A Hybrid Deep Learning Improved Method for Share Price Prediction

Share Market/ Equity Market are the most important current research topic. Machine learning is increasingly used in stock/index price prediction due to its ability to analyze large amounts of data and identify complex patterns that may not be immediately obvious to human analysts. There are several deep learning algorithms commonly used for stock price prediction, including RNN, CNN, LSTM, and DNN. In stock price prediction, hybrid models can be used to combine the predictions of multiple models to produce more accurate predictions. The paper proposed hybrid deep learning DNN-CNN based method to improve the prediction of NSE Bank i.e. Bank Nifty. The ensemble DNN-CNN technique consists of two main components a DNN for feature extraction and a CNN for regression or classification tasks. In DNN-CNN model DNN layer is used to extract features from input data related to an estimated future value and CNN layer is used to combine features learned from the DNN layers. The results represent that proposed method recall is 91.02, precision is 98.2 and accuracy is 97.4