International Business Machines Corporation

Ford Global Technolgoies, LLC

Rajendra Rao

Vijay Ekambaram

Rajesh Phillips

Puneet Sharma

Manisha Sharma Kohli

John Anthony Lockwood

Randal Henry Visintainer

Methods, systems and computer program products for providing automatic determination of recommended hyper-local data sources and features for use in modeling is provided. Responsive to training each model of a plurality of models, aspects include receiving client data, a use-case description and a selection of hyper-local data sources, generating a client data profile, determining feature importance and generating a use-case profile. Aspects also include generating a feature profile relation graph including client data profile nodes, hyper-local feature nodes and a use-case profile nodes, wherein each hyper-local feature node is associated with one or more client data profile nodes and user-case profile nodes by a respective edge having an associated edge weight. Responsive to receiving a new client data set and a new use-case description, aspects also include determining one or more hyper-local features as suggested hyper-local features for use in building a new model.

Automatic determination of suitable hyper-local data sources and features for modeling

Methods, systems and computer program products for facilitating use of select hyper-local data sets for improved modeling are provided. Aspects include receiving customer data associated with a customer by a workbench platform and determining an accuracy of a customer model using the customer data. For each of a plurality of hyper-local data sets, aspects also include determining an increase in model accuracy based on use of the hyper-local data set and the customer data. Aspects include identifying at least one group of hyper-local data sets of the plurality of hyper-local data sets that result in similar increases in model accuracy. Aspects also include facilitating use of a selected one or more of the hyper-local data sets of the at least one group of hyper-local data sets in generating an improved accuracy customer model.

Facilitating use of select hyper-local data sets for improved modeling

A vehicle bears labels describing handling characteristics of the vehicle for the benefit of autonomous vehicles in proximity to the vehicle. The labels may be nonvisible, such as through use of UV or IR inks. The labels may be present such that they are visible regardless of view direction and may be affixed using a vehicle wrap applied to panels of the vehicle. Autonomous vehicles detect the labels and retrieve handling characteristics from a local database or a remote server. The autonomous vehicles are therefore relieved from the processing required to predict or infer the handling characteristics of the vehicle.

Vehicle classification system

Growing community of inventors

Los Gatos, CA, United States of America

Rajendra Rao