International Journal of Computer Applications (0975 – 8887) Volume 134 – No.12, January 2016 9 Prediction of Stock Market using Data Mining and Artificial Intelligence G. S. Navale Savitribai Phule Pune University SITS Narhe, Pune-411041 Nishant Dudhwala Savitribai Phule Pune University SITS Narhe, Pune-411041 Kunal Jadhav Savitribai Phule Pune University SITS Narhe, Pune-411041 Pawan Gabda Savitribai Phule Pune University SITS Narhe, Pune-411041 Brij Kishor Vihangam Savitribai Phule Pune University SITS Narhe, Pune-411041 ABSTRACT Predicting anything is very hard where the relationship between inputs and outputs are non-linear in nature. The prediction of stock market values is one of a challenging task of financial time series. Online application for buying and selling the shares is used in high amounts these days. The next step of this web application will be not just registering, buying and selling the shares but it will also be predicting the values for particular shares in the market. We are proposing the system which will study the database of shares and will give predictions according to it. With the help of study of neural networks the system will be designed and based on. For prediction particularly ARMA (autoregressive-moving- average) algorithm is used. Hence the system will be able to give highest probability predictions for particular shares. General Terms Data Mining, Prediction, Stock Market Keywords Artificial Neural Network, ARMA Algorithm, News articles, Text mining 1. INTRODUCTION Data mining is analytic process design to explore data (usually large amount of data-typically business or market related- also known as “Big Data”) in search of consistent patterns and/or systematic relationships between variables, and then to validate the findings by applying the detected patterns to new. Stock market is very volatile in nature. Prices of stocks changes almost instantly. Financial analysts who purchases stocks are not aware of all factors like inflation, economic growth affecting stocks prices. They do not have idea in which stocks to invest and sell. They can be easily manipulated by the stock brokers. Stock prices depend on news appearing in news articles. It is not possible for an average buyer to analyze such large amount of information .To deal with this problem Data Mining technique can be used. Data mining can automatically extract important information from large amount of data that is affecting the stock prices [9]. Predicting the stocks prices accurately can be done by Artificial Neural Network (ANN). The advantage of using ANN is that it can deal with both linear and non-linear data for forecasting the stock prices. Network is set of interconnected nodes and a node is a computational unit which produces an output on receiving an input. The nodes can be both unidirectional and bidirectional. In unidirectional nodes, information can flow in one way while in bidirectional nodes, information can flow in both ways. So, ANN is neural network consisting of artificial neurons. ANN is inspired by the way our brain functions [10]. 2. RELATED WORK Table 1 Paper ID Methodology Advantage Disadvantage [1] Genetic Algorithm, Support vector machines. SVM transform the inputs into decision classes. There is correlation between prices of certain stocks. Considering closing, opening, mean, standard deviation and number of days for which correlation is found is considered Various political, economic factors, company policy decide trends of markets are not considered while calculation. [2] Sentiment Analysis, Trading model. They collected aggregating information from multiple online sources. They performed sentiment analysis on given data and filtered out dataset as a It is necessary to analyze effects of applying different sentiments analysis methodology.