What metrics did you obtain from the real estate valuation model and how did you monetize it?

For a real estate valuation model, the key metrics are:

• MAE (Mean Absolute Error) — the average absolute error, showing the average deviation of the predicted price from the actual.
• RMSE (Root Mean Squared Error) — the square root of the mean squared error, more sensitive to larger errors.
• R² (coefficient of determination) — shows the proportion of price variation explained by the model.

Example: an MAE of about 5000 rubles on an average apartment price of 3 million is an acceptable result.

Earnings from such a model can be achieved through:

• Automating valuation for real estate agencies, reducing labor costs.
• Integration into platforms for quick valuation during sale or rent.
• Providing analytics and forecasts for investors.

Example of use: the model predicts the market price, which helps set a competitive price and sell the property faster.