Heterogeneous Demand Effects of Recommendation Strategies in a Mobile Application: Evidence from Econometric Models and Machine-Learning Instruments

TL;DR

This study evaluates how different recommendation strategies in mobile apps influence consumer demand, revealing that social proof and diversity-based approaches are most effective, with heterogeneity across items and users confirmed through advanced econometric and machine learning methods.

Contribution

It introduces novel econometric instruments based on deep learning to estimate causal effects of recommendation strategies, highlighting the importance of social proof and diversity in demand impact.

Findings

Social proof strategies outperform others

Diversity-based recommendations have stronger effects

Demand effects vary across items and users

Abstract

In this paper, we examine the effectiveness of various recommendation strategies in the mobile channel and their impact on consumers' utility and demand levels for individual products. We find significant differences in effectiveness among various recommendation strategies. Interestingly, recommendation strategies that directly embed social proofs for the recommended alternatives outperform other recommendations. Besides, recommendation strategies combining social proofs with higher levels of induced awareness due to the prescribed temporal diversity have an even stronger effect on the mobile channel. In addition, we examine the heterogeneity of the demand effect across items, users, and contextual settings, further verifying empirically the aforementioned information and persuasion mechanisms and generating rich insights. We also facilitate the estimation of causal effects in the presence of endogeneity using machine-learning methods. Specifically, we develop novel econometric instruments that capture product differentiation (isolation) based on deep-learning models of user-generated reviews. Our empirical findings extend the current knowledge regarding the heterogeneous impact of recommender systems, reconcile contradictory prior results in the related literature, and have significant business implications.