Hybrid Genetic-Based Support Vector Regression with Feng Shui Theory for Appraising Real Estate Price

Abstract

In this paper, we proposed a novel house prediction model that integrated hybrid genetic-based support vector regression (HGA-SVR) model and Feng Shui theories for developing a high accuracy appraising real estate price system in Taiwan. In Taiwan, Feng Shui theory applies in choosing good days, divination and house selection. From the past researches, many factors might affect the real estate price which are the announced land values, the building room age, building total number of floor, the transportation condition and surrounding environment of house etc. However, few studies have been considered the Feng Shui effects in appraising real estate price. Therefore, the present study pioneers in applying Feng Shui theories for developing a high accuracy real estate price prediction system with back-propagation neural network(BPN), fuzzy neural network (FNN) and Hybrid Genetic-based SVR (HGA-SVR) to compare.Our results obtained from the comparison between two house price models with various artificial neural network models. By comparing the accuracy with various network architectures, the result demonstrates that HGA-SVR is the best network architecture and the Feng Shui model has a better performance in BPN, FNN and HGA-SVR. Our house price prediction system discovers some real estate price much higher than the reasonable prices. This result shows these unreasonable price needs adjusting to become more reasonable to conform the housing market.