International Journal of Computer Applications (0975 – 8887) Volume 119 – No.24, June 2015 35 Importance of Location Classification using Rough Set Approach for the Development of Business Establishment Sujogya Mishra Research scholar, Utkal University Bhubaneswar-751004, India Shakti Prasad Mohanty Department of Mathematics College of Engineering and Technology Bhubaneswar-751003, India Sateesh Kumar Pradhan Department of Computer Science Utkal University Bhubaneswar-751004, India Radhanath Hota Department of Computer Science College of Basic Science & Humanities OUAT, Bhubaneswar- 751003, India ABSTRACT In the recent age business establishments are basically needs scientific approach to attain success. In this paper we consider different forms of location and using rough set we develop an algorithm to find best form of location required to attain success in a particular business. Keywords Rough Set Theory, business data, Granular computing, Data mining 1. INTRODUCTION The demand for business and wide use of modern technology for the development of business produces huge data in many forms. The data generation not only put dilemma in the mind of the user but also it creates obstacle for user to derive the exact result. This has created an obvious challenge for the researchers in the development of reduce data set and to derive the exact data for a particular application. The application of rough set theory has a prime role to play for knowledge discovery in data base(s).The ever increasing field of knowledge discovery (KD) that helps in derivation of hidden information from large database[3]. Data mining is also considered as essential tool in this knowledge discovery process which uses techniques from different disciplines ranging from machine learning, statistics information sciences, database, visualization ([4]- [12]). Further, prediction of business failure needs a systematic and scientific study. The first approach to predict business failure started in 1995 by Zopounidis( [24]-[26]). The methods proposed are the “five C” methods, the “LAPP” method, and the “credit-men” method. Then, financial ratios methodology was developed for business failure prediction problem. This approach gives rise the methods for business failure prediction based on multivariate statistical analysis (Altman ([13]-[15]), Beaver[17], Courtis[18]). Frydman et al[19] first employed recursive et al[16], multi-factor model by Vermeulen et al[23] are also other methods developed for business failure prediction. This paper presents a methodology for business success by reduction of attributes using rough set theory. Portioning, while Gupta et al[20] use mathematical programming as an alternative to multivariate discriminate analysis for business failure prediction problem. Other methods used were survival analysis by Luoma, Laitinenl[21] which is a tool for company failure prediction, expert systems by Messier and Hansen[22] , neural network by Altman 2. PRILIMINARIES 2.1 Rough set Rough set theory as introduced by Z. Pawlak[2] is an extension of conventional set theory that support approximations in decision making. 2.1.2 Approximation Space An Approximation space is a pair (U , R) where U is a non- empty finite set called the universe R is an equivalence relation defined on U. 2.1.3 Information System An information system is a pair S = (U , A), where U is the non-empty finite set called the universe, A is the non-empty finite set of attributes 2.1.4 Decision Table: A decision table is a special case of information systems S= (U, A= C U {d}), where d is not in C. Attributes in C are called conditional attributes and d is a designated attribute called the decision attribute. 2.1.4 Approximations of Sets Let S = (U, R) be an approximation space and X be a subset of U. The lower approximation of X by R in S is defined as R X = { e ε U | [e] ε X} and The upper approximation of X by R in S is defined as where [e] denotes the equivalence class containing e. A subset X of U is said to be R-definable in S if and only if R X= R X A set X is rough in S if its boundary set is nonempty. } ] /[ {      X e U e X R