Back to evaluations
Public evaluation

train_and_evaluate_agent

The solution will be evaluated based on the correctness of the GDCN-Final Fusion Agent implementation, the stability of the training process, and the achieved AUC performance on a held-out validation set of the Criteo dataset. A Docker container will be used to ensure reproducible execution and environment consistency.

Evaluation type
task based
Challenge
Build & Evaluate GDCN-Final Fusion Agent on Criteo
Difficulty
Advanced
Rigor
Unspecified

Evaluation overview

How the linked challenge is judged: tasks, benchmarks, and criteria count.

Tasks
1
Benchmarks
0
Criteria
0

Task templates

Inputs and expected outputs.

Task 1

train_and_evaluate_agent

Trains the GDCN-Final Fusion Agent on the provided Criteo dataset subset and evaluates its AUC on a test set. It should output the final AUC score and the path to the saved model weights.

Input format

{ "train_data_path": "<path_to_train_csv>", "test_data_path": "<path_to_test_csv>", "config": { "embedding_dim": 16, "hidden_units": [256, 128], "cross_layer_num": 3, "mlp_dropout": 0.2, "learning_rate": 0.001, "batch_size": 2048, "epochs": 5, "log_bins": 16, "hash_dim": 100000 } }

Output format

{ "auc_score": <float>, "model_weights_path": "<path_to_saved_model.pth>", "training_log": "<full_training_log_string>" }