US 12,294,601 B2
Detection of anomalous behavior on online platforms using machine learning techniques
Tanuj Arcot Omkar, Cedar Park, TX (US); Rodrigo de Souza Scorsatto, Porto Alegre (BR); Aravind Reddy Lakkadi, Flower Mound, TX (US); Jonathan Leventis, College Station, TX (US); Kasey Mallette, Las Vegas, NV (US); Vinicius Facco Rodrigues, Sao Paulo (BR); Rodrigo da Rosa Righi, São Leopoldo (BR); Lucas Micol Policarpo, São Leopoldo (BR); Thaynã da Silva França, São Leopoldo (BR); Jorge Luis Victória Barbosa, São Leopoldo (BR); Rodolfo Stoffel Antunes, São Leopoldo (BR); and Cristiano André da Costa, São Leopoldo (BR)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Jun. 16, 2023, as Appl. No. 18/336,594.
Prior Publication US 2024/0422184 A1, Dec. 19, 2024
Int. Cl. H04L 9/40 (2022.01); H04L 67/1396 (2022.01)
CPC H04L 63/1425 (2013.01) [H04L 63/10 (2013.01); H04L 67/1396 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining a set of machine learning models configured to detect at least one type of anomalous behavior associated with one or more users interacting with an online platform;
performing an incremental machine learning process on one or more of the machine learning models in the set, wherein the incremental machine learning process comprises: (i) obtaining data related to interactions of the one or more users with the online platform, (ii) updating at least one machine learning model from the set of machine learning models based on at least a portion of the obtained data, (iii) comparing performance metrics determined for respective ones of the machine learning models in the set, and (iv) selecting one of the machine learning models from the set to be used by the online platform based at least in part on a result of the comparing;
determining, utilizing the selected machine learning model, that a given user is exhibiting the at least one type of anomalous behavior on the online platform; and
initiating one or more automated actions on the online platform to at least partially mitigate the anomalous behavior of the given user;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.