This year’s Hackathon challenges teams to come up with innovative solutions to help financial institutions leverage the potential of machine learning and artificial intelligence.
This year, the Swift Hackathon is challenging the financial community to develop innovative financial services that can benefit the entire industry.
Hackathon teams will focus on how artificial intelligence and machine learning can be leveraged to help financial institutions efficiently manage risk, and develop anonymised data-sets that can help test the next generation of AI-based services.
Why take part?
The winning teams will get the chance to present their innovative solutions at the world's largest transaction banking event – Sibos. And, to make the competition even more appealing, we'll be inviting the winners to come and co-create their solution with us so that it can benefit the entire financial community.
The role of AI and ML in financial services
Today, AI and ML are already used in a range of financial services – detecting fraud, reducing false positives, automating trading activities and providing financial advisory services to investors. This technology has the unique capability to quickly analyse millions of data sets and build accurate predictive models that enhance decision making – all without being explicitly programmed.
We believe AI/ML technology is now mature enough to help reduce the frictions our community faces in managing cross-border transactions, as well as delivering innovative new financial services to our customers.
What are the Hackathon challenges?
Challenge 1: Enhancing the accuracy of anomaly detection in payments
Detecting fraudulent transactions and identifying money laundering activities are costly operations for financial institutions that pose a real reputational risk for banks that get it wrong.
For this challenge, teams must develop novel data representations that can better detect transaction anomalies. Ultimately, this solution should contribute to a reduction in the overall number of alerts and false positives without compromising accuracy or effectiveness.
Challenge 2: Building ‘synthetic’ data-sets required for AI-based product development, whilst protecting privacy
In the digital world, banks are striving to create new intelligent services that improve customer experiences of banking services – all underpinned by machine learning algorithms that recognise transaction types and learn from user behaviour.
Building, maintaining and improving such services requires using large datasets to train machine learning models. Yet financial institutions cannot use their own customer datasets due to data protection laws.
Teams must develop novel simulation techniques that maintain the ‘utility’ of the original transaction data, whilst fully protecting the privacy of the institutions involved.
How will the solutions be assessed?
Both challenges will be evaluated by a panel of industry experts, based on the best understanding and explanation of the business challenge and the originality of the approach.
What tools will be provided to participants?
We’ll supply participants with all the reference data sets and collaboration tools needed to develop solutions for both challenges.
This year we are also offering participants access to a dedicated Hackathon sandbox environment for teams to design, develop and test their solutions before submitting them for assessment.
Who can enter the Hackathon?
All Swift members, fintechs and companies that provide services interacting with and complementing Swift’s offering can enter the Hackathon.
Applicants will need to form a multidisciplinary team from within their own institution, with an official representative to sign the Hackathon T&Cs.
What’s the timeline?
Registrations will remain open until Friday 6 August. As soon as registrations are received, we’ll begin the onboarding process – the signing of T&Cs and performing relevant sanctions checks.
The Hackathon will last three weeks, taking place between 6 and 24 September. During this time, teams will have full access to the Hackathon sandbox environment to develop and test their solutions.
Judging will take place once the event is complete, and the winners and runners-up will be announced at Sibos.