STAR Summary
- Situation
- My wife asked me to suggest baby names. I wanted something that learns her taste instead of guessing.
- Task
- Owned the end-to-end build, from implementation through the final deliverable.
- Action
-
- Aggregated SSA baby-name records (1880-present) and engineered trend features.
- Built a simple 'quiz' script to collect like/dislike labels.
- Trained several models and averaged their scores to produce recommendations.
- Result
-
- Generated personalized top 50 name lists for boys and girls.
- Helped us narrow the list when naming our child.
- Stack
- Python ? scikit-learn
- Status
- Live interactive demo
Demo
Explore rated names and similarity-based recommendations.
- Choose Girls, Boys, or All at the top to change the dataset slice.
- In “Ratings Snapshot”, click a rating bar to see the names at that score.
- In “Name Explorer”, switch between Recommendations and Rated Names.
- Use search + sort to find names quickly.
Links
Data Links
Notes
Uses SSA baby-name data plus personal quiz labels; recommendations are preference predictions, not a population forecast.
