Predictive data mining based on similarity and clustering methods.

Abstract

Predictive data mining is an attractive goal in data mining. It has wide application, including credit evaluation, sales promotion, financial forecasting and market trend analysis. In this paper we propose a predictive data mining model based on the combination of similarity, clustering and predictive modeling. This model is implemented and tested using real estate data. Our study concludes that our predictive data mining model can improve the prediction ability by using all attributes in the different clusters with the nearest distance as input fields. In this paper we explain the importance of data mining, similarity, the proposed predictive data mining model, the testing of the model, discussion and conclusion.