Featurespace , an enterprise-grade technology provider that prevents fraud and financial crime, has launched TallierLTM, a Large Transaction Model (LTM). As stated in the press release, TallierLTM, a foundation AI technology for the payment and financial services industry, is a large-scale, self-supervised, pre-trained model designed to power AI applications for the financial protection of consumers.

TallierLTM has shown improvements of up to 71% in fraud value detection when compared to industry standard models operating at an industry-typical 5:1 False Positive Ratio. TallierLTM is intended to give fraud and financial crime professionals access to a generative Large Transaction Model providing an improvement when it comes to differentiating between genuine consumers and bad actors. Moreover, 70% of financial institutions in North America consider financial criminal attacks to be getting worse as they become more sophisticated with exponentially increasing losses.

According to the Nilson Report, global losses from card fraud are expected to total USD 397.4 billion over the next 10 years, with USD 165.1 billion of those losses happening in the US alone. TallierLTM has been pre-trained across jurisdictions and market segments using a self-supervised approach, with the aim of making it an accurate and representative of real-world consumer transactions. By analysing many transactions, TallierLTM identifies hidden transactional patterns that may be undiscoverable using current industry methods.

This enables it to generate likely future consumer transactions. Insights are based on time sequencing, such as unusual spending patterns over a short period of time and patterns of behaviour between a consumer and a merchant. For data scientists, these are a critical task when differentiating between genuine and criminal activity.

Financial institutions will be able to interact with TallierLTM via its embedding API, which is a data science accelerator that enables a consumer’s transaction history to be converted to a machine-readable feature vector. It creates a unique 'behavioural bar code,’ providing a representation of a consumer’s transactional behaviour without revealing any personally identifiable information. As per the press release, Featurespace is introducing the TallierLTM service with its partner TSYS, a global payments company.

About Featurespace Featurespace's mission to create a safer space to transact. The company helps banks and financial institutions protect customers and reduce risk and costs by providing machine learning financial crime prevention solutions. Featurespace launched Adaptive Behavioral Analytics, Automated Deep Behavioral Networks, and now TallierLTM.

Headquartered in the UK, Featurespace, operates globally from seven locations. .