Dr. Priya Narang

➜ ~ stats --all

➜ ~ ls ./links

➜ ~ cat about.md

My PhD was on sequence models for healthcare time series — which taught me that the model is the easy part. The hard part is the data pipeline, the evaluation that doesn't lie to you, and the deployment that survives contact with reality. I've since built recommendation and forecasting systems serving millions of users, and I've learned to be deeply suspicious of any metric that only improves offline. I publish when the work is genuinely new, and I ship when it genuinely helps.

// mission: Build models that are honest offline and useful online.

const values = ["Rigor", "Reproducibility", "Impact over novelty", "Ethical ML"]

➜ ~ cat experience.log

# Applied ML across recommendation, forecasting, and healthcare — research to production

➜ ~ ls ./projects

▸ Two-tower ranking at scale

Rebuilt the recommendation ranker — +7.2% conversion, 40ms p99 at 3B daily candidates. Architecture + online eval.

#RecSys #Production #+7.2%

▸ forecast-kit (OSS)

A probabilistic forecasting library with proper backtesting built in. 1.8k stars.

#OSS #Forecasting

▸ Clinical sequence models

PhD work: attention models for ICU time series. Published at NeurIPS workshop, code released.

#Research #Healthcare

▸ Eval you can trust

A framework for offline/online metric alignment that catches overfit before it ships.

#MLOps #Evaluation

➜ ~ cat reviews.md

➜ ~ cat achievements.log

• ✓ 3 papers at NeurIPS / ICML workshops
• ✓ Reviewer, NeurIPS & ICLR
• ✓ 1.8k⭐ on forecast-kit
• ✓ Patent: adaptive ranking (pending)

➜ ~ cat contact.sh