### Track I : Item Combination Prediction
The task of Track I is to predict users' feedback to the given nine exposed items. It is not a simple point-wise supervised learning task. You need to give a prediction of 0/1 for each item and arrange the results as a nine-length space-delimited list (left to right top to bottom). The quality of submissions will be evaluated using the CategorizationAccuracy measure. Solutions will be evaluated in Kaggle and the results will be published on the public leaderboard. The score will be computed on a subset of the test dataset, fixed for all participants. The final evaluation will be performed after the completion of the competition using the remaining part of the test dataset. Those results will also be published online. It is important to note that only teams which submit a report describing their approach before the end of the challenge will qualify for the final evaluation.

### Track II : Item Combination Generation (Recommended)
The task of Track II is to generate the best item combination (no repeat items) for each user to maximize the expected reward, i.e., the sum of the product of items' price and their purchase probability. It is a pure reinforcement learning task. The quality of submissions will be evaluated using the pure reinforcement learning measure, reward. You need to send your Kaggle 'User Name' as email title and submission.csv (1 Maximum Daily Submissions) as attachment to bigdatacup2021_rl4rs@service.netease.com . Solutions will be evaluated by a pre-trained large-scale RL environment. The results will be replied to immediately and published on the [Track II leaderboard](https://fuxi-up-research.gitbook.io/fuxi-up-challenges/challenge/bigdatacup2021-rl4rs-challenge). The score will be also computed on a subset of the test dataset, fixed for all participants. The final evaluation will be performed after the completion of the competition using the remaining part of the test dataset.
Track I Submission Format
For every user in the test dataset
, submission files should contain two columns: id and category (the predicted user purchase actions derived by your model).  category should be a nine-length space-delimited list representing whether the users will purchase each items.
The file should contain a header and have the following format:
id,category
1,1 1 1 0 1 0 0 0 0
Track II Submission Format
For every user in the test dataset
, submission files should contain two columns: id and itemids (the best item combination derived by your RL model).  ItemIds should be a nine-length space-delimited list.
The file should contain a header and have the following format:
id,itemids
1,1 2 3 4 5 6 7 8 9