Forecasting significant stock price changes using neural networks

TL;DR

This study explores the use of neural networks to predict significant stock price changes based on previous data, demonstrating high accuracy and outperforming traditional methods like random forest and RSI.

Contribution

It introduces and evaluates neural network classifiers specifically for predicting significant stock price changes, a less explored area in financial forecasting.

Findings

Neural networks outperform benchmark models in predicting significant stock changes.

High accuracy achieved in forecasting large price movements.

Neural models outperform previous studies focusing on price direction.

Abstract

Stock price prediction is a rich research topic that has attracted interest from various areas of science. The recent success of machine learning in speech and image recognition has prompted researchers to apply these methods to asset price prediction. The majority of literature has been devoted to predicting either the actual asset price or the direction of price movement. In this paper, we study a hitherto little explored question of predicting significant changes in stock price based on previous changes using machine learning algorithms. We are particularly interested in the performance of neural network classifiers in the given context. To this end, we construct and test three neural network models including multi-layer perceptron, convolutional net, and long short term memory net. As benchmark models we use random forest and relative strength index methods. The models are tested using 10-year daily stock price data of four major US public companies. Test results show that predicting significant changes in stock price can be accomplished with a high degree of accuracy. In particular, we obtain substantially better results than similar studies that forecast the direction of price change.