Prediction model for predict the Share Market Price

Abstract

In current days, stock market has become one of the most popular investing methods among investors. But investing on share market is not much easy thing. Most of the traders have no idea about the right time to invest in stock market. Since share market can change due to many facts, it is very hard to make the prediction about financial market trends. successful prediction can make huge profits. Nowadays most of the investors are trying to make the predictions by analyzing the past values of share market. These predictions can be made by using machine learning techniques. Artificial Neural Networks and Support Vector Machines are the most common methods that can be used to make the predictions. In this study, three different forecasting techniques have been implemented to make the prediction. Standard averaging, Exponential moving average and Long short-term memory are the techniques used in this article. This article is comparing the outcomes of above-mentioned methods to find out the most suitable prediction technique among them. Here, historic data in Colombo stock exchange has been used as the inputs for above mentioned methods. The data set used in this research contains data from 2011 to 2018. Here, data preprocessing methods have to be followed as row data set which is given by CSE had some dirty, missing data. This study also talked about the preprocessing techniques that can be used to clean the dirty data.