Appropriate rental price prediction for condominiums in Pattaya, Thailand, applying artificial neural network approach

Abstract

There is a high demand for condominiums in Pattaya, Thailand, a popular tourist destination and business hub. It is an economic and strategic location within the Eastern Economic Corridor (EEC). Accurate rental price estimation is crucial for investors, tenants, real estate developers, and policymakers. Traditional methods, such as regression analysis, have limitations in terms of requiring linear relationships and capturing complex data. This study applied Artificial Neural Network (ANN) to predict condominium rental prices in Pattaya by using factors such as distance to the beach, property size, building age, number of bedrooms and bathrooms, floor level, room type, and sea view. The dataset comprised 983 rental listings used to train the ANN model, validate its performance, and optimize its predictive accuracy. A comparison between the predictions from the ANN model and results obtained from stepwise multiple regression was also conducted. The findings confirm that ANNs provide a higher level of accuracy than multiple regression analysis. This study affirms the effectiveness of ANN in condominium rental price prediction and highlights the importance of combining ANN with traditional methods to enhance prediction accuracy and performance in the Thai real estate market.