PAARS: Persona Aligned Agentic Retail Shoppers
This work addresses the need for cost-effective and faster behavioral simulation in e-commerce, though it is incremental as it builds on existing LLM agent methods with specific retail applications.
The paper tackles the problem of simulating human shopping behavior using LLM-powered agents by proposing a framework that creates synthetic shopping agents from historical data and aligns them at the population level, showing that personas improve alignment but a gap to human behavior remains.
In e-commerce, behavioral data is collected for decision making which can be costly and slow. Simulation with LLM powered agents is emerging as a promising alternative for representing human population behavior. However, LLMs are known to exhibit certain biases, such as brand bias, review rating bias and limited representation of certain groups in the population, hence they need to be carefully benchmarked and aligned to user behavior. Ultimately, our goal is to synthesise an agent population and verify that it collectively approximates a real sample of humans. To this end, we propose a framework that: (i) creates synthetic shopping agents by automatically mining personas from anonymised historical shopping data, (ii) equips agents with retail-specific tools to synthesise shopping sessions and (iii) introduces a novel alignment suite measuring distributional differences between humans and shopping agents at the group (i.e. population) level rather than the traditional "individual" level. Experimental results demonstrate that using personas improves performance on the alignment suite, though a gap remains to human behaviour. We showcase an initial application of our framework for automated agentic A/B testing and compare the findings to human results. Finally, we discuss applications, limitations and challenges setting the stage for impactful future work.