competitive also in the LV scenario.
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2112.01841&r=
  19. By: Tomás Marinozzi; Leandro Nallar; Sergio Pernice
    Abstract: General equilibrium models are typically presented with mathematical methods, such as the Edgeworth Box, that do not easily generalize to more than two goods and more than two agents. This is fine as a conceptual introduction, but it may be insufficient in the “Big-Data Machine-Learning Era”, with gigantic databases filled with data of extremely high dimensionality that are already changing the practice, and perhaps even the conceptual basis, of economics and other social sciences. In this paper present what we call the “Gradient Field Method” to solve these problems. It has the advantage of being, 1) as intuitive as the Edgeworth Box, 2) easily generalizes to far more complex situations, and 3) nicely mesh with the data friendly techniques of the new Era. In addition, it provides a unified framework to present both, partial equilibrium, and general equilibrium problems.
    Keywords: microeconomics, general equilibrium, radient, gradient field, machine learning.
    Date: 2021–12
    URL: http://d.repec.org/n?u=RePEc:cem:doctra:820&r=
  20. By: Jean-David Fermanian (Ensae-Crest); Dominique Guégan (Université Paris1 Panthéon-Sorbonne, Centre d'Economie de la Sorbonne, - Ca' Foscari University of Venezia)
    Abstract: The central question of this paper is how to enhance supervised learning algorithms with fairness requirement ensuring that any sensitive input does not "unfairly"' influence the outcome of the learning algorithm. To attain this objective we proceed by three steps. First after introducing several notions of fairness in a uniform approach, we introduce a more general notion through conditional fairness definition which englobes most of the well known fairness definitions. Second we use a ensemble of binary and continuous classifiers to get an optimal solution for a fair predictive outcome using a related-post-processing procedure without any transformation on the data, nor on the training algorithms. Finally we introduce several tests to verify the fairness of the predictions. Some empirics are provided to illustrate our approach
    Keywords: fairness; nonparametric regression; classification; accuracy
    JEL: C10 C38 C53
    Date: 2021–11
    URL: http://d.repec.org/n?u=RePEc:mse:cesdoc:21034&r=

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 http://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. 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.