This is a past event. Its details are archived for historical purposes.
The contact information may no longer be valid.
Please visit our current events listings to look for similar events by title, location, or venue.
Tuesday, October 2, 2018 at 11:40am to 1:10pm
Sage Hall, 141
Johnson Graduate School-Management, 106 Sage Hall, Ithaca, NY 14853-6201, USA
Jon Kleinberg (Cornell University)
Comparing Human and Algorithmic Performance on Stylized Tasks
Abstract: When we test a theory using data, it is common to focus on correctness: do the predictions of the theory match what we see in the data? But we also care about completeness: how much of the predictable variation in the data is captured by the theory? This question is diffcult to answer, because in general we do not know how much \predictable variation" there is in the problem. In this paper, we consider approaches motivated by machine learning algorithms as a means of constructing a benchmark for the best attainable level of prediction. We illustrate our methods on the task of predicting human-generated random sequences. Relative to an atheoretical machine learning algorithm benchmark, we find that existing behavioral models explain roughly 15 percent of the predictable variation in this problem. This fraction is robust across several variations on the problem. We also consider a version of this approach for analyzing field data from domains in which human perception and generation of randomness has been used as a conceptual framework; these include sequential decision-making and repeated zero-sum games. In these domains, our framework for testing the completeness of theories provides a way of assessing their effectiveness over different contexts; we find that despite some differences, the existing theories are fairly stable across our field domains in their performance relative to the benchmark. Overall, our results indicate that (i) there is a signifcant amount of structure in this problem that existing models have yet to capture and (ii) there are rich domains in which machine learning may provide a viable approach to testing completeness.