US Patent Application 17824555. MACHINE LEARNING-BASED DETECTION OF POTENTIALLY MALICIOUS BEHAVIOR ON AN E-COMMERCE PLATFORM simplified abstract

MACHINE LEARNING-BASED DETECTION OF POTENTIALLY MALICIOUS BEHAVIOR ON AN E-COMMERCE PLATFORM

Organization Name

Dell Products L.P.

Inventor(s)

Tanuj Arcot Omkar of Cedar Park TX (US)

Rodrigo de Souza Scorsatto of Porto Alegre (BR)

Rodrigo da Rosa Righi of São Leopoldo (BR)

Lucas Micol Policarpo of São Leopoldo (BR)

Vinicius Facco Rodrigues of São Leopoldo (BR)

Jorge Luis Victória Barbosa of São Leopoldo (BR)

Rodolfo Stoffel Antunes of São Leopoldo (BR)

Cristiano André Da Costa of São Leopoldo (BR)

MACHINE LEARNING-BASED DETECTION OF POTENTIALLY MALICIOUS BEHAVIOR ON AN E-COMMERCE PLATFORM - A simplified explanation of the abstract

This abstract first appeared for US patent application 17824555 titled 'MACHINE LEARNING-BASED DETECTION OF POTENTIALLY MALICIOUS BEHAVIOR ON AN E-COMMERCE PLATFORM

Simplified Explanation

This patent application describes an apparatus that uses machine learning models to detect and prevent potentially malicious behavior on an e-commerce platform. Here are the key points:

• The apparatus monitors events associated with users interacting with the e-commerce platform.
• It identifies the type of event associated with each user.
• Based on the event type, it selects a machine learning model that can characterize different types of potentially malicious behavior.
• Using the selected model, it determines whether the user is exhibiting any potentially malicious behavior.
• If malicious behavior is detected, the apparatus takes actions to prevent or mitigate the effects of that behavior.

Original Abstract Submitted

An apparatus comprises a processing device configured to monitor for events associated with users interacting with an e-commerce platform, to identify an event type of a given event associated with a given user interacting with the e-commerce platform, and to select, based on the identified event type, at least one of a plurality of machine learning models configured to characterize different types of potentially malicious behavior on the e-commerce platform. The processing device is also configured to determine, utilizing the selected at least one machine learning model, whether the given user is exhibiting at least one of the different types of potentially malicious behavior. The processing device is also configured, responsive to determining that the given user is exhibiting at least one of the different types of potentially malicious behavior, to initiate actions on the e-commerce platform to prevent or mitigate an effect of the potentially malicious behavior.