Abstract
Price prediction in the stock market is challenging since it is affected by several factors and the price shows a semi-random behavior. One important factor that is affecting the stock price, is the news associated with the companies. If a news article affects the market, it is called an Event, otherwise it is called non-important news or noise. Due to the semi-random behavior of the price and the high number of news articles, finding the correlation between the stock price and news articles and detecting the events among the news articles become very sophisticated, and consequently, predicting the price change regarding news articles gets challenging. In this paper, we propose a model to predict the impact of news articles on future stock prices. The model can capture the relationship between the price change and the news articles by an event detection method. The event detection method improves the prediction model by extracting the events among all news articles published in history and removing non-important news articles, or in another word, it decreases the noise. It helps to determine if a newly published news article is similar to an event in history and as a result, improves the performance of the prediction model. The provided results confirm that the event detection method improves the prediction.