A framework for predicting stock prices based on a novel deep learning algorithm

Stock price forecasting has been a difficult and crucial undertaking in the financial markets. The complex prediction models have been developed as a result of the changing stock values, which are affected by a wide range of variables. The development of deep learning (DL) and improved processing power has made programmed techniques of prediction effective at forecasting stock prices. In this article, we proposed a Stochastic Gradient Descent Weighted Long Short Term Memory (SGD-LSTM) method and a complete framework is used for predicting stock prices, which gives a novel viewpoint on stock market forecasting. Our system is comprised of three main parts: data preparation, feature extraction, and model design. To provide the highest quality data for training and assessment, we apply cutting-edge methods for data cleaning, normalization, and feature selection. The stock price data’s are collected. Min-max normalization method is used for preprocessing the collected data. The presented study makes use of the relative strength index to extract features since the index is representative of a variety of investing strategies that are taken into consideration by both the buyers as well as the sellers. This technique is used for analyzing the financial markets. We compared our system against both conventional forecasting models and other deep learning techniques on a wide variety of historical stock datasets to determine its efficacy. The results of the comparison reveal that the suggested prediction model provides more accurate forecasts.