What we're about

Hamburg's largest data event. With over 1600 active members and 10 high quality events per year.

The meetup covers everything data related from data bases, data backend to data visualization, machine learning, reinforcement learning, neural nets, deep learning, ai-systems in production.

Feel free to reach out if you like to contribute in some way. This is a truly community project in Hamburg. Without you this event wouldn't be that great!

Upcoming events (4)

Data Science Meetup Hamburg

Neustädter Neuer Weg 22

!!! New Location @ better.group !!! === Doors open @ 6:30 === === Networking === === Small intro === === Break & Networking === === Talk 1 === RLgraph: Robust, incrementally testable reinforcement learning by Kai Fricke, Postdoc @ Helmut-Schmidt-Universität Hamburg. In this talk, we will introduce RLgraph, a modular reinforcement learning library. Utilizing a strict separation of concerns, RLgraph makes it easy to build, test and debug reinforcement learning algorithms, or to just use well-tested off-the-shelf algorithms for optimization problems. This talk will introduce the library, discuss the challenges we faced implementing the library, and touch the topic on how you can extend the library to fit your needs. === Talk 2 === Fabian Braun Algorith Egineer at MOIA on features beat algorithms - Improving Card Fraud Detection through Suspicious Pattern Discovery In this talk we will introduce the topic of credit card fraud from a data science perspective. Then we show how frequent pattern mining can be used to improve card fraud detection. According to our hypothesis fraudsters use stolen credit card data at specific, recurring sets of shops. We exploit this behavior to identify fraudulent transactions. In a first step we show how suspicious patterns can be identified from known compromised cards. Then we define new attributes which capture the suspiciousness of a transaction indicated by known suspicious patterns. Eventually a non-linear classifier is used to assess the predictive power gained through those new features. The new attributes lead to a significant performance improvement compared to state-of-the-art aggregated transaction features. Our results are verified on real transaction data provided by our industrial partner. === Networking === === Closing ===

Data Science Meetup Hamburg

Needs a location

=== Doors open @ 6:30 === === Networking === === Small intro === === Break & Networking === === Talk 1 === Andre on graph databases === Talk 2 === Boris Pyakillya Guest Researcher, German Research Center for Artificial Intelligence Senior Data Scientist, Center of Financial Technologies "Multi-agent Reinforcement learning: past, current, future" Multi-agent Reinforcement learning (MARL) is a very hot topic now, where current AI well-known companies (DeepMind, OpenAI) and numerous research groups worldwide try to suppress human performance in the very complicated environments, like DOTA and Starcraft, where there is a competition between AI agents and human players. The task is hard by many reasons, some of them are coordination between AI agents inside the group and how not to fall into local agent's group behavior and forget about long-term goals. There are many methods to deal with this, and every one has its own advantages and disadvantages. I want to shed some light on these issues and to talk about how it started, how it goes and how it will go. === Networking === === Closing ===

Data Science Meetup Hamburg

Needs a location

=== Doors open @ 6:30 === === Networking === === Small intro === === Break & Networking === === Talk 1 === Roman Atachiants Principal Software Engineer at @Grab Singapore === Talk 2 === Dr. Alexander Motzek, Technology Consultant at Lufthansa Industry Solutions: „How AI Understands Flight Attendance Feedback“ We have developed an artificial intelligence (AI) that interprets multilingual feedback comments from flight attendances to gain valuable insights and to identify customer pain points automatically. The business case, development, processes and insights around this AI are presented in this talk. === Networking === === Closing ===

Data Science Meetup Hamburg

Needs a location

=== Doors open @ 6:30 === === Networking === === Small intro === === Break & Networking === === Talk 1 === Asma? === Talk 2 === === Networking === === Closing ===

Past events (28)

Data Science Meetup Hamburg

jimdo

Photos (78)