Trulia Estimates 2.0
1 like507 views
Trulia is improving its home valuation estimates (Trulia Estimates) by adding new location-specific data features, improving its modeling techniques, and expanding its geographic coverage. Some key updates include adding crime safety and school proximity scores as new features, using cross-validation to learn location-specific model parameters, and implementing hierarchical modeling to leverage information from higher geographic levels. The goal is to provide more accurate home valuations before surfacing them more prominently on the Trulia platform and to users. Initial results show median error rates decreasing from 8.97% to 8.85% after integrating new geographic boundaries called "geoscopes" into the models.
Trulia Estimates 2.0
- 3. Motivation Trulia Estimates launched in 2011 Public records snowball has evolved since then, but the valuation algorithm has not Valuations already have a lot of visibility (valuation heatmaps etc) and we are planning to give them even more visibility in the near future (valuations history) Brilliant Basics Improve estimates before surfacing them everywhere
- 4. Us v/s Competition 0 5 10 15 Trulia Estimates Zestimate Median Error % Trulia Estimates Zestimate
- 5. Our Work Location specific and temporal features Crime Safety School Proximity Stats and Trends New Geoscopes Solve the problem of geographic boundaries Model Learning Improvements Explicit modeling of location hierarchies Better learned parameters Better feature representation and normalization
- 6. New Features 8.97 8.78 8.82 8.84 8.65 8.7 8.75 8.8 8.85 8.9 8.95 9 Baseline Add CrimeScore only Add SchoolScore only Add avg ppsqft/ hood only Improvement by Individual Features Median Error Percentage
- 9. New Geoscopes After the initial pass Coverage improved by 1.67% ~ 1.15million properties throughout the nation 330 more counties valued For San Mateo, median error goes from 8.97% to 8.85%
- 10. Model Learning Improvements Each geography is different. Static set of model parameters not always ideal Using cross validation to learn parameters for each location model from data Median error % improves from 8.97 to 8.69 (~3% relative improvement) Hierarchical Modeling Explicitly model Location Hierarchies to get smoother estimates using higher level information
- 11. Whats Next? Spend more time optimizing new features Optimization is everything! Add price trends data to the hedonic model and simplify our learning process Make per model parameter optimization scalable Incorporate hierarchical models into the existing mix