A hybrid neural network for predicting Days on Market a measure of liquidity in real estate industry

Abstract

In the real estate industry, Days on Market (DOM) is one of the most important attribute that is normally used to appraise real estate properties. In the academic sector, DOM is seemingly attracting a lot of researchers. DOM can be define as the length of time (i.e. in days) a real estate listing takes in passive market. In our paper, a novel hybrid neural network model is proposed to solve DOM prediction problem. Our proposed model extracts features using both CNN-based Attention (CNNA), and Bidirectional LSTM (BLSTM) modules. Furthermore, we concatenate their outputs and pass the results through a prediction (MLP) block, for predictions to be made. In implementing our model, overfitting was experienced as a challenge. In order to combat overfitting in our network we introduce Dropout layers in almost all the modules. Moreover, we present confidence intervals for four attributes in our dataset by using either percentile bootstrap confidence interval (CI) or percentile bias corrected accelerated (BCa) bootstrap CI, depending on the estimated distribution of an attribute. Finally, we appraise our model by experimenting with dataset of a famous real estate agency in Shanghai. The experimental outcomes clearly prove the superiority of the projected approach for solving DOM prediction problem.