Stock Portfolio Prediction by Multi-Target Decision Support

Authors

  • Everton Jose Santana State University of Londrina
  • João Augusto Provin Ribeiro da silva State University of Londrina
  • Saulo Martiello Mastelini University of São Paulo
  • Sylvio Barbon Jr State University of Londrina

DOI:

https://doi.org/10.5753/isys.2019.381

Abstract

Investing in the stock market is a complex process due to its high volatility caused by factors as exchange rates, political events, inflation and the market history. To support investor's decisions, the prediction of future stock price and economic metrics is valuable. With the hypothesis that there is a relation among investment performance indicators,  the goal of this paper was exploring multi-target regression (MTR) methods to estimate 6 different indicators and finding out the method that would best suit in an automated prediction tool for decision support regarding predictive performance. The experiments were based on 4 datasets, corresponding to 4 different time periods, composed of 63 combinations of weights of stock-picking concepts each, simulated in the US stock market. We compared traditional machine learning approaches with seven state-of-the-art MTR solutions: Stacked Single Target, Ensemble of Regressor Chains, Deep Structure  for Tracking Asynchronous Regressor Stacking,   Deep  Regressor Stacking, Multi-output Tree Chaining,  Multi-target Augment Stacking  and Multi-output Random Forest (MORF). With the exception of MORF, traditional approaches and the MTR methods were evaluated with Extreme Gradient Boosting, Random Forest and Support Vector Machine regressors. By means of extensive experimental evaluation, our results showed that the most recent MTR solutions can achieve suitable predictive performance, improving all the scenarios (14.70% in the best one, considering all target variables and periods). In this sense, MTR is a proper strategy for building stock market decision support system based on prediction models.

Downloads

Download data is not yet available.

Downloads

Published

2019-04-17

How to Cite

Santana, E. J., da silva, J. A. P. R., Mastelini, S. M., & Barbon Jr, S. (2019). Stock Portfolio Prediction by Multi-Target Decision Support. ISys - Brazilian Journal of Information Systems, 12(1), 05–27. https://doi.org/10.5753/isys.2019.381

Issue

Section

Extended versions of selected articles