As more and more companies choose TANGO to replace their aging legacy payments systems, we thought we'd shed some extra light on it by talking with Brian Miller, our General Manager at Lusis Payments.
The consumer demand for faster, more secure 24/7 payments continues to challenge payments organizations across the globe. For many organizations, the costs and difficulties of nursing an aging payments platform are now unsustainable. As a result, these organizations are now planning to replace their legacy applications with a faster, more agile solution that can free their business from the constraints of an inflexible payments platform.
Lusis Payments has set out to help payments organizations simplify and streamline their migration projects, reducing risks and delivering predictable progress milestones. As the innovative provider of TANGO, the mission-critical online transaction processing engine, Lusis Payments is making it much easier for organizations to keep pace with consumer desires for greater convenience, speed, and security in payments.
Q. What are the biggest challenges organizations with legacy transaction processing systems face today?
Miller: Legacy systems bring a whole host of challenges for organizations. For example, one of our clients, a top-five global bank, found their 28-year-old legacy system severely constraining to their business. It had become too expensive to maintain and operate, development times were lengthy, and they were less able to compete in the market.
When they started looking to replace the system, they realized that they were using the software throughout their entire line of banking services. Clearly, it would be crucial for the new solution to provide a highly extensible architecture, enable them to orchestrate low-risk migrations, and be powerful enough to handle diverse transactions and increasing volumes.
Of course, they also wanted a solution that would reduce their cost of ownership and application life-cycle costs while increasing the bank's agility in adapting to consumers' changing needs. The ability to efficiently support new regulations and scheme mandates was another key requirement. The bank conducted an extensive analysis of the leading payment solution providers. The analysis showed that TANGO exceeded all the client's business and technical requirements, and TANGO outperformed its competitors in the areas of architecture, flexibility, and cost of ownership.
Q. Why is TANGO so successful in replacing legacy systems, such as BASE24®?
Miller: Much of Lusis Payments' success comes because TANGO is easily “built to order” because of its micro-services platform. We recognize that payments organizations need a solution that works the way they do, that empowers its staff, not hinder them. TANGO does this.
A good example of this in action is our client BankservAfrica, which wanted to expand into the rapidly growing South African development community. Well, to do this, they needed a fully functional core system that could cope with fast-changing payment methods and customer requirements. TANGO also met BankservAfrica's business requirements, which included that it must be configurable, with specific monitoring capabilities. In addition, TANGO's cost and clear licensing structure appealed to the BankservAfrica team and our phased approach really makes for a painless migration.
Q. It really says something that some of the largest banks in the world have chosen TANGO to replace their systems. What's something you want other organizations and financial institutions to know about TANGO as they may be looking at replacing legacy systems?
Miller: At Lusis, it boils down to this. We don't care what transaction processing system you had. We want to hear about what functionalities you want for the present and the future. With TANGO, we can build whatever you need with scalability for any of your future needs as well.
Q. What should organizations avoid when it comes to migrating their payments system?
Miller: The most important advice I can give is don't wait. To be successful, organizations need to develop the operational skills and procedures to manage continual change. Migrating to a new payments solution is not a one time thing, it is actually a transition to a different operational lifestyle – one where change is the expected norm.
This Lusis Payments customer is one of the largest financial institutions in the world. The organization has over 10 million global customers covering several public and business sectors. They provide tailored banking solutions for personal, small business, commercial and cross border payments.
THE NEED: Freedom from a Constraining Legacy Payments Platform
The client's business was becoming severely constrained by their 28 year-old legacy payments system. The high cost of ownership, lengthy
development times, and soaring maintenance challenges became urgent pressures for change. The legacy software was widely utilized throughout the client's vast line of banking services. It was therefore crucial that the new solution would provide a highly extensible architecture, facilitate low-risk migration projects, and have the robustness to handle diverse and high-growth volumes.
Additional high-priority requirements included;
“We have implemented more “new” functional capabilities in the last 3 years on the TANGO platform than we have in over a decade on our previous legacy platform. It is great to be free from all the constraints.”
Bayesian and Dempster-Shafer models for combining multiple sources of evidence in a fraud detection system
By Fabrice Daniel, Artificial Intelligence Department of Lusis, Paris, France
Combining evidence from different sources can be achieved with Bayesian or Dempster-Shafer methods. The ﬁrst re-quires an estimate of the priors and likelihoods while the second only needs an estimate of the posterior probabilities and enables reasoning with uncertain information due to imprecision of the sources and with the degree of conﬂict between them. This paper describes the two methods and how they can be applied to the estimation of a global score in the context of fraud detection.
Fraud detection mainly relies on expert driven methods that implement a set of rules and data driven approaches implementing machine learning (ML) models. Both provide an estimate (or a score) for a new transaction to be fraudulent.
While each ML model naturally returns a fraud probability, the experts can also attach a probability to each rule. They can also be automatically calculated from the labeled his-tory. Combining them together produces a global score that can be used in a near real time system to rank a set of trans-actions having the highest probability to be fraudulent. By obtaining this ranking, investigators can concentrate their efforts on the suspect transactions with the highest probability of being true frauds.
The most common approaches for combining scores are summing individual scores or returning the highest score among the trigged rules. This is not entirely satisfactory given that summing scores is equivalent to averaging the probabilities returned by each predictor (rule or model). It also does not take into account the uncertainty of each predictor and the degree of conﬂict between them.
For the Lusis fraud system, we work on implementing more appropriate approaches.
This paper proposes two ways for addressing this problem. The ﬁrst is to use Bayesian methods ; the second is to combine the scores by using Dempster-Shafer theory .
The latest company and industry news from Lusis Payments.