Stock Price Forecasting: Machine Learning Models with K-fold and Repeated Cross Validation Approaches

Abstract

Background: Stock exchange price prediction is one of the most researched topics, attracting interest from both academics and industry. Various algorithms have been developed since the introduction of Artificial Intelligence (AI) and have been used to forecast equities market movement. Despite all these researches, less attention has been paid to the use of cross validation (CV) approaches for better stock price prediction. Objective: The aim of this work is to predict Nigerian stock prices using machine learning models with K-fold and repeated K-fold CVs. Methods: In this work, we consider the prediction performance of machine learning models under two cross validation approaches, namely K-fold and repeated K-fold CVs and when no cross validation technique is used. The models consider here are simple linear regression model, random forest (RF), classification and regression tree (CART), and artificial neural network and the support Vector Machine model. Standard strategic indicators such as root mean square error and mean absolute error are used to evaluate the models. The financial data including real gross domestic product, inflation rate, exchange rate and interest rate are used as the input units in the model. Results: Predicting models with CVs technique exhibit superior performance to models with no CV technique involved. Conclusion: Modelling and forecasting stock exchange prices using RF model with CV are conducive to prediction for stock exchange price in Nigeria. Future research are warranted to consider other machine learning models with CVs approaches.