Abstract
Deep Learning is appealing for learning from large amounts of unlabeled/unsupervised data, making it attractive for extracting meaningful representations and patterns from big data. Deep learning, by its simplest definition, is expressed as the application of machine learning methods to the big data. In this study, it was investigated how to apply hierarchical deep learning models for the problems in finance such as prediction and classification. The Design and pricing of securities, construction of portfolios, risk management and stock market forecasting are some of important prediction problems in finance. These kind of problems include large data sets with complex relationship among data and events. It is very difficult or sometimes impossible to represent these complex relationships in a full economic model. Deep learning methods, by representing complex relationships among data, allows the production of more useful results than standard methods in finance. In this study, we introduced and applied deep learning methods to stock market prediction problem and obtained successful results.