A survey on machine learning models for financial time series forecasting

Abstract

Financial time series (FTS) are nonlinear, dynamic and chaotic. The search for models to facilitate FTS forecasting has been highly pursued for decades. Despite major related challenges, there has been much interest in this topic, and many efforts to forecast financial market pricing and the average movement of various financial assets have been implemented. Researchers have applied different models based on computer science and economics to gain efficient information and earn money through financial market investment decisions. Machine learning (ML) methods are popular and successful algorithms applied in the FTS domain. This paper provides a timely review of ML’s adoption in FTS forecasting. The progress of FTS forecasting models using ML methods is systematically summarized by searching articles published from 2011 to 2021. Focusing on the analysis of ML methods applied to the theoretical basis and empirical application of FTS data forecasting, this paper provides a relevant reference for FTS forecasting and interdisciplinary fusion research against the background of computational intelligence and big data. The literature survey reveals that the most commonly used models for prediction involve long short-term memory (LSTM) and hybrid methods. The main contribution of this paper is not only building a systematic program to compare the merits and demerits of specific FTS forecasting models but also detecting the importance and differences of each model to help researchers and practitioners make good choices. In addition, the limitations to be addressed and future research directions of ML models’ adoption in FTS forecasting are identified.