A major technology firm asked us to measure friendly fraud (aka chargeback fraud) risk. Friendly fraud occurs when an individual purchases online via their credit or debit card and then requests a chargeback from the bank once the goods or services have been consumed. A completed chargeback cancels the original transaction and refunds the individual, and the merchant is held accountable regardless of the measures taken to verify the transaction.

Purpose of the Study.

The purpose of this study was to predict the customers who are most likely to request a chargeback.

Approach.

We developed an analytical algorithm and data modeling set to:

1)      identify the traits, signals, patterns of the customers who are most likely to do request a chargeback

2)      predict the customers who are most likely to request a chargeback and when

Solution.

The analytic algorithms and data modeling allowed our clients to:

1)      feed newly subscribed customer data and purchasing information into the data models and analytical algorithms to produce a prediction result for each new customer

2)      show the prediction result as a report (CSV, Excel) on the likelihood of chargeback behavior based on:

a.       subscriber information

b.      date of the first purchase

c.       chargeback timeline: date or days after the first purchase

d.      confidence level

e.      the identified traits, signals, and patterns for the chargeback behavior

Upon the completion of the project, we provided:

1)      analytical algorithm software module(s) in Python

2)      data modeling module(s) in Python

3)      a simple software application for us to feed the new data into the algorithms and data models for generating the prediction results described above.