Offering Online Recommendations with Minimum Customer Input Through Conjoint-Based Decision Aids

摘要: In their purchase decisions, online customers seek to improve decision quality while limiting search efforts. practice, many merchants have understood the importance of helping in decision-making process and provide aids visitors. this paper, we show how preference models which are common conjoint analysis can be leveraged design a questionnaire-based aid that elicits customers' preferences based on simple demographics, product usage, self-reported questions. Such system offer relevant recommendations quickly with minimal customer input. We compare three algorithms---cluster classification, Bayesian treed regression, stepwise componential regression---to develop an optimal sequence questions predict visitors' preferences. empirical study, relying fewer easier-to-answer questions, achieved predictive accuracy equivalent traditional approach.