Munich Datageeks June Edition

We are incredibly happy to announce our next Meetup on June 22nd at ProSiebenSat.1!

Format:

• 2 talks (each ca. 40 min incl. discussion)
• Time for networking + food + drinks before, in between and after the presentations
• Talks are held in English
• We will be taking photos and/or film footage at the event. These will be used to share news about our meetups, and to publicize upcoming events.

The lineup:

Atef Attia, Malte Blumhoff and Manuel Heller - Evaluating Machine Learning Models at Scale in the Context of TV Advertising

Abstract:
One of our goals at ProSiebenSat.1 Media SE is to support our TV advertising clients in their planning process by providing them with the best selection of advertising slots. To achieve this, we leverage machine learning techniques on our user tracking data to develop a predictive model that estimates the potential website visits generated by future TV spots. In this talk, we will first provide an overview of this compelling use case, emphasizing the importance of the underlying data and machine learning model. Additionally, we will showcase the creation of a state-of-the-art pipeline designed to facilitate large-scale model
evaluation. Lastly, we will delve into the underlying AWS infrastructure that drives this and other AI-driven products developed at ProSiebenSat.1.

Bios:
Atef Attia is a Machine Learning Engineer at ProSiebenSat.1, with over three years of experience in developing innovative AI solutions. He is currently technical lead and actively involved in projects that aim to assist TV advertisers in optimizing and planning their TV advertising campaigns. He holds a Master of Science degree in Computer Science from the Karlsruhe Institute of Technology (KIT), which has equipped him with a strong theoretical foundation in Artificial Intelligence, data science, and machine learning. His passion for AI pushes him to stay at the forefront of technological advances.

Malte Blumhoff joined ProSiebenSat.1 one and a half years ago, right after concluding his Master's degree in Physics at the Ludwig-Maximilians-Universität in Munich. As a Cloud Engineer he is mainly responsible for the Data Lake and Infrastructure with a focus on networking, performance, security and cost optimization in AWS. Furthermore, he is involved in the ongoing Cloud Migration project within the department to enable the teams to leverage the advantages of cloud computing for their daily work.

Manuel Heller: Having completed his Master's degree in Management & Technology with a specialization in computer science and machine learning at the Technical University of Munich, Manuel Heller joined ProSiebenSat.1 two years ago as a Data Scientist. He is mainly involved in projects that aim to assist TV advertisers in optimizing and planning their TV advertising campaigns. Additionally, he contributes to initiatives establishing MLOps within the AI department. Prior to joining ProSiebenSat.1, he gained experience in financial consulting and FinTech
startups.

Second talk:

Furkan M. Torun - How to Build an Open-Source Machine Learning Platform in Biology?

Abstract:
Healthcare is moving towards real personalized medicine, for which complex and large biological datasets called “—omics” (e.g., genomics and proteomics) are crucial to guide medical intervention. However, these data are so extensive that support for interpreting health
and disease states is needed. Although machine learning (ML) has become an indispensable tool for this goal, it is sometimes applied in an opaque and unreproducible manner without applying the best practices of ML. To address issues like reproducibility or transparency and to grant researchers access to ML for their omics datasets without any programming or bioinformatics skills, we developed “OmicLearn” (OmicLearn.org), an open-source, web-based, easy-to-use ML platform.
OmicLearn is tailored to the needs of researchers in the biology and omics fields. It also fosters open and reproducible science via transparent assessment of state-of-the-art algorithms in a
standardized format. This talk is for every scientist and developer who is interested in biology or omics or who wants to learn how to build a machine learning platform from open-source tools.

Bio:
I am a molecular biologist and geneticist with research experience and programming background. After working as a computational biologist and data scientist at a rare disease research laboratory and OmicEra Diagnostics, respectively, now, I am working at a cancer diagnostics
biotechnology company as a Researcher and Data Scientist in Munich.
The underlying ultimate goal of my works is to combine the power of computation with mysterious biological questions to reveal the unknown. So, let’s continue 🧬 debugging DNA software!