Supervised Machine Learning for Eliciting Individual Demand
研究发现，用监督机器学习改进Becker-DeGroot-Marschak程序测得的支付意愿，能更准确预测购买行为，且用简单任务的选择数据替代支付意愿效果相近，用机器学习定价可增收29%。
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.