Utilizing a machine learning model to determine attribution for communication channels

US11538047B2 · kind B2 · utility

Assignee

• ACCENTURE GLOBAL SOLUTIONS LIMITED · IE

Inventors

• Mayank Mishra · Singapore, SG
• Namita Sahu · Mumbai, IN
• Hemant Kumar Sharma · Delhi, IN
• Suchit Malhotra · Gurugram, IN

Key dates

• Filing date: Dec 19, 2019
• Grant date: Dec 27, 2022
• Expiry date: Dec 9, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q30/0242
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

A device may receive customer data, and may identify unique communication channels associated with the customer data. The device may determine, based on the customer data, an optimal order for a Markov chain model, and may determine a model accuracy of the Markov chain model based on the optimal order. The device may transform transitions in the Markov chain model, based on the customer data, to generate transformed transitions, and may process the customer data, with a multi-level indexing model and based on the unique communication channels and the transformed transitions, to generate sparse matrices. The device may determine removal effects and steady state values for the sparse matrices, and may determine attribution weights for the unique communication channels based on the Markov chain model with the optimal order, the removal effects, and the steady state values. The device may perform actions based on the attribution weights.