Inspiration
Medicaid data is fragmented and often difficult to interpret in real time, leading agencies to react to problems only after they affect coverage and access. We were inspired to build a system that helps decision‑makers understand why enrollment and administrative changes happen, not just report that they did.
What it does
MedicaidIQ is an AI‑powered intelligence platform that analyzes Medicaid enrollment and administrative data to detect meaningful shifts, explain their likely drivers, and provide interpretable insights that support proactive, evidence‑based policy decisions.
How we built it
We built MedicaidIQ by integrating Medicaid enrollment, eligibility processing, and drug pricing datasets, applying time‑series modeling, anomaly detection, and rules‑based attribution to translate noisy data into actionable, policy‑ready insights through an interpretable decision‑support layer.
Challenges we ran into
Issues using PowerBI, deploying, running out of API credits, and deploying to Github via Mac.
Accomplishments that we're proud of
A workable prototype within 12 hours. A starting point to continue to flesh out the system, providing explainable insights that are meaningful to real‑world policymakers.
What we learned
We learned that interpretability and context are just as important as predictive accuracy in public sector AI.
What's next for MedicaidIQ
An ability to add/remove datasets. Less static data with more user-responsive data, end-to-end deployment.
Log in or sign up for Devpost to join the conversation.