This is the implementation of two attentive models forlearning the weights used in the score aggregation method. The models follow the description given in 2 papers namely Attentive Group Recommendation and Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation.

Run the synthetic_movie_dataset notebook to generate a synthetic dataset or add a real one by saving the necessary files as shown in the notebook. Change the models and choose parameters in the models_dev notebook and train the models.