Machine learning engine for demand-based pricing

US11361335B2 · kind B2 · utility

Assignee

• FAIR IP, LLC · US

Inventors

• Daniel J. Malik · Sierra Madre, US
• Joshua S. Schoenfield · Los Angeles, US
• John M. Case · Wellesley, US
• Scott Painter · Beverly Hills, US

Key dates

• Filing date: Jun 26, 2020
• Grant date: Jun 14, 2022
• Expiry date: Oct 5, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N7/01
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

Systems, methods and products for determining a consumer-facing price using a demand model that is generated based on historical transactional data. One embodiment comprises a method implemented in a pricing module of an automotive data processing system. Data that identifies a consumer (or consumer group) and a vehicle type are received and the demand model is accessed to generate a payment corresponding to the attributes of the consumer and the attributes of the vehicle type. The demand model may be implemented in a machine learning engine that maintains a set of weights β used in a predictive demand function. The weights are adjusted by the machine learning engine to minimize a loss function which measures deviation of demand estimated by the predictive demand function from the demand indicated by a set of historical transaction data.