The fact that no-one’s gotten the optimal solution is very much intended. (If anyone had, I would be both very impressed with them and somewhat disappointed with myself.) You should not expect to be able to fully model a domain with data science, it’s like trying to thread a needle wearing huge thick gloves. But you can expect to figure out something about the domain, and use that to at least substantially outperform randomness. (Our highest scorer this round, abstractapplic, had ~half the optimal winrate, but ~100x the ‘random approach’ winrate).
+1.
The fact that no-one’s gotten the optimal solution is very much intended. (If anyone had, I would be both very impressed with them and somewhat disappointed with myself.) You should not expect to be able to fully model a domain with data science, it’s like trying to thread a needle wearing huge thick gloves. But you can expect to figure out something about the domain, and use that to at least substantially outperform randomness. (Our highest scorer this round, abstractapplic, had ~half the optimal winrate, but ~100x the ‘random approach’ winrate).