Loading...
Search results:


November 8, 2016

How is big data used to identify credit card frauds?

How is big data used to identify credit card frauds?

Big data, which I refer to as data-driven decision making [1], is used in each of the three functions of fraud prevention, i.e., automated screening, manual verifications, and chargeback management [2].

With automated screening, i.e., the process of testing payments automatically against whitelists, blacklists, force-review rules, and scoring algorithms, big data is used to perform the following tasks:

1. identify the most important drivers of payment fraud [3];

2. calculate the relative importance of each risk factor [4]; and

3. review the performance of all those models [5].

With manual verification, i.e., the process of manually reviewing payments for possible fraud, big data is used to perform the following tasks:

4. explore custom risk reports [6];

5. make data-driven arbitrage decisions [1]; and

6. audit the performance of manual verifications retrospectively [7].

Finally, with chargeback management, i.e., the process of reviewing who is liable for chargebacks (e.g., the issuing bank, the merchant, the cardholder, see “liability” [8]), big data is used to perform the following tasks:

7. retrieve and review related cases of payment fraud; and

8. build a defense for the chargeback case based on past cases.

Fabrice

References

[1] Harvard Business Review on Making Smart Decisions (Harvard Business Review Paperback Series): Harvard Business Review: 9781422172391: Amazon.com: Books

[2] Chargeback - Wikipedia

[3] Feature selection - Wikipedia

[4] Calibration (statistics) - Wikipedia

[5] Model selection - Wikipedia

[6] Exploratory data analysis - Wikipedia

[7] Verification and validation of computer simulation models - Wikipedia

[8] EMV - Wikipedia