Advanced Recommender System

Jun 20, 2025 · 1 min read
System Architecture
projects

This project was developed within the CESMA Master’s program in collaboration with TIM. Instead of framing the problem as a standard classification task, the system was designed as a learning-to-rank pipeline for next-best-action recommendation.

That shift in framing matters because ranking is closer to the actual business decision: not just whether an action is good or bad, but which action should come first for a given user.

The pipeline combines careful validation, Bayesian optimization, and ensemble ranking strategies. The end result is a substantial improvement over baseline performance on NDCG@5, making the project a solid example of applied machine learning under realistic evaluation constraints.

Performance summary:

StageNDCG@5 ScoreImprovement vs Baseline
Baseline Model0.5030
Best Single Model0.6838+35.94%
Best Ensemble0.6852+36.23%

Overall, it is one of the clearest examples in the portfolio of taking a familiar ML task and reformulating it in a way that is better aligned with the actual decision problem.

Stefano Blando
Authors
PhD Student in Artificial Intelligence
Stefano Blando is a PhD student in the National PhD Program in Artificial Intelligence at Scuola Superiore Sant’Anna and the University of Pisa. His research lies at the intersection of AI, agent-based modeling, and economics. He studies adaptive multi-agent systems, statistical verification of economic simulations, and robust quantitative methods for financial and socio-economic data.