US 12,346,942 B2
Asset-exchange feedback in an asset-exchange platform
Mark Zhao, San Francisco, CA (US); Ashish Dhaka, San Francisco, CA (US); Jingtian Wei, San Francisco, CA (US); and Bharanidharan Ganesan, San Francisco, CA (US)
Assigned to LendingClub Bank, National Association, Lehi, UT (US)
Filed by LendingClub Bank, National Association, Lehi, UT (US)
Filed on Oct. 4, 2022, as Appl. No. 17/960,048.
Prior Publication US 2024/0112230 A1, Apr. 4, 2024
Int. Cl. G06Q 30/0283 (2023.01); G06N 20/20 (2019.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0283 (2013.01) [G06N 20/20 (2019.01); G06Q 30/0601 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, in a data processing system comprising one or more processors and one or more memories, the one or more memories comprising instructions executed by the one or more processors to cause the one or more processors to implement an asset-exchange feedback system for performing asset-exchange feedback operations, the method comprising:
collecting historical asset-listing data from an asset-exchange platform, the historical asset-listing data comprising, for each asset listing of a plurality of previous asset listings, a plurality of asset-listing attributes and a result of the asset listing;
using the collected historical asset-listing data, training a first machine learning model to output attribute-importance scores, wherein each attribute-importance score:
corresponds to a respective asset-listing attribute in the plurality of asset-listing attributes, and
indicates an importance of the respective asset-listing attribute to one or more offerees participating in the asset-exchange platform;
training a second machine learning model to categorize asset listings into one or more predefined categories based on the historical asset-listing data and a set of asset-listing attributes;
training a third machine learning model to predict asset-listing outcomes based on the historical asset-listing data and the set of asset-listing attributes;
after training the first machine learning model:
using the first machine learning model to output, based on a set of input attributes, a first set of attribute-importance scores, wherein each attribute-importance score in the first set of attribute-importance scores indicates an importance of the respective asset-listing attribute to a specified group of one or more offerees; and
combining outputs of the first machine learning model, the second machine learning model, and the third machine learning model to generate feedback for optimizing the set of input attributes;
based on the first set of attribute-importance scores and the feedback generated from the combined outputs of the first, second, and third machine learning models, performing an asset-exchange feedback operation.