Predicting Group Choices from Group Profiles

TL;DR

This paper tackles predicting a group’s final choice from observed individual preferences by learning a mapping from group profiles to choices, inspired by Social Decision Scheme. It introduces a Learning-based Choice Prediction (LCP) model that uses machine learning to map aggregated group profiles to predicted group choices, and it augments training data with synthetic profiles (Winners and Permutations) to address data scarcity. Empirical results on travel destination decisions show that LCP consistently outperforms traditional PACP baselines, remains robust under missing data, and even surpasses human performance in predicting group choices, with augmentation further improving accuracy and distribution alignment. The findings suggest practical benefits for group recommender systems, enabling faster convergence to decisions and enabling more nuanced recommendations around the predicted group choice.

Abstract

Group recommender systems (GRSs) identify items to recommend to a group of people by aggregating group members' individual preferences into a group profile, and selecting the items that have the largest score in the group profile. The GRS predicts that these recommendations would be chosen by the group, by assuming that the group is applying the same preference aggregation strategy as the one adopted by the GRS. However, predicting the choice of a group is more complex since the GRS is not aware of the exact preference aggregation strategy that is going to be used by the group. To this end, the aim of this paper is to validate the research hypothesis that, by using a machine learning approach and a data set of observed group choices, it is possible to predict a group's final choice, better than by using a standard preference aggregation strategy. Inspired by the Decision Scheme theory, which first tried to address the group choice prediction problem, we search for a group profile definition that, in conjunction with a machine learning model, can be used to accurately predict a group choice. Moreover, to cope with the data scarcity problem, we propose two data augmentation methods, which add synthetic group profiles to the training data, and we hypothesize they can further improve the choice prediction accuracy. We validate our research hypotheses by using a data set containing 282 participants organized in 79 groups. The experiments indicate that the proposed method outperforms baseline aggregation strategies when used for group choice prediction. The method we propose is robust with the presence of missing preference data and achieves a performance superior to what humans can achieve on the group choice prediction task. Finally, the proposed data augmentation method can also improve the prediction accuracy.

Figures (7)

• Figure 1: Schema of GRSs that utilize either standard preference aggregation strategies (lower workflow) or ML models (upper workflow). In the preference aggregation-based approaches, the system receives the individual rating (actual or predicted) as input to construct group profiles, by using a preference aggregation strategy. The constructed group profiles contain predicted group scores for the options ($o_1, o_2, o_3,$ and $o_4$). This group profile is used by the group recommendation algorithm to generate recommendations. In ML-based approaches, the system leverages individual ratings and group scores as input to construct the embedded group profile. Embedded profiles are defined by latent features (e.g., LF1, LF2, and LF3). The embedded group profile, in addition to group scores, is used by the group recommendation algorithm to generate recommendations.
• Figure 2: The logical schema of the proposed approach for learning the group choice from the group members' individual ratings of the considered options.
• Figure 3: Comparison of the accuracy of the LCP and PACP variants. As indicated in this figure, LCP-AVE outperforms the other LCP and PACP variants. Additionally, for all variants, LCP-* outperforms the corresponding variant of PACP.
• Figure 4: PACP and LCP accuracy in predicting groups' choices when some of the group members' ratings are not available (sparse user-option matrix). The x-axis in this figure indicates the actual sparsity of the generated user-option matrix, i.e., the percentage of ratings that were not present in the rating matrix.
• Figure 5: User study GUI where the group members' ratings for ten options are displayed and the subject can select the option that they believe could be the group's final choice.