7th June, 2019
Ai Editorial: CyberSource has highlighted that effective fraud management requires the careful balance of three interdependent dimensions, reports Ai’s Ritesh Gupta
Payment and fraud executives have to be crafty enough to ensure that genuine customers aren’t denied an opportunity to complete a transaction or even face hiccups with added friction. At the same time, merchants can’t afford to be a victim of fraud owing to weak authentication or fraud prevention mechanism.
CyberSource ( https://www.cybersource.com/), in its latest report – the 2019 Global eCommerce Fraud Management Report Asia Pacific Edition, has highlighted that effective fraud management requires the careful balance of three interdependent dimensions –
· Delivering a positive experience for genuine customers and maximising the acceptance of genuine orders - The balancing act, as highlighted by Ai previously, is about being proficient in validating a buyer and such verification shouldn’t interrupt the manner in which they interact and transact with a business. Merchants need to look at new regulations, what sort of action is required and its impact on the user experience, and also the flexibility of consumes when it comes to additional measures that are being taken for authentication. One way to differentiate between transactions is the risk associated with them.
· Accurately detecting and rejecting fraudulent orders to minimise fraud losses - Merchants need to leverage the prowess of data-driven, artificial-intelligence powered offerings for combatting fraud. Rules-based systems are in general reactive and probabilistic solutions, which is why they are unable to prevent fraud before it happens. Rather than using a blanket rule that forces every user to login with 2FA, real-time surveillance can be used to assess logins in the background, and only logins with borderline risks expected to go through 2FA. Merchants should still develop their own fraud tools that are able to tap on their own sources of data for greater efficiency and more accurate detection of fraud.
Real-time machine learning can help against blanket blacklists and whitelists by focusing on the customer’s behaviour instead. It works with real-time live data collected on the merchant’s website, where the system trains itself with each incoming transactions to identify fraud patterns instead. Deploying a multidisciplinary approach combining different technologies - both supervised and unsupervised machine learning - would better equip merchants for fraud management. Unsupervised machine learning can be used to learn on the fly and identify fraudulent patterns even without having been trained with historical data, i.e. able to identify unknown fraud attacks. Thereafter, predictive analytics may still be used to run the probabilities of fraud, giving a risk score.
CyberSource indicated that in particular, enterprise organisations tend to more proactive with their fraud strategies because the financial and reputational ramifications of fraud can be far reaching.
· Efficiently managing the operational costs of fraud management activities – The report also shared that as in other regions, minimising operational costs is generally a lower priority for businesses in Asia Pacific.
The report also highlights that it takes “constant recalibration and fine-tuning of fraud management controls and processes to keep achieving the best balance”.
6 characteristics of the masters of balance, according CyberSource:
1. Have a lower chargeback rate
2. Are more likely to rate ecommerce fraud management as extremely important to their business strategy
3. Find it less challenging to respond to emerging fraud attacks
4. Have a greater range of capabilities that give them agility to respond to the dynamic landscape they operate in
5. Have a greater capability to use data effectively for fraud management
6. Are less likely to conduct manual review, and spend less in this area
Hear from senior executives about the balancing act at the 8th Annual ATPS Asia-Pacific to be held in Penang, Malaysia (27-29 August, 2019).
Click here for more information
Follow Ai on Twitter: @Ai_Connects_Us