Application of Machine Learning Technology in Financial Market
Download as PDF
Mengtian Wang, Pan Xu, and Jun Liu
With the development of economy, people are paying more attention to the financial investment. The prediction of the Stock/Future prices could have significant influence on the financial market. But it is hard to predict the prices for they are time series, dynamic and non-linear. To have valid data, machine learning methods are adopted, because they are good at dealing with those problems and have good performance on the financial market. Therefore, this paper presents a detailed review of 30 research papers about the application of machine learning technology in financial market suggested methodologies like Support Vector Machine (SVM), Artificial Neural Networks (ANN), Decision Tree (Random Forest) and so on. We use publication years, datasets, methods and research direction to analyze the works. Most papers reviewed here are published in recent years, and SVM and ANN are the most common methods used in the quantitative trading. According to the research direction, Stock Selection and Timing are the main targets. Based on lots of research results, the paper finds that many disadvantages exist in the current quantitative trading. From this survey, it can be concluded that machine learning technology used in financial market is not very efficient. And a better machine learning method should be found and more factors should be considered for quantitative trading as well.
Machine learning; Quantitative trading; Financial market