Pareto Front Approximation for Multi-Objective Session-Based Recommender Systems
This provides a flexible tool for businesses needing to balance multiple recommendation objectives in session-based systems, though it appears incremental as it adapts existing techniques to this domain.
The paper tackles the problem of optimizing multiple objectives in session-based recommender systems by introducing MultiTRON, which adapts Pareto front approximation techniques using a transformer neural network. The results show the model effectively manages trade-offs between metrics like click-through and conversion rates, with a single model accessing the entire Pareto front for flexibility.
This work introduces MultiTRON, an approach that adapts Pareto front approximation techniques to multi-objective session-based recommender systems using a transformer neural network. Our approach optimizes trade-offs between key metrics such as click-through and conversion rates by training on sampled preference vectors. A significant advantage is that after training, a single model can access the entire Pareto front, allowing it to be tailored to meet the specific requirements of different stakeholders by adjusting an additional input vector that weights the objectives. We validate the model's performance through extensive offline and online evaluation. For broader application and research, the source code is made available at https://github.com/otto-de/MultiTRON. The results confirm the model's ability to manage multiple recommendation objectives effectively, offering a flexible tool for diverse business needs.