Pokémon Market Analysis
The story
It started with a Miraidon card from McDonald's. Shiny, fancy-looking, and I had no idea if it was worth anything. So Nat and I asked: is the Pokémon card boom on TikTok real?
We tracked 540 chase cards across 49 sets, priced every month from January 2021 to November 2025, and built an interactive Tableau dashboard to dig in.
Across the full window, the median price rose 37.46%. Looks like a boom. Then we ended the window at 2024 instead, and the number flipped: down 22.84%, with 60% of cards underwater instead of 41%.
Nothing about the cards changed. The window did.
The headline gain was a composition effect. Cards join the dataset when they're released, so the sample keeps filling up with newer, pricier cards. Like a class average rising after a few top scorers transfer in, the previous students' grades stayed the same and only the class composition changed.
Over the whole stretch, the median card returned about 4% a year. Philippine land does 8 to 12. And grading? It roughly doubles a card's value, but a single card needs to be worth about $125 raw to clear even a $25 fee.
Most cards don't moon.
What came of it
A perfect 100/100. We presented the dashboard and deck on July 13, two days after we started. It was my first zero-to-hero data science project, and it taught me that a graph can mislead even when every number on it is right.