Work · 2015—Now
Selected work across product measurement, experimentation, pricing, machine learning, applied AI, causal inference, and optimization—organized around the decisions it made possible.
01 · Flagship case study
A fleet-wide system that estimates sellable capacity, models price-sensitive booking behavior, and solves for a yield on every departure date.
Read the full case study →Selected systems
Two production LLM pipelines that convert complex program documents into structured, usable product information.
A deployed pricing model designed around operating economics and instant-booking decisions in a difficult market.
Causal inference, A/B testing, self-serve analytics, and multi-KPI measurement supporting product and merchandising decisions.
05 · Intellectual property
US 12,314,757 B1Named co-inventor
A feedback-based approach that compares actual resource utilization with a target, detects meaningful deviation, and adapts the criteria applied to subsequent resource requests.
View the patent record ↗Receive requests from multiple consumers competing for a shared set of resources.
Compare actual utilization for each usage period with its target utilization.
When deviation crosses a threshold, adjust a scheduling criterion for future requests.
Public contribution language is deliberately conservative: Rudraksh is a named co-inventor on the team’s patented adaptive scheduling approach.
Across the portfolio