Predicting the spending capacity of customers on cars using a combined data mining approach

Data Mining is an analytic process designed to search through a large database in search of consistent patterns or systematic relationships between variables among data. It is an iterative process of selecting, exploring and modeling large amounts of data to identify meaningful, logical patterns and relationships among key variables. It is used to uncover trends, predict future events and assess the merits of various courses of action. In today's scenario there exist various Multinational as well as Indian companies offering a flotilla of cars existing in a wide assortment. It becomes very difficult for the owner of the dealership to identify and project their prospected customers and also to extract the knowledge from the existing voluminous data, which can be used for decision making. This paper is an attempt to analyze various supervised and unsupervised algorithms and to suggest an efficient model that predicts the spending capacity on cars as per the customer's demographic details which further results in future cost reduction as every company now a day is running towards cost cutting and its one of the crucial factor for survival in market in present scenario. The company can make production in accordance with the demand and thereby reducing their maintenance cost. The model is tested using WEKA, a regression and data mining tool. Empirical result shows that the proposed model works better than the traditional model.