Deep Learning with XGBoost for Real Estate Appraisal

Abstract

Real estate appraisal is an important tool for evaluating property values when purchasing, selling, insuring, lending or taxing on residency properties. The traditional way to do real estate appraisal is to analyse recent sales data with basic information, such as bedrooms, bathrooms, land-size, and suburb to estimate house price prediction by comparing and selecting similar properties to the property that is being evaluated. Real estate agents are widely using this method for their clients to help them determine a price to list when selling a home or a price to offer when buying a home. However, the traditional method is very subjective and depends heavily on the experience and knowledge of real estate agents and two different agents might come up with different estimate prices. Today, machine learning and deep learning techniques provide an objective, advanced and robust option, making the joint analysis of tabular data combined with visual content possible. We are interested in estimating the real estate prices like real estate agents. In this paper, we examine to use deep learning combining with extreme Gradient Boosting (XGBoost) for real estate appraisal, by analysing historical sale records together with visual content, with online house pictures, and by scoring each image from an aesthetic point of view to make a house price prediction. Our experiment shows that an improvement in performance of house price prediction accuracy, with replacing the last output layer with XGBoost.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 84 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.