Performing customer segmentation and item categorization

Abstract

A method including receiving a weighting vector for each of a plurality of users, the weighting vector tracking a weight corresponding to each feature of a plurality of features. The plurality of features can represent purchasing criteria that are common to each item in a category of items. Each of the weights in the weighting vector for each user of the plurality of users can represent a level of importance of a different feature of the plurality of features to the user. The method also can include applying categorization rules on the weighting vectors for the plurality of users to categorize the plurality of users into a plurality of subgroups. The method additionally can include generating a profile weighting vector for each subgroup of the plurality of subgroups. The profile weighting vector can include a profile weight corresponding to each feature of the plurality of features that is based on weights for a corresponding one of the feature in the weighting vectors of users from among the plurality of users that are categorized into the subgroup. The method further can include selecting, for a first subgroup of the plurality of subgroups, one or more first items from among a plurality of items in the category of items based at least in part on: (a) the profile weights of the profile weighting vector for the first subgroup, and (b) sentiment data comprising a sentiment score for each feature for each of the plurality of items. The sentiment scores for the plurality of features for each of the plurality of items being derived from user-generated post-purchase content about the plurality of items. The method additionally can include displaying the one or more first items for the first subgroup of the plurality of subgroups. Other embodiments of related systems and methods are disclosed.