US 12,189,723 B2
Deep mapping for imputing nulls
Itay Margolin, Pardesiya (IL); and Tomer Handelman, Ramat-Gan (IL)
Assigned to PAYPAL, INC., San Jose, CA (US)
Filed by PAYPAL, INC., San Jose, CA (US)
Filed on Sep. 15, 2023, as Appl. No. 18/468,235.
Application 18/468,235 is a continuation of application No. 17/064,958, filed on Oct. 7, 2020, granted, now 11,797,648.
Prior Publication US 2024/0078292 A1, Mar. 7, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/18 (2019.01); G06F 18/213 (2023.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06N 5/04 (2023.01); G06N 20/20 (2019.01)
CPC G06F 18/24147 (2023.01) [G06F 18/213 (2023.01); G06F 18/2148 (2023.01); G06N 5/04 (2013.01); G06N 20/20 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a non-transitory memory; and
one or more hardware processors coupled with the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
receiving a request to process a transaction associated with a first entity;
accessing a first dataset associated with the first entity,
wherein the first dataset comprises a first data subset obtained from a first data source and a second data subset imputed based on second entity data associated with a second entity determined to be similar to the first entity,
wherein the second entity is determined to be similar to the first entity based on a first vector generated using the first data subset and a second vector generated using a first portion of the second entity data, the first vector and the second vector generated using a machine learning model framework trained to map data subsets associated with a same entity to vectors within a similarity threshold;
determining a risk associated with the first entity based on the first dataset; and
processing the transaction based on the risk.