The evaluation metric is [**accuracy score**](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_score.html), which is the default classification accuracy in `sklearn` library. There are 5 possible ratings. Target variable is has 1-based index which can is computed as a deterministic function of `uid` and `mid` (see Colab). Notice that this metric does not reward your predicted ratings for being close. You are rewarded for exact match of the rating. The submission format is:

        id,rtg
        1,1
        382,2
        763,3        
        1144,4
        1525,5

FYI: the original competition used RMSE, which defines deviation from true rating. The teams had to beat 0.95 RMSE.