STOCK MARKET PREDICTION USING STACKED LSTM

Abstract

The direction of the financial market is always stochastic and volatile and the return of the security return is deemed to be unpredictable. Analysts now are trying to apply the modeling techniques from Natural Language Processing into the field of Finance as the similarity of having the sequential property in the data. In this research, we have constructed and applied the state-of-art deep learning sequential model, namely Long Short Term Memory Model (LSTM), StackedLSTM and Attention-Based LSTM, along with the traditional ARIMA model, into the prediction of stock prices on the next day. Moreover, using our prediction, we built up two trading strategies and compared them with the benchmark. Our input data not only contains traditional end-day price and trading volumes, but also includes corporate accounting statistics, which are carefully selected and applied into the models. The accounting data are regarded as the news and price shocks to a corporation, hence are expected to increase the predictive power of the model. The result has shown that Attention-LSTM beats all other models in terms of prediction error and shows much higher return in our trading strategy over other models. Furthermore, we discovered that the stacked-LSTM model does not improve the predictive power over LSTM, even though it has a more complex model structure. The prediction of stock value is a complex task which needs a robust algorithm background in order to compute the longer term share prices. Stock prices are correlated within the nature of the market; hence it will be difficult to predict the costs. The proposed algorithm uses the market data to predict the share price using machine learning techniques like recurrent neural network named as Long Short Term Memory, in that process weights are corrected for each data point using stochastic gradient descent. This system will provide accurate outcomes in comparison to currently available stock price predictor algorithms. The network is trained and evaluated with various sizes of input data to urge the graphical outcomes.