AUTHENTICATED CUSTOMIZATION OF MACHINE-LEARNING MODELS

Organization Name

Oracle International Corporation

Inventor(s)

Shashi Prasad Suravarapu of San Ramon CA US

Amitabh Saikia of Mountain View CA US

Srinivasa Phani Kumar Gadde of Fremont CA US

Diego Andres Cornejo Barra of Chicago IL US

Cody Nicholas Maheu of Nashua NH US

Yuanxu Wu of Sunnyvale CA US

Laukik Satish Mujumdar of Bellevue WA US

Daniel Bruce Carter of Redmond WA US

Zachary Jon-Christian Medeck of Kent WA US

Jobinesh Purushothaman Manakkattil of Foster City CA US

Sangeet Dahal of Modesto CA US

Shweta Shyamsunder Gupta of Covington WA US

AUTHENTICATED CUSTOMIZATION OF MACHINE-LEARNING MODELS

This abstract first appeared for US patent application 18883407 titled 'AUTHENTICATED CUSTOMIZATION OF MACHINE-LEARNING MODELS

Original Abstract Submitted

Techniques are disclosed for providing an authenticated model customization for a machine-learning model. A cloud service provider platform accesses a message including, at least, timestamp data and user identification data. A training group of data entities is identified based on the data in the message. A training dataset is determined based on the training group of data entities. A machine-learning model is modified based on the training dataset. The modified machine-learning model is provided during an authenticated network session associated with the user identification data. In some embodiments, the modification of the machine-learning model is removed based on a determination that the authenticated network session had ended.