Does Machine Learning Amplify Pricing Errors in the Housing Market? -- The Economics of Machine Learning Feedback Loops

TL;DR

This paper develops an analytical model to explore how machine learning feedback loops in the housing market can lead to erratic prices, overconfidence in models, and worse economic outcomes for sellers, supported by empirical validation.

Contribution

It introduces a novel analytical framework for understanding machine learning feedback loops in housing markets and proposes strategies to mitigate their negative effects.

Findings

Feedback loops cause overconfidence in ML accuracy.

Prices can become erratic and misaligned with true preferences.

Certain market and model choices worsen seller outcomes.

Abstract

Machine learning algorithms are increasingly employed to price or value homes for sale, properties for rent, rides for hire, and various other goods and services. Machine learning-based prices are typically generated by complex algorithms trained on historical sales data. However, displaying these prices to consumers anchors the realized sales prices, which will in turn become training samples for future iterations of the algorithms. The economic implications of this machine learning "feedback loop" - an indirect human-algorithm interaction - remain relatively unexplored. In this work, we develop an analytical model of machine learning feedback loops in the context of the housing market. We show that feedback loops lead machine learning algorithms to become overconfident in their own accuracy (by underestimating its error), and leads home sellers to over-rely on possibly erroneous algorithmic prices. As a consequence at the feedback loop equilibrium, sale prices can become entirely erratic (relative to true consumer preferences in absence of ML price interference). We then identify conditions (choice of ML models, seller characteristics and market characteristics) where the economic payoffs for home sellers at the feedback loop equilibrium is worse off than no machine learning. We also empirically validate primitive building blocks of our analytical model using housing market data from Zillow. We conclude by prescribing algorithmic corrective strategies to mitigate the effects of machine learning feedback loops, discuss the incentives for platforms to adopt these strategies, and discuss the role of policymakers in regulating the same.