Robotic Process Automation for Stock Selection Process and Price Prediction Model using Machine Learning Techniques

Abstract

Among these last few years, we have seen a tremendous increase in the participation in financial markets as well as there are more robotic process automation jobs emerging in recent years. We can clearly see the scope and increased requirement in both these domains. In the stock market, predicting the stock prices/direction and making profits is the main goal whereas in rpa, tasks which are done on a regular basis are converted into automated or semi-automated form. In this paper we have tried to apply both things into the picture such as developing a price prediction model using machine learning techniques and automating the stock selecting process through technical screeners depending on user requirements. Stacked LSTM and Bi-directional LSTM ML techniques are used and for automation part powerful rpa tool Automation Anywhere has been used. Factors such as evaluation metrics and graph plots are compared for models and advantages, and disadvantages are discussed for using systems with RPA and without RPA practices. Price prediction plots have been analyzed for stocks of different sectors with highest market capitalization and results/analysis and inferences have been stated.