Stock Prediction Based on Technical Indicators Using Deep Learning Model

Stock market trends forecast is one of the most current topics and a significant research challenge due to its dynamic unstable nature. The stock data usually non-stationary, attributes are non-correlative each other. Several traditional Technical Indicators (STIs) may incorrectly predict trends. To study characteristics using STIs make efficient trading decisions, robust model built. This paper aims build up an Evolutionary Deep Learning Model (EDLM) identify trends’ prices by STIs. proposed has implemented (DL) establish concept Correlation-Tensor. analysis dataset three popular banking organizations obtained from live based on National exchange (NSE) – India, Long Short Term Memory (LSTM) used. datasets encompassed days 17 Nov 2008 15 2018. work also conducted exhaustive experiments correlation various with price built EDLM shown improvements over two benchmark ML models deep learning one. aids investors in making profitable investment decisions as it presents trend-based forecasting achieved prediction accuracy 63.59%, 56.25%, 57.95% HDFC, Yes Bank, SBI, respectively. Results indicate that EDLA combination can often provide improved results than other state-of-the-art algorithms.