Prediction of stock price analyzing the online financial news using Naive Bayes classifier and local economic trends

Market and stock exchange news are special messages containing mainly economical and political information. This paper represents data mining algorithms which has been tested on this available information to learn useful trends about the behaviour of the stock markets. The learned trend holds the key to interpret the present and predict the next stock price. This resented work uses Naïve Bayes Algorithm to classify text news related to FTSE100 given on these mentioned websites and the classifier is trained to learn the movement in the stock price (up or down) from the news articles in the web pages of that day. Several heuristics are being used to remove irrelevant parts of the text to get a reasonable performance. This model had demonstrated a statistically significant performance in predicting stock prices compared to other previously developed methods.