Consumer Acquisition for Recommender Systems: A Theoretical Framework and Empirical Evaluations.

How to acquire the most valuable consumers to grow your recommender system? We propose a dynamic consumer acquisition model to enable value-driven acquisition decisions. We build a model of consumer acquisition that takes into account the value that a consumer contributes to the recommender system, the cost of their participation (e.g., privacy loss), and the value of their participation to other consumers (via network externality). We also propose data-driven procedures to estimate this model to enable informed, value-driven acquisition decisions. On three different data sets, we perform comprehensive simulation-based evaluations to demonstrate the performance of this dynamic consumer acquisition model. We find nuanced relationships between the firm's choice of incentive strategies and acquisition outcomes. Neither a constant pricing strategy nor a greedy pricing strategy may be optimal. Instead, under a moderately greedy strategy, where the firm only partially extracts the network externality from consumers, the dynamic acquisition sequence can outperform random acquisition sequences on firm utility, recommender system performance, and consumer surplus simultaneously. Our work contributes a novel theoretical framework, practical insights, and design artifacts to facilitate effective consumer acquisition in recommender systems. We consider a marketplace where a recommender system provider (the firm) offers incentives to acquire prospective consumers by leveraging information that a market intermediary collects about these consumers. We investigate a model of consumer acquisition that incorporates several factors affecting acquisition decisions, including the value that a consumer contributes to the recommender system, the cost of participation to the consumer (e.g., privacy loss), and the value that a consumer can derive from the system due to network externality created by existing consumers. Our model is dynamic in nature, where the firm iteratively decides the next acquisition target based on previously realized acquisition outcomes. We propose flexible data-driven procedures to estimate some of the key parameters in the model using consumers' data collected by the market intermediary, for example their historical consumption data or the consumption data of other similar consumers. We also design an algorithm to compute the dynamic acquisition sequence and the corresponding incentives to offer. We conduct simulation-based empirical evaluations on two canonical recommendation tasks: movie recommendation based on numerical ratings and product offer recommendation based on browsing (clicking) behaviors and benchmark our acquisition model with random acquisition sequences with respect to (i) firm utility, (ii) recommender system performance, and (iii) consumer surplus. We find nuanced relationships between the firm's choice of incentive strategies and acquisition outcomes. Specifically, neither a constant strategy (setting the same incentive for all consumers) nor a fully greedy strategy (extracting all cumulative network externality) is optimal on all acquisition outcomes. Under a moderately greedy strategy, where the firm only partially extracts the cumulative network externality from consumers, the dynamic acquisition sequence can outperform random sequences on three acquisition outcomes simultaneously. Our work contributes a novel theoretical framework, practical insights, and design artifacts to facilitate effective consumer acquisition in recommender systems. History: Giri Kumar Tayi, Senior Editor; Maytal Saar-Tsechansky, Associate Editor. Supplemental Material: The online appendices are available at https://doi.org/10.1287/isre.2023.1229. [ABSTRACT FROM AUTHOR]