Proposed study on evaluating and forecasting the resident property value based on specific determinants by case base reasoning and artificial neural network approach

Abstract

Real estate forecasting has become an integral part of the larger process of business planning and strategic management in real estate sector. This study covers residential estate markets and concentrates on property types, while previous studies that have considered country wide house price indices. There is a gap identified in the literature which need to study correlations between property types within a region or a city and whether they will provide diversification benefits for real estate investors such as risk reduction per unit of returns. This aim of the paper is to propose and develop a computer assisted real estate property price forecasting model. This proposed framework will examine the current uses of artificial intelligence, particularly combining case base reasoning and artificial neural network, in the business-forecasting field and considers suitable applications in real estate. The methodology consists of five phases: 1) Data gathering b) Data cleaning c) ANN Training d) CBR (Case Base Reasoning) similarity retrieval e) Result retrieval. This research will investigate the influence of residential real estate property characteristics on property values (prices) in global context, it revealed a high positive linear correlation between property characteristics and the property market values; an indication that these characteristics reasonably predict property market values. The results of the study will enable Real Estate Professionals to make fair estimates of the market values of residential real estate properties given the features/characteristics of such housing units.