Econ Papers Daily / 期刊论文
个性化推荐的价值：来自Netflix的证据
The value of personalized recommendations: Evidence from Netflix
摘要
Personalized recommendation systems shape much of user choice online, yet their targeted nature makes separating out the value of recommendation and the underlying goods challenging. We build a discrete-choice model that embeds recommendation-induced utility, low-rank heterogeneity, and flexible state dependence and apply the model to viewership data at Netflix. We identify recommendation-induced engagement from observational variation in algorithmic exposure, treating exposure as conditionally exogenous given observed user, good, and state characteristics. Separately, we estimate model-free diversion ratios from a randomized experiment that perturbs recommendations and use these to assess the validity of the structural model. We use the model to evaluate counterfactuals that quantify the incremental engagement generated by personalized recommendations. First, we show that replacing the current recommender system with a matrix factorization or popularity-based algorithm would lead to a 4% and 12% reduction in engagement, respectively, and decreased consumption diversity. Second, most of the consumption increase from recommendations comes from effective targeting, not mechanical exposure, with the largest gains for mid-popularity goods (as opposed to broadly appealing or very niche goods).
中文摘要
个性化推荐系统在很大程度上塑造了用户的在线选择，但其针对性特征使得分离推荐本身的价值与所推荐商品的价值颇具挑战。我们构建了一个离散选择模型，该模型融合了推荐引致的效用、低秩异质性以及灵活的状态依赖性，并将此模型应用于Netflix的观看数据。我们通过算法曝光中的观测变异来识别推荐引致的参与度，将曝光视为在给定观测到的用户、商品及状态特征条件下的条件外生变量。此外，我们利用一项随机实验来估计无模型依赖的转移比率，该实验对推荐进行扰动，并以此评估结构模型的有效性。我们运用该模型评估反事实情境，量化个性化推荐所产生的增量参与度。首先，我们表明，若将当前推荐系统替换为矩阵分解或基于流行度的算法，参与度将分别下降4%和12%，且消费多样性也会降低。其次，推荐带来的消费增长大部分源于有效的目标定位，而非机械性曝光，其中中等流行度商品（相对于广泛吸引力或极为小众的商品）获益最大。