House Hack

Team 14: Support housing decision making


Technologies Used

No stack info.

Project Team


This team is looking for

Product Manager Investor


1) A tool to make housing decisions by: (a) Investigating factors affecting housing prices (b) weighting the importance of factors Target users: (a) People who want to buy a property (e.g. is it a good time to buy?) (b) Property agencies (e.g. which properties should I promote to a specific group of people?) (c) Government: evaluate housing policy effectiveness (e.g. is a policy effective in lower housing price?) 2) Structural Attributes: Price, Floor Area, Property Age etc. Neighbourhood Attributes: Education, Leisure etc. Locational: Distance to the closest city centre by public transport, Pollution Index etc. 3) Structural Attributes: Centaline Property Agency Neighbourhood Attributes: DATA.GOV.HK Locational: Data-HK 4) Problems: Perception on housing price (including that of property buyers, agents and governments) are mostly based on gut feeling. Benefits: - Data blending: Merging traditional standard property data to other open data sources. Map and match as much data as possible. - It serves as scientific way to decide if the property is “good value” or not. Also if a housing policy is effective or not. Use case: Government released a housing policy aiming to support the low-income group to buy properties. (a) Transform and quantify the policy into a variable (b) Fit this variable into a pricing model (c) Decide if the policy is effective in lowing housing price 5) (a) Hedonic pricing model. (b) Box-Cox transformation. (c) Time-series. 6) Sell as a recommendation system to support the decision making process related to property management.