Gaming Helps! Learning from Strategic Interactions in Natural Dynamics

We consider an online regression setting in which individuals adapt to the regression model: arriving individuals are aware of the current model, and invest strategically in modifying their own features so as to improve the predicted score that the current model assigns to them. Such feature manipulation has been observed in various scenarios—from credit assessment to school admissions— posing a challenge for the learner. Surprisingly, we find that such strategic manipulations may in fact help the learner recover the meaningful variables—that is, the features that, when changed, affect the true label (as opposed to non-meaningful features that have no effect). We show that even simple behavior on the learner’s part allows her to simultaneously i) accurately recover the meaningful features, and ii) incentivize agents to invest in these meaningful features, providing incentives for improvement.

我们考虑一种在线回归设定，其中个体适应回归模型：新到达的个体知晓当前模型，并策略性地投资于修改自身特征，以提高当前模型赋予他们的预测分数。这种特征操纵在从信用评估到学校招生等各种场景中都已被观察到，给学习者带来了挑战。令人惊讶的是，我们发现这种策略性操纵实际上可能有助于学习者恢复有意义的变量——也就是说，那些当被改变时会影响真实标签的特征（与那些没有影响的无意义特征相对）。我们表明，即使学习者采取简单的行为，也能使她同时做到：i）准确地恢复有意义的特征，以及ii）激励个体对这些有意义的特征进行投资，从而为改进提供激励。