Solving sparse data problems in a recommendation system with freezing start

US12430678B2 · kind B2 · utility

Assignee

• SAP SE · DE

Inventors

• Nick Pendar · San Ramon, US
• Seyed Farhad Faghihi · Vancouver, CA

Key dates

• Filing date: Dec 16, 2022
• Grant date: Sep 30, 2025
• Expiry date: May 12, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q30/0202
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

Recommendation services typically struggle with sparse data scenarios. A freezing generated item start technique can use a matrix of external generated items to find a linking generated item. Embeddings can be used to determine distance between items. The technologies are useful for providing recommendations even in scenarios involving little or no transaction data.