MACHINE LEARNING ALGORITHMS IN FORECASTING STOCK PRICES IN THE FINANCIAL MARKET

Abstract

The article analyzes approaches based on Machine Learning algorithms and Deep Learning techniques for stock price prediction in financial markets. Concepts of technical analysis, such as exponential and simple moving averages, are explored. Various global indices are analyzed to incorporate Machine Learning models, including Recurrent Neural Network (RNN), Long ShortTerm Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), and XGBoost. Research indicates that each model has distinct characteristics, and selecting the most effective approach depends on specific data and forecasting objectives. The complexity of models like XGBoost and GRU is reflected in their overall performance, and these models are proposed as effective tools capable of most accurately predicting complex time series patterns.