Using machine learning algorithms, a comparative analysis of stock market prediction

Abstract

Stock Market prediction is the process of analyzing the stocks or other financial instruments traded on an exchange and determining their future value. It can prove to be useful for trading and technical analysis, Trading involves hundreds of transactions to be executed in a single second making it manually insurmountable. Therefore, Algorithm Trading has emerged as an area of interest in the financial world, This interest has led to the rise of implementation of Signal Processing Filters which predicts the future market movements and develop algorithms accordingly, In this paper, we study the usage of such signal processing filters, particularly diving deep into the implementation of the Kalman Filter in Algorithmic Trading, this paper aims at applying Machine Learning Algorithms: Linear regression and Kalman Filter to perform stock prediction by forecasting the real stock movements