Rudraksh Syal

Led the development and deployment of a dynamic pricing and decision system across multiple US regions, collaborating with data scientists to replace band-based pricing with an equilibrium approach. Built ML models for fulfillment-cost estimation and lead propensity using gradient-boosting, and integrated results into Salesforce to prioritize outreach. Developed an agentic pricing layer for retrieval, anomaly root-cause analysis, and recommendation explanations for revenue management. Also delivered LLM/RAG solutions for contract intelligence and operator-facing cancellation policy automation.

Applied Bayesian structural time series causal inference with synthetic-control baselines to evaluate in-store endcap experiments, supporting go/no-go decisions. Built optimization models for bakery space planning for new and remodeled store layouts and improved performance in pilot locations. Produced assortment and shelf-adjacency recommendations using customer and basket behavior to inform merchandising actions for consumer brands.

Developed R/Shiny and Flask analytics tools to support real-time product and sales monitoring, replacing an external reporting service. Used NLP and sentiment analysis on customer feedback to identify drop-offs in product journeys. Designed and applied A/B testing approaches to evaluate changes and support conversion improvements.