Reproduce “Unlocking Sales Growth: Account Prioritization Engine with Explainable AI” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Suvendu Jena, Jilei Yang, Fangfang Tan
LinkedIn developed the Account Prioritizer, a machine learning system that identifies customer accounts with high upsell potential or churn risk for sales representatives. This system, which incorporates natural language explanations for its predictions, led to an 8.08% increase in renewal bookings and a 20.4% lift in Renewal Incremental Growth for consistent users.
Key insights
- Framing the problem as predicting the difference between future and past spending directly aligns the model with the business objective of identifying revenue potential.
- Integrating the CrystalCandle explanation engine provides natural language explanations for predictions, significantly improving user trust and adoption among sales representatives.
- Rigorous causal measurement through A/B testing and a Coarsened Exact Matching (CEM) study quantified the system's business impact and highlighted the benefits of consistent usage.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.