This papers studies how competition affects machine learning (ML) predictors. As ML becomes more ubiquitous, it is often deployed by companies to compete over customers. For example, digital platforms like Yelp use ML to predict user preference and make recommendations. A service that is more often queried by users, perhaps because it more accurately anticipates user preferences, is also more likely to obtain additional user data (e.g. in the form of a Yelp review). Thus, competing predictors cause feedback loops whereby a predictor's performance impacts what training data it receives and biases its predictions over time. We introduce a flexible model of competing ML predictors that enables both rapid experimentation and theoretical tractability. We show with empirical and mathematical analysis that competition causes predictors to specialize for specific sub-populations at the cost of worse performance over the general population. We further analyze the impact of predictor specialization on the overall prediction quality experienced by users. We show that having too few or too many competing predictors in a market can hurt the overall prediction quality. Our theory is complemented by experiments on several real datasets using popular learning algorithms, such as neural networks and nearest neighbor methods.

中文翻译：

---

竞争 AI：竞争反馈如何影响机器学习？

本文研究了竞争如何影响机器学习 (ML) 预测器。随着机器学习变得越来越普遍，公司经常部署它来争夺客户。例如，像 Yelp 这样的数字平台使用机器学习来预测用户偏好并提出建议。用户更经常查询的服务，也许是因为它更准确地预测用户偏好，也更有可能获得额外的用户数据（例如，以 Yelp 评论的形式）。因此，相互竞争的预测器会导致反馈循环，从而预测器的性能会影响它接收的训练数据，并随着时间的推移使预测产生偏差。我们引入了一个灵活的竞争 ML 预测器模型，可以实现快速实验和理论可处理性。我们通过实证和数学分析表明，竞争导致预测器专注于特定的亚群，代价是比一般人群表现更差。我们进一步分析了预测器专业化对用户体验的整体预测质量的影响。我们表明，市场中竞争性预测器太少或太多都会损害整体预测质量。我们的理论得到了使用流行的学习算法（例如神经网络和最近邻方法）在几个真实数据集上的实验的补充。我们表明，市场中竞争性预测器太少或太多都会损害整体预测质量。我们的理论得到了使用流行的学习算法（例如神经网络和最近邻方法）在几个真实数据集上的实验的补充。我们表明，市场中竞争性预测器太少或太多都会损害整体预测质量。我们的理论得到了使用流行的学习算法（例如神经网络和最近邻方法）在几个真实数据集上的实验的补充。