The model behind the Property Score.

Inputs

Twelve user-supplied fields and a small set of derived features. We deliberately keep the public version of the model interpretable — every weight visible, every input explained.

• Property type, year built, living area, lot size, beds, baths
• Walk Score, transit time to downtown, school rating
• List price, comparable rent

Weights

• Location 30% — walkability, transit access and nearby schools.
• Value 20% — price per square foot against comparable homes of the same type.
• Yield 15% — expected rental income relative to the asking price, using CMHC market rents discounted by the local vacancy rate.
• Age & build 15% — how the year built affects expected condition.
• Size 10% — interior space against a typical home of that type.
• Lot 10% — land area, for detached and townhouse only.

How the score stays honest

No single factor can carry or sink a property. Extra space and land count for less as they grow — a second acre matters less than the first — and an unusually low price lifts the score without producing a number the property can't justify.

What's deliberately not public

On engagements, the model additionally consumes listing-level comparable sales, micro-location signals, strata health metrics, and a BC hazard layer. We will publish methodology updates as each module ships.