AI in Insurance: Adaptive Questionnaires for Improved Risk Profiling
Authors: Diogo Silva, João Teixeira, Bruno Lima
Organizations: Deloitte and Faculty of Engineering, University of Porto, Porto, Portugal · Deloitte, Porto, Portugal · LIACC, Faculty of Engineering, University of Porto, Porto, Portugal
Insurance application processes often rely on lengthy and standardized questionnaires that struggle to capture individual differences. Moreover, insurers must blindly trust users' responses, increasing the chances of fraud. The ARQuest framework introduces a new approach to underwriting by using Large Language Models (LLMs) and alternative data sources to create personalized and adaptive questionnaires. Techniques such as social media image analysis, geographic data categorization, and Retrieval Augmented Generation (RAG) are used to extract meaningful user insights and guide targeted follow-up questions. A life insurance system integrated into an industry partner mobile app was tested in two experiments. While traditional questionnaires yielded slightly higher accuracy in risk assessment, adaptive versions powered by GPT models required fewer questions and were preferred by users for their more fluid and engaging experience. ARQuest shows great potential to improve user satisfaction and streamline insurance processes. With further development, this approach may exceed traditional methods regarding risk accuracy and help drive innovation in the insurance industry.
Figures & tables
Figure 1. RAG-based question-answering system workflow ( 15 ) .
Figure 2. ARQuest framework and its modules.
Figure 3. System’s flow and architecture.
Figure 4. Raw and labeled municipality values for alcohol mortality.
Figure 5. Captions with different parameters for an image ( 31 ) .
Figure 6. Traditional flow.
Figure 7. Prompt with answer prediction instructions.
Figure 8. Traditional "Insights" section.
Figure 9. Traditional risk forms.
Figure 10. Dynamic "Insights" section.
Figure 11. Dynamic risk form.
Figure 12. Comparison of approaches for the main evaluation metrics.
Figure 13. Risk scores per participant using both approaches.
Figure 14. Participant responses for Question 2 of the feedback form.
Figure 15. Participant responses for Question 9 of the feedback form.