Supervised machine learning for eliciting individual demand

The canonical direct-elicitation approach for measuring individuals' valuations for goods is the Becker-DeGroot-Marschak procedure, which generates willingness-to-pay (WTP) values that are imprecise and systematically biased. We show that enhancing elicited WTP values with supervised machine learning (SML) can improve estimates of peoples' out-of-sample purchase behavior. Furthermore, swapping WTP data with choice data generated from a simple task leads to comparable performance. We quantify the benefit of using various SML methods in conjunction with using different types of data. Our results suggest that prices set by SML would increase revenue by 29 percent over using the stated WTP, with the same data.