Stock Market Analysis Using Artificial Neural Network on Big Data

Abstract

Big Data concern with large amount of data which is complex and continuously increasing [1]. We can relate such Big Data with Stock Market Prediction System. Effective market prediction can help investors with trade advices or can be used as a component inside automatic trader agents. The problem against precise predictions in these approaches, is modeling the random behavior of the market while there is no justification for it. In fundamental analysis of the market, factors are considered such as company economic growth, inflation, unemployment, earnings and etc. A successful news analysis would be achieved if the effective information about stock could be extracted from the news content. Basically automatic text classification techniques are used to analyze the incoming news. In addition in some approaches numerical parameters related to stock price are also include to increase prediction accuracy. There are two types of methods that handles complex data as statistical methods and non-statistical methods. Statistical methods has drawback that they can provide average prediction which is unreliable to handle continuously growing market's data. So we will use non-statistical methods which deals with data mining. If we co-relate data mining with neural network then we can get lots of achievements. From humans or other computer techniques point of view it is very difficult to detect trends and extract patterns from data which is imprecise and complex, but neural network helps us to work on it [2]. Utilizing these facilities on big data is not yet deployed. So we are just trying utilize them and come up with the solution which is suitable for Stock Market Analysis.