The Budapest BI Forum (@budapestbi) is a well-established data, analytics and BI conference held every November in Budapest, Hungary.
We have been running a machine learning track for years, where technical talks, ML best practices and case studies are presented and discussed.
Machine Learning talks accepted for this year:
- Building AI-based solutions for computer vision problems in the automotive industry – Kurics Tamás, Twinner
- You got served: How Deliveroo improved the ranking of restaurants – Jonathan Brooks-Bartlett, Deliveroo
- Human-Centered Interpretable Machine Learning – Przemyslaw Biecek, Samsung R&D / Warsaw University of Technology
- 5 rules of productive data teams – Török Ágoston, AGT International
- Applications of Graph Theoretic Techniques in Data Driven Merchandising – Alex Trickey, Secret Sauce Partners
- Cutting edge neural architecture optimization in practice – Deák-Meszlényi Regina, Continental Automotive Hungary
- Gradient Boosting Machines (GBM): from Zero to Hero (with R and Python code) – Chief Scientist, Epoch (USA)
- GBM: stories from the trenches – Damien Soukhavong, SAP BI / Data Science Consultant, Planeum
- ML alkalmazása az egyedi vásárlói szándék meghatározására a Magyar Telekom-nál – Erdélyi Balázs, Data Scientist Chapter Lead, Magyar Telekom Nyrt.
A sample of our Machine Learning talks from last year’s BudapestBI 2018:
- Can unsupervised machine learning (UML) help in fraud detection?
- Building content similarity recommenders at BBC
- Machine Learning in Trading
- Prediction versus Causality – What Machine Learning can do and what not?
- How Diageo uses Machine Learning to optimize Finance
- ML supported fuel demand planning in MOL Hungary wholesale
- Identifying and Prototyping Data Science Use Cases
- Automated Machine Learning in practice – Roundtable
Meeting of data cultures
The Budapest BI agenda also include an Rstats, a PyData, Data-Driven Business and a DataViz track, so there’s a great opportunity to also discover new tools, approaches and solutions for data problems similar to yours.
What to do next?