Implementation and Analysis of Fragment based Mining by using Jstock framework. Rajesh V. Argiddi,Sulabha S.Apte,Suhas S.Patil Computer Science Department, Walchand Institute of Technology, Solapur,India Abstract— In this research we propose an idea of using a JStock framework for getting accuracy of stock market prediction algorithms. Stock Market is the most unpredictable, popular and a big resource of income all over the world. Many researches are done for predicting the future market prices. Various algorithms lead to varying amount of accuracy. The proposed work will compare the various predictions made by the indicators and algorithms and will lead to a proper testing tool for checking accuracy of the stock market predictors. We have used JStock an open source software which analyses stock market by using technical indicators. By using the data provided by yahoo finance and the data extraction methods of JStock, we try to analyze the various stock market prediction methods and try to compare their accuracy. The performance of this testing is checked by the dataset provided by yahoo finance of Indian Stock markets and particular Indian Companies. However, they are less accurate in case of noisy trading, which makes them less appropriate in environments with high uncertainty about true prices for shares. Keywords— FITI; Fragment Based Mining, Association mining; Stock Data, Application Software, Algorithm analysis I. INTRODUCTION 1.1 What Is Stock market prediction? A stock market or equity market is a public entity (a loose network of economic transactions, not a physical facility or discrete entity) for the trading of company stock (shares) and derivatives at an agreed price; these are securities listed on a stock exchange as well as those only traded privately.[1] Stock Market prediction is future prediction of stock market by using historical data and analysing them to achieve patterns for getting probable market prices. There are various ways of predicting stock prices – 1. Using Technical Indicators. 2. Using historical data. 3. Using stock and related financial rules 4. Using association rules for prediction 5. Using genetic algorithms to get future prices Such various ways are used to get the probable prices of the required prices of stock market. II. RELATED WORK 2.1 JStock Open Source Software JStock software is a GNU Licenced software which uses technical indicators for stock analysis.It extracts data from yahoo finance. JStock is a free stock market software for 26 countries. It provides Stock watchlist, Intraday stock price snapshot, Stock indicator editor, Stock indicator scanner and Portfolio management. Free SMS/email alert supported. JStock has a framework that collects data from Yahoo finance API. It is legal way of collecting data.“To retrieve stock information, it is using method provided and allowed by Yahoo.[13] 2.2 Applications a. Stock Prediction Algorithms 1. Stock Investor gets a fair idea of investment and stock prices. 2. Stock Investors can choose a safer stock with safe price rises when required. b. Stock Prediction Algorithms Analysis 1. Better view of algorithms accuracy. 2. Proper testing tool for testing algorithms. 3. Can be used for stock analysis also. III. METHODOLOGY Proposed idea is to study JStock and create a framework to extract the data from yahoo finance. The framework will be used to implement fragment based mining algorithm. 3.1: Fragment based mining Fragment based mining is similar to Granular mining [17].Data sets are fragmented into fragments and hence the input size for algorithm is reduced. The condition and decision attributes are both used to obtain generalized association rules [18]. 3.2 Technical Indicators [10] – Market Indicators are mathematical calculations that are used to predict market values. Any class of metrics whose value is derived from generic price activity in a stock or asset. Technical indicators look to predict the future price levels, or simply the general price direction, of a security by looking at past patterns. Examples of common technical indicators include Relative Strength Index, Money Flow Index, Stochastic, MACD and Bollinger Bands.[2] The indicators are widely used in stock market prediction [3].Lot of research is done in stock prediction and analysis.[4-9]. The indicators are basic techniques used in JStock for scanning and analyzing the various stock simulations. 3.2.1 Moving Average The Moving Average (MA) is one of the most widely used tools in the technical community. A moving average is a lagging indicator. The importance of the moving average lies in that it tells us the direction of the trend in a smoother Rajesh V. Argiddi et al, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 5 (1) , 2014, 931-934 www.ijcsit.com 931