arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.06797cs.LGcs.AIcs.MAstat.ML
收藏

竞争AI:竞争反馈如何影响机器学习?

Competing AI: How does competition feedback affect machine learning?

Stanford University(斯坦福大学)

Antonio Ginart, Eva Zhang, Yongchan Kwon, James Zou

摘要:

本文研究竞争如何影响机器学习(ML)预测器。随着ML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ML来预测用户偏好并提出建议。用户更经常查询的服务,可能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,竞争的预测器引起反馈回路,由此预测器的性能影响其接收的训练数据并且随时间推移使其预测有偏差。我们引入了一个灵活的竞争ML预测模型,可以实现快速实验和理论上的易处理性。我们用实证和数学分析表明,竞争导致预测者专门针对特定的子人群,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,在市场中有太少或太多的竞争预测可以损害整体预测质量。我们的理论是补充几个真实的数据集上使用流行的学习算法,如神经网络和最近邻方法的实验。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑