# Post mortem -- what worked for me

I only came in 7th, so my approach probably doesn't matter much, but here are the keys to my strategy:
* Ordinal encoding for the "ord" columns, normalized to 0-1 in order to make the coefficients prettier.
* One-hot encoding for everything else, using sparse (csr) representation so that it fits in memory.
* LogisticRegression with the 'saga' solver, and a very carefully tuned C value of 0.1172.  I used 50 iterations, but the number really didn't matter.
* Trusting my CV. I really worked it hard in order to get the optimal C value, and the leaderboard improvements always matched the public LB. (It was only "pretty good" on the private LB, though. If I'd stuck with an older C value of "0.133" I would have been in the money. That's how the shake-up goes.)
That's it. Lots of encodings were tried, but nothing beat one-hot. You just had to be willing to accept the thousands of columns that resulted.