Hi everyone 👋,
During the last 18 months, I played — maybe too much — with census & elections data and tried to predict the french elections with deep learning. I'm not officially a ML researcher, that's only a side project, so be nice please 🙏 ! I'm sharing this only to have fun discussions with people who have the same kink as me. 😊
You don't have to be a data scientist to read this 1st post which talks only about the results of the experiment.
TLDR of this 1st post:
- No I didn't find a way to predict the elections results
- But It's surprising how much you can learn about voters behavior (who votes for which party), even using only aggregated public data.
- It's only qualitative results so it's not real science.
- Still, it's interesting (worrying?) to think about what would be possible with more data (e.g: FAANG)
After that, I'll write 2 more posts: 1 for the model implementation and 1 for the MLOps tooling I've used.