Eliciting Human Judgment for Prediction Algorithms
29 Pages Posted: 15 Jun 2020
Date Written: May 20, 2020
Even when human point forecasts are less accurate than data-based algorithm predictions, they can still help boost performance by being used as algorithm inputs. Assuming one uses human judgment indirectly in this manner, we propose changing the elicitation question from the traditional direct forecast (DF) to what we call the private information adjustment (PIA): how much the human thinks the algorithm should adjust its forecast to account for the information that only the human has. Based on a behavioral model, we theoretically prove that, when there is human random error in the forecast, eliciting the PIA leads to more accurate predictions than eliciting the DF; however, this DF-PIA gap does not exist for perfectly-consistent forecasters. The DF-PIA gap is increasing in the random error people make while incorporating public information (data that the algorithm has access to) but is decreasing in the random error that people make while incorporating private information (data that only the human has access to). In controlled experiments with students and Amazon Mechanical Turk workers, we find support for these hypotheses and demonstrate the flexibility to conduct elicitation in multiple ways to enhance performance.
Keywords: laboratory experiments, behavioral operations, random error, elicitation, forecasting, prediction, discretion, expert input, private information, judgment, aggregation
Suggested Citation: Suggested Citation