Application of Machine Learning for KASE Market Index movement predictions

Abstract

Attempts to forecast stock market trends have been made by many researchers coming from different fields using different approaches and techniques. This research aims to investigate the application of machine learning models, specifically Support Vector Machine (SVM) and Long Short-Term Memory (LSTM), for predicting price movements in the Kazakhstan Stock Exchange (KASE) for KASE Index. The study utilizes historical stock price data for KASE Index from the period of 2007-2023 to train and test SVM and LSTM models. The research finds that SVM and LSTM models can produce satisfactory results in predicting the movements of KASE Index. The results suggest that both SVM and LSTM models have the potential to be effective tools for predicting price movements in KASE, and they can be utilized by investors and traders for making informed decisions in their trading strategies. This research contributes to the research on KASE as well as the literature on stock price prediction in the context of KASE by exploring the application of SVM and LSTM models.