An Artificial Intelligence Based Mechanism For Stock Market Analysis And Prediction

Abstract

Stock markets are always an attractive investment way to grow capital. With the development of communication technology, the stock markets are getting more popular among individual investors in recent decades. A stock’s value can vary depending on various internal and external factors, with this paper the objective is to give a predictive analysis of a company’s stock price forthe future from previous parameters and how artificial intelligence (AI) can be used in stock  markets by companies/ individualsto get a fair return on their investments. While year by year,the number of shareholders and companies is growing in the stock markets, many try to find a
solution to predict a stock market’s future trend. The LSTM method is implemented using python in google colab. The long short term memory (LSTM) makes use of recurrent neural network (RNN) and memory storing and reusing. LSTMs are a complex area of deep learning. It can be hard to get your hands around what LSTMs are, and how terms like bidirectional and sequence-tosequence relate to the field. To test the performance of the proposed mechanism, we have the dataset of BAJAJ FINSERV from the past 10 years is obtained and visualized. The information given in this dataset is used to forecast future stock prices thorough ML algorithms, i.e., SVM, LSTM withRNNs. In the proposed scheme, we have obtained results, like, R2 score was 0.95 on the test dataset and 0.92 on the train dataset. F1 score was 0.15 and accuracy was 96%.