Balázs Hidasi

hidasi_balazs.png

I’m a research scientist working on the field of machine learning. I have 15+ years of experience in designing algorithms.

My research topics include utilizing deep learning for session-based (sequential) recommendations, evaluation of recommender systems, context-aware tensor factorization on implicit feedback data, and more recently counterfactual learning. I was one of the pioneers of deep learning technology for recommender systems and contributed to evangelizing it in the research community.

For the majority of my career, I have been working on algorithms for recommender systems in the industry. Therefore I have vast experience in a wide variety of recommender systems related topics, and my algorithms are designed with efficient resource utilization, scalability and fast training/inference in mind. Moreover, I have been frequently involved in other aspects of the business - beside research and coding - from strategy to product design to leading innovation, allowing me to see the big picture. I have been leading small machine learning or data science focused teams since 2015.

I received my summa cum laude PhD / MSc / BSc from the Budapest University of Technology.

latest posts

Nov 28, 2023 RecSys 2023 overview

selected publications

  1. The Effect of Third Party Implementations on Reproducibility
    Balázs Hidasi, and Ádám Tibor Czapp
    In Proceedings of the 17th ACM Conference on Recommender Systems, 2023
  2. Widespread Flaws in Offline Evaluation of Recommender Systems
    Balázs Hidasi, and Ádám Tibor Czapp
    In Proceedings of the 17th ACM Conference on Recommender Systems, 2023
  3. Recurrent Neural Networks with Top-k Gains for Session-Based Recommendations
    Balázs Hidasi, and Alexandros Karatzoglou
    In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018
  4. Session-based Recommendations with Recurrent Neural Networks
    Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk
    International Conference on Learning Representations, 2016
  5. General factorization framework for context-aware recommendations
    Balázs Hidasi, and Domonkos Tikk
    Data Mining and Knowledge Discovery, 2016
    First online: 07 May 2015
  6. Speeding up ALS learning via approximate methods for context-aware recommendations
    Balázs Hidasi, and Domonkos Tikk
    Knowledge and Information Systems, 2016
    First online: 14 July 2015
  7. Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Implicit Feedback
    Balázs Hidasi, and Domonkos Tikk
    In Machine Learning and Knowledge Discovery in Databases, 2012
  8. ShiftTree: An Interpretable Model-Based Approach for Time Series Classification
    Balázs Hidasi, and Csaba Gáspár-Papanek
    In Machine Learning and Knowledge Discovery in Databases, 2011