Financial time series prediction using exogenous series and combined neural networks

Abstract

Abstract-Time series forecasting have been a subject of interest in several different areas of research such as: meteorology, demography, health, computer and finance. Since it can be applied to various practical problems in real world, techniques to predict time series have been a topic of increasing research activities, especially in the financial sector that has a great interest in the forecast of the stock market. In this article, we are interested in the forecast of the time series related to the Brazilian oil company, Petrobras (PETR4). A methodology based on information obtained from exogenous series was used in combination with a neural network to predict the PETR4 stock series. Exogenous series were selected by analyzing the correlation between the series with the Petrobras stocks series. In this way, the prediction was obtained by not just using the previous values of the series but also by using information external to the PETR4 series. The values of the selected series were used as features for a prediction stage based on combined neural networks. To evaluate the performance of the system classical measurements were used, however we also introduce a new performance index called Sum of the Losses and Gains (SLG).

Portfolio Optimization Based on the LSTM Forecasting Model

“…The time series model is introduced to improve portfolio performance. For instance, Soeryana, Fadhlina, and Rusyaman took a time series approach to optimize the Mean-Variance portfolio [1]; Neto, Calvalcanti and Ren used data extracted from exogenous series to do a time series forecast [2]; Zhou, Yang and Yu achieved portfolio optimization under the fuzzy time series method [3]. In recent years, there has been a surge in the utilization of machine learning and deep learning models for the purpose of portfolio development, such as random forest (RF), support vector regression (SVR), and long short-term memory (LSTM).…”

A multivariate LSTM-based deep learning model for stock market prediction

“…The technical analysis use historical price movement to predict price pattern while the fundamental analysis use the financial information about the company such as inventory or revenue growth relates [2]. Time series method involves using historical performance for prediction with current observations dependent on past observation in time [3]. However, it sometimes fails to accurately forecast the financial market because of national and global economic trends [4].…”