fraud prevention, fraud, cybersecurity

Worldline: Taking a Combined Approach to Defeat Payment Fraudsters

Fraud across the world has risen exponentially as the growth of digital has created many new paths for fraudsters to exploit. While there have been some great technological developments to keep businesses safe, if payments fraud’s current trajectory is maintained, by 2027, fraudulent transactions will amount to over $38billion.

So what can be done? We heard from Panteha Pedram, the director of risk operations and products at Worldline, about what she believed needed to be done. Pedram is responsible for building and deploying innovative risk management solutions at Worldline as well as preventing risks associated with fraud, money laundering, and terrorist financing on the operational level. In her role, she evangelises and guides cross-functional teams toward delivering integrated risk products and solutions that Worldline merchants will love.

Wearing dual hats, she also manages the global fraud risk management and AML/CTF monitoring teams at Worldline acquiring and PSP entities.

With more than 12 years of experience in managing different teams in the different areas of risk management, she is also pursuing her PhD in Financial Risk management and had been a member of the European Supervisory Board of MRC.

Speaking to The Fintech Times, Pedram explained how there was not a singular approach that could be taken to tackling payments fraud, but rather, a combined approach where new tech meets old fraud prevention methods.

Panteha Pedram, the director of risk operations and products at Worldline
Panteha Pedram, director of risk operations and products at Worldline

Over the past few years, e-commerce has flourished across the globe – but payment fraud has grown commensurately as fraudsters look for ever more sophisticated methods of ‘cashing in’. In fact, global fraudulent transactions are set to amount to $38.5billion a year by 2027, according to Statista, and online payments fraud will remain a long term, significant and expanding issue.

Online merchants looking to implement successful fraud prevention practices and counter theft measures need to be aware of the ever-increasing sophistication of their fraudulent foes. The challenges they face can vary enormously by sector and territory and each merchant needs to work closely with a solution provider, or fraud prevention partner that best understands the relevant market idiosyncrasies and demonstrates the expertise to address and overcome these variables. Likewise, it is imperative that fraud management practices and solutions evolve ahead of the tactics used by fraudsters.

In recent years, machine-learning (ML) tools have started to supersede the more traditional static rule-based solutions (While each methodology has its advantages, deployed in unison they have an even greater possibility of succeeding in their purpose).

To meet the challenges presented by today’s increasingly sophisticated fraudsters, the optimal solution tends to use a ‘hybrid’ approach. This offers businesses the best of both worlds, allowing them to retain a certain level of control offered through the more traditional fraud protection solutions while enabling them to harness the power of data through the scientific advances of machine learning models.

While concepts such as “hybrid” can include a wide range of characteristics, when it comes to fraud prevention, a successful hybrid model has its very own formula.

A successful system should allow for easy configuration to fulfill the unique requirements of any market vertical in which the merchant operates now and in the future. It should also be more cost-effective as more advanced, inbuilt machine learning capabilities reduce the requirement for manual reviews. Any hybrid solution equally needs to overcome any other common shortcomings of any legacy solution. This includes those presented by the inability of one system to operate seamlessly and successfully in every geography – or having to be expensively recalibrated to address multiple regional complications.

Early identification of fraudulent transactions is both important and challenging, particularly when trying to maintain the right balance between maximising legitimate orders and weeding out the others. A hybrid solution should help provide this delicate balance of detecting fraud patterns and recognising good customers. Having the knowledge of fraud patterns associated with each business vertical and geographical market – which can be a linear outcome of the market coverage and diversity in profile of a payment solution provider or a fraud prevention partner – can help with fine-tuning the system to deliver that delicate balance from the day one.

Such an ideal hybrid solution would also require a significant level of sophistication to be able to combine the best of both methodologies – namely the static rules and ML model – in a single entity. It would encompass the combination of data, knowledge, and science, as well as the technical sophistication required to ensure the rules work. As time evolves, the data science element will take on a growing importance, ensuring the longer-term success and longevity of the solution. Likewise, any truly valuable solution should offer multiple models which can be applied and customised ubiquitously to each merchant’s very distinct requirements, i.e. it is not a “one size fits all” solution but rather a “bespoke to the merchant” system.

Critically, any viable solution needs to be future-proofed to ensure it stays up to date with technological innovations and can overcome the challenges posed by increasingly sophisticated fraud methodologies too.

A hybrid solution offers a much more efficacious deterrent, benefitting as it does from being able to learn and adapt to the ever-changing fraud patterns as well as being tailored to an individual organisation’s specific requirements. Any global e-commerce merchant, wishing to augment the revenue impact of their current fraud management systems, would benefit from implementing a next generation of hybrid fraud management solution that combines rules and machine learning together with the most comprehensively available dataset, to increase accuracy and efficiency beyond what rules or advanced machine learning alone could achieve. If your payment solution provider or fraud prevention partner can also offer dedicated expertise to make such a system bespoke to your unique requirements, congratulations, you have found the ideal partner.


Related posts

Webinar Review: How Can We Use Fintech to Make Banking More Ethical

The Fintech Times

Fintech, ABI: Italian banks are working on blockchain pilot

Manisha Patel

Grab, DTI and Mayani Collaborate to Help Filipino Farmers Go Digital

Polly Jean Harrison