International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 03 Issue: 05 | May-2016 www.irjet.net p-ISSN: 2395-0072 © 2016, IRJET | Impact Factor value: 4.45 | ISO 9001:2008 Certified Journal | Page 1410 DEVELOPING PREDICTION MODEL FOR STOCK EXCHANGE DATA SET USING HADOOP MAP REDUCE TECHNIQUE Mrs. Lathika J Shetty 1 , Ms. Shetty Mamatha Gopal 2 1 Computer Science & Engineering, Sahyadri College of Engineering and Management, Mangalore, Karnataka, India 2 Computer Science & Engineering, Sahyadri College of Engineering and Management, Mangalore, Karnataka, India ---------------------------------------------------------------------***--------------------------------------------------------------------- ABSTRACT- Stock Market has high profit and high risk features which tells why its prediction must be close to accurate. The main issue about such data sets is that these are very complex nonlinear functions and can only be learnt by a data mining methods to recognize the future market trend. Companies provide daily statistics of their market trend and in time, generating a great deal of information which is dumped into their database. Forecasting stock price is an important task for investment and financial decision making process. This is considered as one of the biggest challenges. In this paper the proposed system goal is to develop a prediction model using MapReduce with the help of time-series analysis in Hadoop which can be used to predict the future stock closing price. This system will be a Hadoop based Stock Prediction Model generator for the people interested to know the future market trend of a particular company. The target clients are shareholders and the company officials. The developed model can be deployed and used by companies and shareholders to adjust their strategies based on the results of the analysis done. Key Words: Hadoop, HDFS, Map reduce, prediction model, stock exchange data set, prediction model 1. INTRODUCTION Stock Market has high profit and high risk features which tells why its prediction must be close to accurate. The main issues about such data sets are that these are very complex nonlinear functions and can only be learnt by a data mining methods to recognize the future market trend. Companies provide daily statistics of their market trend and in time, generating a great deal of information which is dumped into their database. The project goal is to develop a prediction model using Map Reduce technique with the help of time-series analysis in Hadoop which can be used to predict the future stock closing price. Hadoop is a Java based open source framework which uses simple programming models to allow storing and processing of Big Data in a distributed computing environment across clusters of computers. It is a part of the Apache Software foundation. It provides a design to scale up from single servers to thousands of machines and each offering local computation and storage. One of the most efficient solutions for processing of large data sets is Hadoop. The main components of Hadoop framework is HDFS and Map reduce. HDFS (Hadoop Distributed File System) is a block structured distributed file system which holds large amount of Big Data. It provides high throughput access to application data. HDFS uses master/slave architecture. Master consists of a single name node that manages the file system metadata and one or more slave data nodes that store the actual data. Hadoop MapReduce- Hadoop runs applications using map reduce algorithm which is a programming framework for distributed computing. Here divide and conquer method is used to break large complex data. A time series is a sequence of numerical data points in successive order, usually occurring in uniform intervals. In general, a time series can be defined as a sequence of numbers collected at regular intervals over a period of time. A stock is a share in the ownership of a company. Stock represents a claim on the company's assets and earnings. As you acquire more stock, your ownership stake in the company becomes greater. 2. LITERATURE SURVEY Various contributions are made in the direction of building prediction models for historical stock exchange data set. Works carried out in this field are as follows: [1] Time Series Forecasting Of Nifty Stock Market(NSE) Using Weka by Raj Kumar, Anil Balara in 2010, JRPS: Here the researchers utilized Weka 3.7.8 tool to obtain more accurate stock prediction price using time series forecasting package of weka for the work. Weka tool has been used and it analyzed and compared results by plot graphs.