Does Machine Learning Amplify Pricing Errors in Housing Market? : Economics of ML Feedback Loops
45 Pages Posted:
Date Written: September 18, 2020
ML pricing models (Zillow’s Zestimate, Redfin Estimate) have been deployed in the last decade to make house price predictions. These ML models are revised regularly using recent sample of sales. The recent sales are themselves confounded by previous version of the ML model. We theoretically show how this Feedback Loop creates a self fulfilling prophecy where ML over estimates its own prediction accuracy and market participants over rely on ML predictions. We formulate size of resulting pricing bias. We identify conditions on ML and market characteristics such that participants are worse off after introduction of ML. We use data from Zillow’s Zestimate for empirical evidence for necessary primitives of our theoretical model.
Keywords: Machine Learning, Covariate Shift, Housing Market, Zillow, Bias - Variance Tradeoff
Suggested Citation: Suggested Citation