OKEMA helps data-rich businesses determine which customers to target, what action to take, and how to allocate limited resources, then measures the incremental impact of every decision.
Customer, transaction, operational, and contextual data.
Likely outcomes and causal response to each action.
Best permitted action against the business objective.
Send the recommendation into the existing workflow.
Compare outcomes against a baseline or holdout.
Improve future decisions with every cycle.
Determine who genuinely needs an incentive, what offer to provide, and who would purchase without one.
Read the study →Identify which policyholders are at risk, which can be influenced, and which intervention maximizes expected retained premium.
See the pilot design →Validate every payable item against applicable authorization and operating rules before money leaves.
View the case study →Who can we influence, and how?
What is the least costly action that changes the outcome?
Where should limited capacity go next?
Most businesses already know what happened yesterday. OKEMA is built to help them decide what to do next, on every customer, every incentive, every case worth reviewing.
Three distinct kinds of evidence, clearly labeled.
A live payment-integrity system converts operational data and business rules into auditable, production-grade decisions embedded in daily workflows.
Home-care payment integrity · in productionLost lifetime value recovered via treatment-effect modeling, and LTV improvement from behavior and causal models.
Prior employment & researchPublic- and synthetic-data studies demonstrating how the methods apply to concrete commercial decisions, with assumptions stated.
Methodology & results published in full“After building production AI at Microsoft and researching causal inference, reinforcement learning, and recommender systems, I saw that enterprises rarely struggle because they lack data. They struggle because they lack systems that consistently recommend the best business action.”
I personally lead every initial engagement. PhD in Systems & Information Engineering (University of Virginia); prior work at Microsoft, Netflix, and DoorDash; two issued patents and peer-reviewed publications in causal models, contextual bandits, and counterfactual systems.
Read the founder story →We identify one high-value repeated decision, build and evaluate a decision policy on your historical data, and define how its incremental impact will be measured in production.