By Anna Lykourina, EMEA Fraud Analytics Expert at SAS

In the past, the fight against fraud has been a bit hit-and-miss. It has relied on auditors to identify patterns of behaviour that just didn’t quite fit. They often only detected problems months after the event. And then organisations had to claw back stolen funds through legal processes.

In a world where transactions happen in under a second, however, this is no longer acceptable. We need to be able to detect fraud immediately, if not before it happens. Customers want safe and protected data that is not vulnerable to identity theft through company systems. But they still want to be able to pay online and in seconds. The stakes are high, but fortunately new tools and techniques in fraud analytics are enabling companies to stay ahead of fraud.

Trusting machines to do the work

Machines are much better than humans at processing large data sets. They are able to examine large numbers of transactions and recognise thousands of fraud patterns instead of the few captured by creating rules. On the other hand, fraudsters have become adept at finding loopholes. Whatever rules you set, it is likely that they will be able to get ahead of them. But what if your system was able to think for itself, at least to a certain extent?

New approaches to fraud prevention combine rules-based systems with machine learning and artificial intelligence-based fraud detection systems. These hybrid systems are able to detect and recognise thousands of fraud patterns and learn from the data. Automated analytical-based fraud detection systems can reveal novel fraud patterns and identify organised crime more consistently, efficiently and quickly. This makes them a good investment for businesses across a wide range of sectors, including public sector, insurance, banking, and even healthcare or telecommunications.

How, though, can you harness analytics as a tool in your fight against fraud?

Identifying needs and solutions

The first step is to identify which options you need. Probably the best way to do this is through a series of company-wide workshops with the fraud analytics experts to determine what analytics you need, which data to include and techniques to use, and what results to report. They can also identify the ideal combination of rules-based and AI/ML approaches to detect fraud as early as possible.

Companies looking towards advanced analytics for fraud detection will need to make a number of decisions. They will need to optimise existing scenario threshold tuning, explore big data, develop and interpret machine learning models for fraud, discover relevant information in text data, and prioritise and auto-route alerts. There may be industry-specific decisions to make, too, such as automating damage analysis through image recognition in the insurance sector. By automating these areas, companies can both significantly reduce human effort – reducing costs – and improve their fraud detection and prevention.

Benefits of an analytical approach to fraud detection and prevention

Companies that are already using an analytical approach for fraud prevention have reported several important benefits. First, the quality of referrals for further investigation is better. Investigators also have a much clearer idea of why the referral has been made, which improves the efficiency of investigation. Analytics also improves investigation efficiency by reducing the number of both false positives (that is, alerts that turn out not to be fraud) and false negatives (failure to spot actual frauds). This improves customer experience and reduces risk to the company.

Analytics makes it possible to uncover complex or organised fraud that rules-based systems would miss. Companies can group together customers and accounts with similar behaviors, and then set risk-based thresholds appropriate for each scenario.

There are several sector-specific benefits too. For example, insurance firms can identify fraudulent claims faster to prevent improper payments from going out. Claims investigation is likely to be more consistent because claims are scored through technology, algorithms and analytics, rather than by people. Finally, it becomes possible to shorten the claims process through automated damage analysis. It is no wonder that organizations across a wide range of sectors are placing analytics at the heart of their anti-fraud strategy.

Jason Pugh, Managing Director, D2 Legal Technology

The derivatives industry has been transformed by the proactive engagement of its members over the last 30+ years, an exemplar of bright, resourceful individuals coming together to achieve business outcomes that benefit the industry as a whole. From pioneering the master agreement, the eye-catching creation of protocols, to harmonisation of business process through the likes of FpML, the industry has constantly evolved.

Today, the industry is facing new challenges and while many will consider, correctly, that the proliferation of global and regional regulations since the financial crisis has both been challenging and led to unintended consequences, there is an even more stark reality that players in this market need to consider, i.e. surviving in a disrupted universe.

Jason Pugh, Managing Director, D2 Legal Technology, outlines the potential that can be achieved by enhancing legal data standards and how that this is an essential precondition to fundamentally transforming the operating environment through technology.

We all witness the impact of Uber and Amazon in every walk of life which has extended client expectations. We all know that as clients appreciate and come to expect these new capabilities and services, disrupted technology will not be put back into the bottle.

Similarly, clients in the financial services industry rightly expect more for less. It may also be less complex than we fear – the industry is, after all, not as unique as it likes to think and a vast proportion of our business can be commoditised.

The critical challenge for the industry is therefore to transform itself into a cheaper and better risk managed operation that achieves the twin goals of client satisfaction and regulatory compliance – this means simplification, the current framework is too complex comprising too many disparate processes pieced together in a makeshift manner.

The correlation between better client service, better risk management/compliance and cost efficiency is high when viewed through the prism of effective front to back processes. This is the challenge the industry faces, and the good news is that many of the strands are already being developed; the challenge is to bring them together.

The journey so far

Over these last decades, ISDA has worked with its members and market participants to produce and maintain a documentation framework. It has constantly responded to market changes and this has led to an evolution of its suite of documentation especially with the development of the ISDA Master Agreement and associated documentation, such as various annexes, definitional booklets and protocols. This framework has provided important legal certainty, clarity and efficiency for market participants and critically transformed the credit risk profile of trading entities through the concept of close-out netting.

In recent years, the number of standard form documents and their complexity has proliferated often in response to regulatory requirements. Many of the core terms have remained constant, yet there has been an ever-increasing number of variants in the specific clauses used within the documentation framework, increasing the time taken for negotiation and onboarding of new client relationships.  These increased variances have different commercial and operational effects and have precipitated multiple bespoke business processes to monitor, at a time when monitoring has been more scrutinised than ever, post financial crisis.

The increased cost of supporting pre- and post-trade activities and complying with the new regulatory obligations, alongside reduced profit margins in the derivatives business, is not sustainable. Against a backdrop of an increasingly digital and data-driven world, there is a need and an opportunity to standardise and digitise the legal documentation.

Through the adoption of common market standards, the market will be able to leverage technology-enabled contract delivery and management solutions, as well as allow the use of technology such as Distributed Ledger Technology (DLT) and smart derivatives contracts.

Significant work has progressed in these areas through the work of ISDA and others and there is a broader recognition of the need for market infrastructure, utilities, data governance, documentation change and process change. However, there is more to be done and until recently, legal agreement clause/data standardisation and legal agreement data had been at the periphery of current legal technology initiatives. But it is now falling into the mainstream, with clause taxonomies which are designed to address the growth of clause variants into one singular vernacular. Most importantly, we have seen the development of an outcomes based approach where variants are being condensed if they relate to the same business outcome. This is foundational when looking to enhance process, reduce risk and meet client expectations.

A glimpse of what “strategic state” looks like

Historically, written legal agreements have been king as we look to document and evidence the intention of trading parties, which has been largely effective. However, the legal profession has, on occasion, complicated contracts through verbose legalese that is not even consistent with the prose of other lawyers and incomprehensible to the uninitiated – never mind those e.g. in operations, giving effect and managing the risks arising from the contractual obligations they create.

The environment has changed and in an increasingly data-driven world, it is no longer the written word that is king. Firms are moving to operationalise their businesses through automated data-driven processes, and accordingly, key commercial and operational terms, as well as risks monitored within legal agreements need to form a part of the business process if they are to play a part in optimising the business decision-making, management of commercial risks and operations. However, until the key data elements of the legal agreements are structured, transparent and consumable, this optimisation is impossible. This means defining standard structured data variables and allowable values for those defined variables.

It all starts with structured data

We are on an inevitable journey to data-orientated legal agreements, with a representation of the written contractual terms in a manner that follows a consistent, predictable and structured data format. There are numerous tangible benefits to data orientated contracts, such as enhancing the process of negotiating legal agreements, allowing the opportunity to automate the creation and delivery of legal agreement documentation, and negotiate and execute it with multiple counterparties simultaneously, by focusing on intended business outcomes.

By having a standard list of variants focusing on outcomes of those clauses, it is possible to utilise LegalTech solutions to parse through legacy legal agreement documentation, and classify the clauses contained within such documentation against those standards and successfully manage those contractual obligations to optimise the business.

Challenges on the road to delivery

Markets and industries, by their very nature, tend to resist new ideas, products and standards. Added to this is the sheer amount of change to the pre- and post-trade processing and market infrastructure landscape in OTC derivatives following the 2008 financial crisis.

However, to unlock the benefits of the changing legal documentation landscape, the focus needs to be on data. Firms have historically under-invested in core reference data, and whilst there have been marked improvements, the standard is lacking for legal contract data; firms are simply unable to systematically understand the risks emanating from their broad contractual portfolio.

Clause taxonomies create a framework in which to work with legal agreements and manage the contractual obligations they contain, allowing classification to be conducted within the framework of that taxonomy. Although taxonomies are a well-established approach to categorising and linking to business processes, these have only been used to a limited extent by market participants for legal agreement management, and typically created individually (often for a particular department or specific use within a firm). They do however, form the foundations of optimising value from business processes and unlocking value through (legal) change.

Conclusion

Market participants have demonstrated considerable pioneering spirit to develop the industry through legal documentation. It now needs to be bold enough to take the next step to unlocking the digital agenda by developing common data standards. There are times when firms should compete and there are times when they should converge for the common good – and this in one of them.

Structured data will enable technology to provide the insights clients require with a far simpler and more sustainable operating model. We therefore need to think smart and adapt to operate in this new landscape which we should embrace, rather than resist.