Stock Market Trading Framework using Deep Lea...

Stock Market Trading Framework using Deep Learning

Author Name : Aryankumar Pande, Pranali Nirbhawane, Riya Patil, Asmita Mahajan, Dr Mangesh M. Ghonge

ABSTRACT

Share Market prediction has been a key region of concern for the experts in this and related fields. Numerous modern technologies have been used with previously available statistical models over the years, in order to find better prediction techniques. Among the modern technologies, machine learning and to be more precise artificial intelligence holds the lion's share when it comes to market prediction models. In comparison to others techniques Deep learning techniques have shown better results when it comes to modeling the market movements. Some techniques have been tried and tested individually but results were not satisfactory, these techniques include automatic feature extraction, time series forecasting, convolutional neural network (CNN) etc. However a mixed framework with a variety of inputs and based on deep learning methods likes CNN and LSTM (Long Short Term Memory) is not much explored. we suggest a framework based on a convolutional neural network (CNN) paired with long-short term memory (LSTM) to predict the closing price of the stock market. A CNN-LSTM framework extracts features from a rich feature set and applies time series modeling to predict what will happen next. Features sets include raw price data of target index as well as foreign indices, technical indicators, currency exchange rates, commodities price data which are all chosen by similarities and well-known trade setups across the industry. Now let’s come to LSTM(Long Short Term Memory) part of it, it is famous for its series forecasting. works greatly with time series forecasting. Proper prices prediction will lead to an significant profit for the user of our framework/model. The successful prediction of a stock’s future price could yield a significant profit.

Keywords: Long Short-Term Memory, Convolutional neural network (CNN), Deep learning, machine learning, artificial intelligence.