Working Papers
Informal Ties and Sales Agent Turnover: Evidence from Randomized Dormitory Assignment
This paper studies how informal ties (e.g., shared hometowns) among sales agents affect turnover. We develop a framework that distinguishes the effect of tied peers while they remain from the incremental effect of losing a tied peer. Partnering with a leading Chinese medical equipment company, we exploit random dormitory assignment of roughly 2,000 agents tracked over 20 months to identify exogenous variation in peer exposure along traits such as hometown, dialect, and alma mater. We find that tied peers reduce quit risk while present, yet their departure raises the remaining agent's quit risk, with survey evidence pointing to psychological support as the operative mechanism.
LLM Simulation Training: Field Evidence on Turnover and Performance in Healthcare B2B Sales
Collaborating with a major advanced manufacturing firm, we conduct a five-month randomized field experiment with over 200 newly recruited sales agents, comparing LLM simulation training to traditional role-play training. LLM training reduces early-career turnover by 21% and improves agent performance. We further analyze millions of training interactions and 170,000 subsequent customer conversations to examine when and why LLM simulation works.
Work-in-Progress
Volume to Content: Multi-Stage Field Evidence on LLM Appraisal's Impact on Sales Agents
Sales agent effort is always difficult to measure even with huge investment. LLM now can auto assess sales agent interactions, yet its impacts remain unknown. To answer this, we conduct a three-stage field experiment with a leading sales center to separate new appraisal's awareness, learning, and adoption effects.
Inclusive Visual Marketing: Overcome Cognitive Biases for Vision-Impaired Consumers
Visual marketing often excludes consumers with visual impairments through biases like poor grouping, framing, and contrast. Working with a major eye hospital, we study how these biases affect patients with cataracts, glaucoma, macular degeneration, and retinopathy, and how to correct biases with deep learning methods.