English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Machine learning algorithms are increasingly employed to price or value homesfor sale, properties for rent, rides for hire, and various other goods andservices. Machine learning-based prices are typically generated by complexalgorithms trained on historical sales data. However, displaying these pricesto consumers anchors the realized sales prices, which will in turn becometraining samples for future iterations of the algorithms. The economicimplications of this machine learning "feedback loop" - an indirecthuman-algorithm interaction - remain relatively unexplored. In this work, wedevelop an analytical model of machine learning feedback loops in the contextof the housing market. We show that feedback loops lead machine learningalgorithms to become overconfident in their own accuracy (by underestimatingits error), and leads home sellers to over-rely on possibly erroneousalgorithmic prices. As a consequence at the feedback loop equilibrium, saleprices can become entirely erratic (relative to true consumer preferences inabsence of ML price interference). We then identify conditions (choice of MLmodels, seller characteristics and market characteristics) where the economicpayoffs for home sellers at the feedback loop equilibrium is worse off than nomachine learning. We also empirically validate primitive building blocks of ouranalytical model using housing market data from Zillow. We conclude byprescribing algorithmic corrective strategies to mitigate the effects ofmachine learning feedback loops, discuss the incentives for platforms to adoptthese strategies, and discuss the role of policymakers in regulating the same.

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