
Predicting Hourly Bike Rentals
In Pursuit of Model Accuracy!
A data science project to predict hourly bike rentals in the city of Seoul using date and weather seasonal data.

I Build Data Systems People Actually Use
I started my career counting inventory at Whole Foods. Now I build AI systems that analyze millions of customer interactions at Snowflake.
Along that path, I've learned that the best data work doesn't come from fancy tools. It comes from understanding what actually matters to the business and building things that get used. Whether it's optimizing safety stock for 3,500 SKUs or building LLM-powered case analysis that saves thousands of hours of manual review, the approach is the same: figure out the real problem, then ship something that doesn't sit in a deck somewhere.
I've spent the last decade doing analytics across retail, supply chain, marketing, and enterprise support. I like messy problems, cross-functional work, and turning ambiguous asks into clear results.
I start every project by understanding the business context. The best technical solution is worthless if it doesn't solve a real problem.
Complex problems don't always need complex solutions. I aim for clarity and simplicity in both analysis and communication.
Insights are useless if no one uses them. I embed solutions directly into stakeholders' existing workflows so they're easy to access and actually get used.
From data modeling to stakeholder presentation, I take ownership of the full analytics lifecycle to ensure impact.
The data landscape evolves rapidly. I stay current with new tools and techniques, especially in AI and automation.
A path from understanding business fundamentals to building AI-powered solutions
Scroll horizontally to exploreSwipe to explore
A collection of work that showcases my approach to solving complex data problems
Ideas, insights, and lessons from my work in data and analytics
I'm always open to discussing new opportunities, exploring collaborations, or connecting with fellow data enthusiasts.