Mercedes-Benz Group Ag

Legion Technologies, Inc.

Yahya Sowti Khiabani

Sanish Mondkar

Gopal Sundaram

Dat Nguyen

Charles Furrer

Thomas Joseph

Chieh Hsu

Disclosed are a system, method and system to predict an individual's action in connection with a vehicle user interface using machine learning. One or more models may be developed based, at least in part, on observations of past actions by the individual among the plurality of target actions by the individual. Extracted features of a current context may be applied to the developed one or more models to predict a subsequent action among the target actions by the individual.

System and/or method for predicting user action in connection with a vehicle user interface using machine learning

A machine learning system for forecasting demand implements an improved process using event streams for predicting the impact that events in the geographic area surrounding an establishment have on demand forecasts for the establishment. A range of distances from the establishment can be determined and divided up into different distances. Event streams can be generated from the events by grouping the events into combinations of event attributes, such as event category and the distance of the event from the establishment. The event streams can be provided as inputs along with demand data for computing demand forecasts that account for increased or decreased traffic patterns in the geographic area surrounding the event. The event streams can be filtered based on the magnitude of the impact the events have on the demand for the products and/or services of the establishment before, during and after the event takes place.

Event streams in a machine learning system for demand forecasting

Growing community of inventors

Fremont, CA, United States of America

Yahya Sowti Khiabani