Inferring consumer affinities based on shopping behaviors with unsupervised machine learning models
Abstract:
A process of discovering psychographic segments of consumers with unsupervised machine learning. A first set of consumer-behavior is converted into respective consumer-behavior vectors for training an unsupervised machine learning model. The unsupervised machine learning model is trained with the first set of consumer-behavior vectors to determine psychographic segments of consumers. A second set of consumer-behavior records is obtained after determining the psychographic segments of consumers and the second set of consumer-behavior records is converted into respective consumer-behavior vectors. The second set of consumer-behavior vectors is classified as each belonging to at least a respective one of psychographic segments with the trained machine learning model to predict, based on the classification, a likelihood of the respective consumer engaging in behavior associated with a corresponding one of the psychographic segments.
Information query
Patent Agency Ranking
0/0