In generating a choice model to produce a good quality estimate of parameters related to product attributes, a high quality choice set is essential. However, the choice set data is often not available. This research proposes a methodology that utilizes online data and customer reviews to construct customer choice sets, in the absence of both actual choice set and customer socio-demographic data. The methodology consists of three main parts , i.e. clustering the products based on their attributes, clustering the customers based on their reviews, and constructing the choice sets based on a sampling probability scenario that relies on product clusters and purchased products. There are three scenarios proposed, i.e. Random as the baseline, Normalized, and Inverted. There are two utility functions proposed, i.e. a linear combination of product attributes only and a function that includes customer reviews as well. The methodology is implemented into two data sets of products, i.e. in-car DVD players and laptops. For both data sets, the Inverted scenario scores higher log-likelihood and adjusted R-squared values than both Random and Normalized. It implies that, in constructing their choice sets, customers are more likely to include groups of products that are rarely purchased by the people similar to themselves. As for the utility functions, the inclusion of customer reviews results in choice models with significantly better performance in most cases.

This content is only available via PDF.

Article PDF first page preview

Article PDF first page preview
You do not currently have access to this content.