The Application of Deep Learning in Financial Time Series Forecasting

Abstract

Financial time series forecasting is a challenging problem at the intersection of finance and computer science. It is the most widely known subset of artificial intelligence for finance researchers in both academic field and the finance sector due to its widespread application areas and great impact. Researchers in machine learning have developed numerous models, and a great number of related studies have been published. Accordingly, there are a significant amount of publications covering machine learning studies on financial time series forecasting. Recently, deep learning models have emerged in the sector, greatly outperforming the classical machine learning approches. Therefore, the purpose of this study is to present a comprehensive state-of-the-art of deep learning researches on the implementation of financial time series forecasting. The study begins with an introduction to artificial intelligence, the financial industry, and the fundamentals of trading. In addition to this, providing a review of the problem ”finanicial time series forecasting” across a variety of markets and exploring the various approaches discussed in the relevant academic literature. We classified the papers according to their intended application areas for forecasting, namely the cryptocurrency, stock, and forex markets, and we picked the most recent and well-known deep learning models, such as LSTM, GRU, and CNN...