Comparing Artificial Neural Network Architectures for Brazilian Stock Market Prediction

Abstract

Prediction of financial time series is a great challenge for statistical models. In general, the stock market times series present high volatility due to its sensitivity to economic and political factors. Furthermore, recently, the covid-19 pandemic has caused a drastic change in the stock exchange times series. In this challenging context, several computational techniques have been proposed to improve the performance of predicting such times series. The main goal of this article is to compare the prediction performance of five neural network architectures in predicting the six most traded stocks of the official Brazilian stock exchange B3 from March 2019 to April 2020. We trained the models to predict the closing price of the next day using as inputs its own previous values. We compared the predictive performance of multiple linear regression, Elman, Jordan, radial basis function, and multilayer perceptron architectures based on the root of the mean square error. We trained all models using the training set while hyper-parameters such as the number of input variables and hidden layers were selected using the testing set. Moreover, we used the trimmed average of 100 bootstrap samples as our prediction. Thus, our approach allows us to measure the uncertainty associate with the predicted values. The results showed that for all times series, considered all architectures, except the radial basis function, the networks tunning provide suitable fit, reasonable predictions, and confidence intervals.

Advanced Predictive Analytics for Comprehensive Risk Assessment in Financial Markets: Strategic Applications and Sector-Wide Implications

“…On the other hand, logistic regression is utilized for binary outcomes, estimating the probability of a categorical event occurring, such as the likelihood of loan defaults or the probability of credit risk. Logistic regression works by applying a logistic function to the linear combination of the input variables, thus transforming the output into a probability value between 0 and 1, making it ideal for classification tasks in financial risk assessment (de Pauli et al, 2020). These models are crucial in various financial applications due to their simplicity, interpretability, and effectiveness.…”

A Buffalo‐based bi‐directional recurrent paradigm for Indian stock market prediction

“…Popular theories suggested that the stock markets required a random walk; in most conventional time series, prediction methods were dependent on stationary trends; therefore, the stock price prediction was inherently tricky 11 . Moreover, the stock price prediction was challenging due to the more significant number of involved variables 12 . Moreover, machine learning (ML) is the most powerful tool that includes various algorithms to develop their performance effectively 13 .…”

“…11 Moreover, the stock price prediction was challenging due to the more significant number of involved variables. 12 Moreover, machine learning (ML) is the most powerful tool that includes various algorithms to develop their performance effectively. 13 In general, ML can obtain detecting patterns and valid information from the dataset.…”

Forecasting Directional Movement of Stock Prices using Deep Learning

“…Deep learning hierarchical models such as convolutional neural network (CNN) [ 13 ], recurrent neural network (RNN) [ 14 , 15 ], long short term memory (LSTM) [ 16 ] and recurrent convolutional neural network (RCNN) [ 17 ] are capable for finding the hidden features through a self learning process. The performance of five neural network architectures such as multi-layer perceptron (MLP) network, elman neural network (ENN), jordan neural network (JNN), radial basis functions neural networks (RBF), and multiple linear regression (MLR) to predict the six most traded stocks of the official Brazilian stock exchange during the Covid-19 period is compared in [ 18 ]. Their analysis concluded that these models provide reasonable predictions and thus can be used as support models for the companies.…”