FICO® Focused Language Model and FICO® Focused Sequence Model are redefining global standards in trust, model design, and Responsible AI—driving enterprise value

FICO (NYSE: FICO):

Highlights:

• FICO® Focused Foundation Model for Financial Services (FICO® FFM) is a domain, data, and problem-specific GenAI model for financial services that delivers accurate and auditable outcomes.
• FICO® Focused Language Model (FICO® FLM) and FICO® Focused Sequence Model (FICO® FSM) lay the groundwork to deliver sustained value in GenAI models across financial services.
• FICO’s patent-pending Trust Scores give enterprises a risk-based approach to managing GenAI hallucinations and ensure consistent outcomes when tackling sensitive and highly regulated challenges.

Global analytics software leader FICO announces a new unparalleled domain-specific FICO® Foundation Model for Financial Services (FICO® FFM) product offering, consisting of FICO® Focused Language Model for Financial Services (FICO® FLM) and FICO® Focused Sequence Model for Financial Services (FICO® FSM), purpose-built to reduce hallucinations and achieve precise accuracy over conventional Generative AI (GenAI) models.

The FICO FFM is designed with a precise, auditable focus on the data used to build and further task-train the model for each specific task or business problem. The model is architected for trusted, responsible use of GenAI. Unlike general-purpose LLMs trained on broad world knowledge and requiring massive compute power, FICO’s focused domain-specific models require up to 1,000x fewer resources—making them significantly more focused, cost-effective to train and maintain, auditable and adaptable. FICO’s models are custom-built, engineered in-house and are focused on curated data sets related to the domain of financial services.

“The focused foundation model represents a practitioner's approach to GenAI in financial services, moving beyond trying to refine universal knowledge models,” said Dr. Scott Zoldi, chief analytics officer at FICO. “FICO FFM enables enterprises to use small language models built for their specific business problems, significantly helping to mitigate hallucinations, provide transparency, auditability, and adaptability. The model complies with regulations through the transparency of data and a decreased risk of hallucinations through Trust Scores and business owner-defined knowledge anchors. These domain-specific models can result in 38% lifts in compliance adherence use cases and more than 35% lifts in world-class transaction analytic models, in areas such as in fraud detection.”

FICO FLM and FICO FSM Enhance Data Transparency and Trust for Financial Institutions

FICO FLM is built on domain-specific and task-specific contextual data, allowing the model to significantly reduce hallucinations given that the training data is directly relevant to the problem. These models are smaller, more accurate, and significantly lower in cost, driving a practical approach toward agentic AI. FLM models enhance performance, have a low barrier to entry, and streamline operations for financial institutions.

FICO FSM is focused on leveraging long-range attention in transaction sequences, finding critical relationships in transaction histories typically not captured in traditional analytics systems. The model plays a crucial role in improving real-time detection accuracy across financial services transaction analytics, while capturing complex inter-relationship sequences in use cases like payment fraud, real-time risk assessment, next-best action, and more. The model empowers customers to uncover transactional behavior patterns that were previously impossible or too expensive to identify.

"FLMs are essentially similar to SLMs (Small Language Models) and these are transforming how GenAI is used in financial risk management and compliance by providing highly accurate, domain-specific insights and reducing misinformation. Built on curated data and Responsible AI principles, these models are becoming essential tools for institutions that require precision, transparency, and scalable trust,” said Megha Kumar, research vice president of analytics and AI analyst at IDC.

Trust Scores Drive Implementation of Responsible AI Standards

FICO FLM and FICO FSM are built with both patented and patent-pending Trust Scores, providing a risk-ranking of the reliability of the output generated by these models. By using a Trust Score, organizations can set their own risk thresholds, reduce hallucinations, and operationalize model outputs with confidence. This framework empowers financial institutions to deploy GenAI responsibly, ensuring that all outputs align with business-defined knowledge anchors and have sufficient statistical support, enabling ongoing risk oversight and risk monitoring in GenAI decision-making.

LLMs Built on Responsible AI Standards Drive Business Value

A recent global FICO survey, State of Responsible AI in Financial Services: Unlocking Business Value at Scale, developed with Corinium Global Intelligence, revealed that while 40% of respondents see GenAI and LLMs as major drivers of ROI, an even greater 56.8% pointed to Responsible AI standards as the most crucial factor for increasing reliable, consistent returns. These findings underscore the continued importance of combining Responsible AI and GenAI solutions—such as FICO Focused Foundation Models. Responsible AI is increasingly recognized as a critical driver for delivering substantial impact and value.

“While LLMs have been a significant enabler in the rise of AI – and a major disruptor across industries – their adoption has been more limited in financial services,” said Dr. Zoldi. “In highly regulated environments where accountability and precision are critical, current LLMs often lack the reliability, transparency, and governance required for enterprise deployment. FLMs, designed with domain-specific data, auditable model focus, and task specific auditable data, enable development of GenAI that is built for purpose, auditable, and able to be monitored and constrained to business guidelines.”

FICO has filed multiple patent applications on FICO FLM and FICO FSM core technology and specific use cases, including trust scoring frameworks, model training techniques, tracking content generated by language models, real-time monitoring, and transaction sequence modeling. These advancements underscore FICO’s innovation in Responsible AI and in the commitment to make GenAI usable, trustworthy, and impactful for the financial services industry.

To learn more about the FICO® Foundation Model for Financial Services, including FICO® Focused Language Model for Financial Services and FICO® Focused Sequence Model for Financial Services, visit: https://www.fico.com/en/products/fico-focused-foundation-model-financial-services

About FICO

FICO (NYSE: FICO) powers decisions that help people and businesses around the world prosper. Founded in 1956, the company is a pioneer in the use of predictive analytics and data science to improve operational decisions. FICO holds more than 200 US and foreign patents on technologies that increase profitability, customer satisfaction and growth for businesses in financial services, insurance, telecommunications, health care, retail and many other industries. Using FICO solutions, businesses in more than 80 countries do everything from protecting four billion payment cards from fraud, to improving financial inclusion, to increasing supply chain resiliency. The FICO® Score, used by 90% of top US lenders, is the standard measure of consumer credit risk in the US and has been made available in over 40 other countries, improving risk management, credit access and transparency.

Learn more at https://www.fico.com/en.

Join the conversation at https://x.com/FICO_corp & https://www.fico.com/blogs/

For FICO news and media resources, visit https://www.fico.com/en/newsroom.

FICO is a registered trademark of Fair Isaac Corporation in the U.S. and other countries.

View source version on businesswire.com: https://www.businesswire.com/news/home/20250923160340/en/

FICO FFM enables enterprises to use small language models built for their specific business problems, significantly helping to mitigate hallucinations, provide transparency, auditability, and adaptability.