Machine Learning for Improved Automated Valuation Model (II)

To estimate the market value of a real estate, a computer software program can produce the result by analyzing the location, market conditions, and other characteristics relevant to it. This is known as the 'automated valuation model (AVM)'. The previous Mitacs Accelerate project with 'Data Nerds' has conducted a series of experiments with the attributes of real estates and geographic dependencies. This project is to further develop the AVM by incorporating temporal factors. The deep learning based approaches will be employed in this project. This development work will enable Data Nerds to achieve more accurate estimation of the real estate market by using all relevant data and information.

Junchi Bin
Faculty Supervisor: 
Zheng Liu
Project Year: 
British Columbia