Stock Portfolio Prediction by Multi-Target Decision Support

Silva, João Augusto Provin Ribeiro da; Santana, Everton José; Mastelini, Saulo Martiello; Barbon, Sylvio

doi:10.1145/3229345.3229382

Cited by 2 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the MTR methods, differently from what found out in [Silva et al 2018], ERC presented the smallest errors in 5 out 12 times, followed by MTAS (the best 4 times), DSTARS (the best 2 times) and SST (the best once). Though ERC presented the smallest aRRMSE most of times, only in the second period it was the smallest error for the dataset.…”

Section: Resultscontrasting

confidence: 66%

“…In this sense, a regression model for a performance indicator could use information of other outcomes to yield better predictions and compose a more reliable decision support tool. This paper is an extension of the work of [Silva et al 2018], whose goal was proposing a kernel to decision support tool based on MTR to predict performance indicators of stock market, showing that this approach can generate an accurate model due to the inter-target influence in this model. This work aims at obtaining the method that would result in the best prediction performance for the given problem.…”

mentioning

confidence: 96%

See 1 more Smart Citation

Stock Portfolio Prediction by Multi-Target Decision Support

Santana

Silva

Mastelini

et al. 2019

iSys

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Resultscontrasting

confidence: 66%

mentioning

confidence: 96%