CV

Graduate Researcher

Johannes Kepler Universität Linz

Research focus on Recommender Systems, Explainable and Fair AI/ML.

• Developed a novel effective recommendation algorithm and a tool to offer explainable predictions and model's insights.
• Devised a new approach for modular debiasing of latent embeddings of pre-trained ML recommendation models.
• Led 2 funded science-communication projects that resulted in interactive exhibits for thousands of people.

Visiting Student

Technische Universität Berlin

• Awarded 1 of 12 departmental merit-based scholarships
• Developed a SQL query resolution system for Geo-distributed federated databases while enforcing data shipment constraints. Implemented in Java and Apache Calcite.

PhD

Johannes Kepler Universität Linz

Computer Science/AI

• Machine Learning (PyTorch)
• Recommender Systems & Ranking (Collaborative Filtering)
• Explainable AI (Modelling)
• Fairness in ML (Regularization, Debiasing)
• Deep Learning (VAE, Adversarial Networks, ...)

MSc - Graduated with honors

Sapienza Università di Roma

Engineering in Computer Science

• Machine Learning (Python, TensorFlow)
• Big Data (Hadoop, Spark, Flink)
• Natural Language Processing

BSc - Graduated with honors

Università degli Studi di Napoli Federico II

Engineering in Computer Science

• Software Engineering (UML, Design, Analysis, Testing)
• Computer Programming (C, C++, Java)
• Databases (SQL, DBMS)

Black Holes of Popularity at the ARS Electronica Festival 2022

PI role - Project coordination and planning, recruiting, role assignments, and fostering ideas and contributions.

Emotion-aware Music Tower Blocks at the ARS Electronica Festival 2021

Co-PI role - System design, data analysis, tasks assignment, API integration development. Python/JavaScript.

Hassaku, a(nother) research-oriented Recommender System Framework

Data processing, training, testing, hyperparameter optimization, metrics computation, and logging for several Collaborative Filtering-based Recommender Systems. Python/PyTorch.

Modular Debiasing of Latent User Representations in Prototype-based Recommender Systems

Proceedings of 2024 Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD)

A. B. Melchiorre, S. Masoudian, D. Kumar, M. Schedl

ProtoMF: Prototype-based Matrix Factorization for Effective and Explainable Recommendations

Proceedings of the 16th ACM Conference on Recommender Systems (RecSys)

A. B. Melchiorre, N. Rekabsaz, C. Ganhör, M. Schedl

Explainability in Music Recommender Systems

AI Magazine

D. Afchar, A. B. Melchiorre, M. Schedl, R. Hennequin, E. V. Epure, M. Moussallam

Investigating Gender Fairness of Recommendation Algorithms in the Music Domain

Information Processing & Management (IPM)

A. B. Melchiorre, N. Rekabsaz, E. Parada-Cabaleiro, S. Brandl, O. Lesota, M. Schedl

LEMONS: Listenable Explanations for Music recOmmeNder Systems

European Conference on Information Retrieval (ECIR)

A. B. Melchiorre, V. Praher, M. Schedl, G. Widmer

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD)

Main Conference

2nd Workshop on Human-Centric Music Information Retrieval (HCMIR23)

ISMIR 2023 Satellite Event

ACM Transactions on Recommender Systems (TORS)

ACM Conference on Recommender Systems (RecSys)

Main Conference

ACM Multimedia (ACMMM)

Main Conference

Web Conference (TheWebConf)

User Modeling and Personalization

ACM Conference on User Modeling, Adaptation and Personalization (UMAP)

Demo and Late-Breaking Results (2021), Main Track (2020)