Automatic control group generation

Patent metadata

Field	Value
Publication number	US-12535781-B2
Application number	US-202117644692-A
Country	US
Kind code	B2
Filing date	Dec 16, 2021
Priority date	Dec 16, 2021
Publication date	Jan 27, 2026
Grant date	Jan 27, 2026

Abstract

Techniques are disclosed for automatically generating and updating a control group. In disclosed techniques, a server computer system trains, using a plurality of transactions, a machine learning model. During training the machine learning model learns a feature distribution of both a current set of control group (CG) transactions and a current set of non-control group (non-CG) transactions included in the plurality of transactions. The system inputs the current set of CG transactions into the trained machine learning model. Based on the output of the trained machine learning model for the current set of CG transactions, the system modifies the current set of CG transactions to generate an updated set of CG transactions. Based on the updated set of CG transactions, the server performs one or more preventative measures for a transaction processing system. The disclosed techniques may advantageously improve the accuracy e.g., of a transaction processing system.

First claim

What is claimed is:

1 . A method, comprising:
training, by a server computer system using a plurality of transactions, a machine learning model, wherein during training the server computer system:
causes a first portion of the machine learning model to learn a feature distribution of a current set of control group (CG) transactions;
causes a second portion of the machine learning model to learn a feature distribution of a current set of non-control group (non-CG) transactions included in the plurality of transactions; and
concatenates output of a third portion of the machine learning model indicating classifications for CG transactions to transactions input to a portion of the machine learning model for reconstructing CG transactions; and
inputting, by the server computer system into the trained machine learning model, the current set of CG transactions; modifying, by the server computer system based on output of the trained machine learning model for the current set of CG transactions, the current set of CG transactions to generate an updated set of CG transactions; and performing, by the server computer system based on the updated set of CG transactions, one or more preventative measures for a transaction processing system.

2 . The method of claim 1 , wherein further during training, the machine learning model predicts, based on a predetermined weight associated with a particular transaction feature, whether transactions included in the plurality of transactions are to be included in the current set of CG transactions or the current set of non-CG transactions.

3 . The method of claim 2 , wherein the inputting includes inputting the current set of CG transactions into a non-CG portion of the machine learning model, and wherein the current set of CG transactions predicted by the machine learning model during training are predicted by a CG portion of the machine learning model.

4 . The method of claim 2 , wherein predicting whether transactions included in the plurality of transactions are CG transactions or non-CG transactions is further based on one or more predefined weights for one or more transactions included in the plurality of transactions.

5 . The method of claim 2 , wherein training the machine learning model further includes:
concatenating output of the third portion of the machine learning model indicating classifications for non-CG transactions to transactions input to a portion of the machine learning model for reconstructing non-CG transactions.

6 . The method of claim 1 , wherein performing the one or more preventative measures includes:
training, using the updated set of CG transactions, a machine learning classifier, wherein the trained machine learning classifier is usable to generate an authorization decision for newly requested transactions.

7 . The method of claim 1 , wherein the machine learning model is a Dragonnet model, wherein the first portion of the Dragonnet model is a CG portion and the second portion of the Dragonnet model is a non-CG portion, wherein the CG portion and the non-CG portion of the Dragonnet model are executed using variational auto encoders (VAEs), and wherein the third portion of the Dragonnet model classifies transactions.

8 . The method of claim 7 , wherein modifying the current set of CG transactions includes:
determining reconstruction error of the non-CG portion of the Dragonnet model by comparing reconstructions of CG transactions output by the non-CG portion with corresponding CG transactions; and removing, based on the reconstruction error, one or more CG transactions from the current set of CG transactions to generate the updated set of CG transactions.

9 . The method of claim 1 , wherein the machine learning model includes: a branch for reconstructing non-suspicious CG transactions, a branch for reconstructing suspicious CG transactions, a branch for reconstructing non-suspicious non-CG transactions, and a branch for reconstructing suspicious non-CG transactions.

10 . A non-transitory computer-readable medium having instructions stored thereon that are executable by a server computer device to perform operations comprising:
training, using a plurality of transactions, a machine learning model, wherein during training the machine learning model:
learns a feature distribution of both a current set of control group (CG) transactions and a current set of non-control group (non-CG) transactions included in the plurality of transactions; and
concatenates output of a portion of the machine learning model indicating classifications for non-CG transactions to transactions input to a portion of the machine learning model for reconstructing non-CG transactions; and
inputting, into the trained machine learning model, the current set of CG transactions; modifying, based on output of the trained machine learning model for the current set of CG transactions, the current set of CG transactions to generate an updated set of CG transactions; and performing, based on the updated set of CG transactions, one or more preventative measures for a transaction processing system configured to process newly received transactions.

11 . The non-transitory computer-readable medium of claim 10 , wherein further during training the machine learning model predicts, based on a predetermined weight associated with a particular transaction feature, whether transactions included in the plurality of transactions are to be included in the current set of CG transactions or the current set of non-CG transactions.

12 . The non-transitory computer-readable medium of claim 11 , wherein predicting whether transactions included in the plurality of transactions are CG transactions or non-CG transactions is further based on one or more predefined weights for one or more transactions included in the plurality of transactions.

13 . The non-transitory computer-readable medium of claim 10 , wherein the inputting includes inputting the current set of CG transactions into a non-CG portion of the machine learning model, and wherein the current set of CG transactions predicted by the machine learning model during training are predicted by a CG portion of the machine learning model.

14 . The non-transitory computer-readable medium of claim 13 , wherein modifying the current set of CG transactions includes:
determining reconstruction error of the non-CG portion of the machine learning model by comparing reconstructions of CG transactions output by the non-CG portion with corresponding CG transactions; and removing, based on the reconstruction error, one or more CG transactions from the current set of CG transactions to generate the updated set of CG transactions.

15 . The non-transitory computer-readable medium of claim 14 , wherein modifying the current set of CG transactions based on output of the non-CG portion of the machine learning model further includes:
performing a first comparison using a divergence algorithm, including comparing transactions in the current set of CG transactions with non-CG transactions included in the plurality of transactions; performing a second comparison using the divergence algorithm, wherein performing the divergence algorithm includes comparing transactions in the updated set of CG transactions with non-CG transactions included in the plurality of transactions; comparing results of the first comparison and the second comparison; and based on comparing the results, adding one or more non-CG transactions to the updated set of CG transactions.

16 . The non-transitory computer-readable medium of claim 10 , where

Assignees

• Paypal Inc

Inventors

• Sharma Nitin S
• Rouhsedaghat Mozhdeh

Classifications

• G06Q20/4016

  involving fraud or risk level assessment in transaction processing · CPC title

• G06N3/088 Primary

  Non-supervised learning, e.g. competitive learning · CPC title

• G05B13/027 Primary

  using neural networks only · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title