Clickstream purchase prediction using Hidden Markov Models

US11042898B2 · kind B2 · utility

Assignee

• Staples, Inc. · US

Inventors

• Courosh Mehanian · Mountain View, US
• Tchavdar Dangaltchev · Bellevue, US
• Karthik Kumara · Santa Clara, US
• Jing Pan · San Jose, US
• Timothy Wee · San Mateo, US

Key dates

• Filing date: Dec 23, 2014
• Grant date: Jun 22, 2021
• Expiry date: Oct 15, 2037

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q30/0254
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

Technology for predicting online user shopping behavior, such as whether a user will purchase a product, is described. An example method includes receiving current session data describing a current session for a current user, extracting a current clickstream from the current session data classifying the current clickstream as a purchase clickstream or a non-purchase clickstream by processing the current clickstream using one or more sets of Hidden Markov Model parameters produced by one or more Hidden Markov Models, and computing, using the one or more computing devices, a purchase probability that the current user will purchase a product during the current session based on the classifying.