Learning from Streaming Data when Users Choose

TL;DR

This paper models the feedback loop between user choices and service model updates in digital markets, proposing a decentralized algorithm that converges to optimal solutions and is validated with real data.

Contribution

It introduces a formal model of user-service interactions and a decentralized algorithm for minimizing user loss in streaming data settings.

Findings

Algorithm asymptotically converges to stationary points.

Validated effectiveness with real-world data.

Provides theoretical guarantees for convergence.

Abstract

In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model. The service providers' models influence which service the user will choose at the next time step, and the user's choice, in return, influences the model update, leading to a feedback loop. In this paper, we formalize the above dynamics and develop a simple and efficient decentralized algorithm to locally minimize the overall user loss. Theoretically, we show that our algorithm asymptotically converges to stationary points of of the overall loss almost surely. We also experimentally demonstrate the utility of our algorithm with real world data.