Modelling Prediction of Cities Real Estate Price Trend Using Recurrent Neural Network: A Case of Dar es Salaam City

Abstract

Real estate refers to a class of real property such as land and its associated infrastructure. The prediction of real estate prices in cities, which is affected by a number of parameters, is an open research problem. The lack of reliable and effective tools for price forecasting in real estate, especially in residential housing, can adversely affect investment flows and the growth of the real estate sector. Taking Tanzania as an example, the price prediction practices rely on human suggestions that are prone to personal bias and subjective to price hysteria for personal gain and impact consumer expectations. To address the challenge, this paper designed a real estate price trend prediction model for the cities using Recurrent Neural Networks (RNN) with a Long Short-Term Memory (LSTM). The study identified the factors influencing real estate property prices, including size, location, time, property quality, accompanied services, market nature, price of land, cost of building materials, and value for money. However, the study spotted the size, price, location, and time as key factors in predicting price trends when using RNN-LSTM. The results show that the proposed RNN-LSTM model performed better with 50% MSE less compared to the Convolutional Neural Network (CNN). In computing the price trend per location, the model prediction accuracy was 97.45%, 79.23%, and 53.8% for the high class, middle class, and low class, respectively, resulting in an average prediction accuracy of 76.8%.