PersonaBOT: Bringing Customer Personas to Life with LLMs and RAG
This work addresses the need for scalable customer persona generation for business decision-making at Volvo Construction Equipment, representing an incremental improvement over traditional qualitative methods.
The paper tackled the problem of generating synthetic customer personas for a chatbot using LLMs and RAG, finding that Few-Shot prompting produced more complete personas and that augmenting the chatbot's knowledge base increased average accuracy from 5.88 to 6.42 on a 10-point scale, with 81.82% of participants finding it useful.
The introduction of Large Language Models (LLMs) has significantly transformed Natural Language Processing (NLP) applications by enabling more advanced analysis of customer personas. At Volvo Construction Equipment (VCE), customer personas have traditionally been developed through qualitative methods, which are time-consuming and lack scalability. The main objective of this paper is to generate synthetic customer personas and integrate them into a Retrieval-Augmented Generation (RAG) chatbot to support decision-making in business processes. To this end, we first focus on developing a persona-based RAG chatbot integrated with verified personas. Next, synthetic personas are generated using Few-Shot and Chain-of-Thought (CoT) prompting techniques and evaluated based on completeness, relevance, and consistency using McNemar's test. In the final step, the chatbot's knowledge base is augmented with synthetic personas and additional segment information to assess improvements in response accuracy and practical utility. Key findings indicate that Few-Shot prompting outperformed CoT in generating more complete personas, while CoT demonstrated greater efficiency in terms of response time and token usage. After augmenting the knowledge base, the average accuracy rating of the chatbot increased from 5.88 to 6.42 on a 10-point scale, and 81.82% of participants found the updated system useful in business contexts.