An Innovate Hybrid Approach for Residence Price Using Fuzzy C-Means and Machine Learning Techniques

House price forecasting is an important topic of real estate. The excessive increase of housing price will affect not merely the quality of life, but also the business cycle dynamics. However, the factors influencing residential real estate prices are complex and the selection of effective features is vague, which leads many of the traditional housing price prediction approaches to lower accuracy results. Housing price is strongly correlated to other factors such as location, area, population. In this research, the authors propose an innovate hybrid approach that consists of (i) Fuzzy C-Means (FCM) Algorithm and (ii) Coarse Tree, to predict the cluster that the residence price belongs. The innovation of this research stands to the use of FCM for data-handling and at the exhaustive search for the best Machine Learning (ML) Algorithm. The proposed approach achieves promising results achieving an overall accuracy of 78.8% for Train Data and 79.37% for Test Data. Furthermore, all indices range to relatively high levels and confusion matrix indicate a stability and consistency in the forecast. The algorithm can generalize and therefore, could be utilized as a benchmark for a variety of groups that could benefit from housing price prediction.