Featurespace, a leader in enterprise-grade technology that combats fraud and financial crime, has proudly introduced its innovative product, TallierLTM™.
The ever-evolving sophistication of financial criminal attacks has led to escalating concerns among institutions. With an alarming 70% of financial establishments in North America viewing these attacks as intensifying, the need for advanced measures is paramount. This urgency is underscored by the Nilson Report’s prediction of global card fraud losses amounting to $397.4bn over the forthcoming decade, of which $165.1bn is anticipated to occur in the U.S.
Specialising in state-of-the-art technology, Featurespace has carved a niche in developing tools that prevent fraud and financial crime, catering especially to payment and financial service sectors.
TallierLTM™ stands as the world’s pioneering Large Transaction Model (LTM), engineered specifically for the payment and financial services industry. As a vast, self-regulating, pre-trained model, it is the cornerstone of future AI applications aimed at fortifying financial consumer protection. The model excels in differentiating genuine consumers from ill-intentioned actors, boasting a remarkable 71% improvement in fraud value detection against prevailing industry standards.
Designed to reflect real-world consumer transactions, TallierLTM™ undergoes pre-training across varied market segments and jurisdictions, leveraging a self-supervised modus operandi. By scrutinising billions of transactions, it discerns latent transactional motifs, eluding current industry techniques, empowering it to predict probable future consumer transactions. The insights derived focus on temporal sequencing, spotlighting anomalies like uncharacteristic expenditure patterns within brief time frames or peculiar interaction blueprints between consumers and merchants.
Financial establishments can seamlessly integrate with TallierLTM™ through its embedding API. This innovative tool converts a consumer’s transaction chronicle into a machine-interpretable feature vector. Consequently, it produces a distinctive ‘behavioural barcode,’ encapsulating a consumer’s transactional behaviour, all while preserving personal anonymity.
In its forward-looking approach, Featurespace is gearing up to roll out the TallierLTM™ service in collaboration with its enduring partner, TSYS, a notable entity under the Global Payments (NYSE: GPN) umbrella.
Featurespace founder David Excell commented, “What OpenAI’s LLMs have done for language, TallierLTM™ will do for payments. There is widespread concern about how deep-fakes and generative AI have been used to deceive consumers and our financial systems. We plan to reverse this trend by utilising the power of generative AI algorithms to create solutions that protect consumers and make the world a safer place to transact.”
Featurespace’s chief innovation officer, Dr. David Sutton, added, “We know that smarter technology helps financial institutions better understand their consumers. We have taken this to the next level by pairing cutting-edge generative AI algorithms with huge volumes of data, enabling a machine to efficiently comprehend the relationships between different customer transactions. By adding TallierLTM™’s feature vectors to the inputs of an industry-standard fraud model, we’ve seen improvements of up to 71% in fraud value detection. This will accelerate data science teams’ ability to level up their model performance and realise the value of machine learning investments more quickly.”
Dondi Black, executive vice president and chief product officer for TSYS, remarked, “TSYS and Featurespace have a long track record of co-innovating to deliver industry-leading technologies and solutions that help financial institutions provide secure, seamless experiences at scale. TallierLTM™ is the next transformative step, allowing us to unlock new insights and power new experiences for our clients around the world, further differentiating our capabilities with this new groundbreaking solution.”
Copyright © 2023 RegTech Analyst
Copyright © 2018 RegTech Analyst
