Browse Prior Art Database

Method to estimate the net-worth of a person based on only credit card transactions

IP.com Disclosure Number: IPCOM000245206D
Publication Date: 2016-Feb-18
Document File: 3 page(s) / 80K

Publishing Venue

The IP.com Prior Art Database

Abstract

Banks would like to estimate various financial indicators of a person in order to suggest their products to the person. However, they may not have all the data to estimate these parameters mainly because banks may not own the primary transaction account of their customer. This method would help banks to estimate the financial indicators of the person with only credit card transaction information.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 3

Method to estimate the net-worth of a person based on only credit card transactions

Detailed Description


Motivation
Banks would like to estimate the financial indicators of a person in order to suggest their products to the person. The financial indicators could include net in-flow and out-flow of money into the account, credit worthiness, net worthiness, risk appetite, etc. Banks typically need to have salary accounts of the person to accurately estimate the financial indicators of the person. Banks interact with customers that may not have salary accounts with them. A large percentage of accounts in a bank are non-salary. And, a large percentage of customers use products like credit cards, loans who may not have salary account with the bank. The main disclosure idea is to use other transactions to estimate the financial indicators of the customers who may not have salary account with the bank.

The Method


The proposed method is a two steps process.

Step 1 is the model building. This step considers the other (credit card, loan, …) transactions of salary account holders whose financial indicators are known. It builds a machine learning models that map other transactions to financial indicators as shown in Figure 1.

Figure 1 Building machine learning model that maps other transactions to financial indicators.

Step 2 estimates the financial indicators of a person. This includes extraction of the other transactions of holders whose financial indicators needs to be estimated. Then, it uses the model in Step 1 to estimate financial indicators from other transactions as shown in Figure 2.

Figure 2 Estimating the financial indicators using machine learning model.

1


Page 02...