Patents by Inventor Danut Prisacaru

Danut Prisacaru has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12737735
    Abstract: This disclosure describes a system and method for classifying transactions including receiving a plurality of transactions associated with a user, vectorizing the plurality of transactions, and providing the vectorized transactions to a machine learning model trained to identify one or more reportable transaction to one or more third party servers. The machine learning model includes one or more sub-models. The output of the machine learning model is obtained and represents a subset of the vectorized plurality of transactions that are reportable transactions. A recommendation is generated based on the reportable transactions. Data is provided to a user device to be rendered by the user device which will display the recommendation. Upon receiving an instruction from the user device, the particular reportable transaction is reported to a third-party server.
    Type: Grant
    Filed: October 30, 2023
    Date of Patent: September 15, 2026
    Assignee: Self Financial, Inc.
    Inventors: Cary Penniman, Massoud Masir, Qiaochu Tang, Hani AbuGhazaleh, Danut Prisacaru, Drew Bullard, Kelvin Pho
  • Publication number: 20250139594
    Abstract: This disclosure describes a system and method for classifying transactions including receiving a plurality of transactions associated with a user, vectorizing the plurality of transactions, and providing the vectorized transactions to a machine learning model trained to identify one or more reportable transaction to one or more third party servers. The machine learning model includes one or more sub-models. The output of the machine learning model is obtained and represents a subset of the vectorized plurality of transactions that are reportable transactions. A recommendation is generated based on the reportable transactions. Data is provided to a user device to be rendered by the user device which will display the recommendation. Upon receiving an instruction from the user device, the particular reportable transaction is reported to a third-party server.
    Type: Application
    Filed: October 30, 2023
    Publication date: May 1, 2025
    Inventors: Cary Penniman, Massoud Masir, Qiaochu Tang, Hani AbuGhazaleh, Danut Prisacaru, Drew Bullard, Kelvin Pho