Azure OpenAI Service supports honest insurance with transforming alerts for potential fraud into human readable stories
There are many use cases for Azure OpenAI Service within FRISS solutions, such as using a fraud bot, network explainer, commercial underwriting chatbot, or a claim summarizer. FRISS is also planning to enhance existing capabilities with Azure OpenAI Service such as its underwriting indicator engine, to improve overall accuracy on commercial underwriting data.
FRISS is currently developing a “smart” explanation of its AI models’ predictions, aligning with its responsible AI approach. Azure OpenAI Service enables FRISS to present potential fraud cases into more engaging and understandable stories, using the art of storytelling as the essence of the explanation. With this approach, understanding and conveying potential fraud incidents to insurance professionals and fraud investigators becomes remarkably seamless.
Christian van Leeuwen, FRISS Co-Founder and CSO, comments: “Every time our AI model makes a prediction, we automatically create sentences, or bullet points, which explains why the model made such a prediction. Our vision is to transition to a more engaging and user-friendly “smart story” approach, capitalizing on the power of Microsoft Azure OpenAI Service.”
FRISS chose this approach because it allows for:
- Responsible AI: FRISS applies the 7 principles for trustworthy AI in its platform, based on the “ethics guidelines for trustworthy AI” developed by the European Commission’s High-Level Expert Group on AI.
- Better explainable AI: FRISS customers can now grasp the explanations of the AI Fraud Model better, as ChatGPT enables FRISS to create more compelling, coherent explanations compared to the current simple sentences.
- Unbiased and ethical AI: By using ChatGPT for explanations only, FRISS reduces the chance of potential bias or ethical concerns, as it doesn’t influence the fraud assessment or add any scores.
“After conducting an initial survey, the response to the ‘smart story’ format was very positive,” says Gian Luigi Chiesa, Product Owner Data Science at FRISS. “We are now working on implementing this approach for a group of pilot customers, ensuring its seamless integration and effectiveness.”
FRISS’s commitment to enhancing fraud model explanations and providing a transparent, unbiased experience for its customers remains unchanged. “As we move forward, we envision even more possibilities, with plans to release use cases for our customers based on generative AI, such as large language models, into our platform in the first half of 2024. This collaboration is just the beginning of our journey towards a more secure and trustworthy future in the fight against fraud,” concludes Van Leeuwen.
“We are pleased to support the digital transformation of business processes in the insurance industry, especially in this new era of AI,” says Matthew Kerner, Corporate Vice President, Microsoft Cloud for Industry. “FRISS brings differentiated new experiences to insurance customers with the power of Microsoft Azure OpenAI Service. With a deep understanding of the insurance domain, FRISS has the know-how to apply Azure OpenAI Service responsibly to core business processes of insurers and other regulated firms.”
SOURCE: BusinessWire
