Munich Datageeks - December Edition

It is time for our next Meetup. In December, ProSieben Sat.1 will host it for the first time.

Format:

• 2 presentations (each ca. 30-40 min incl. discussion)

• Of course time for networking + food + drinks before, in between and especially after the presentations

• Talks are held in English

The line up:

Martin Preusse & Gökcen Eraslan - Deep modeling of DNA sequences

Abstract:

Ordered sequences of molecules are the central concept of biological information. The DNA is composed of the 4 nucleotides (A, C, G, T) and is used to persist information over generations. Our understanding of these DNA sequences is very limited. We cannot read them like a book, we still have not learned their grammar and vocabulary. Consequently, there is no way to predict the biological purpose of a stretch of DNA from the sequence alone.
Deep learning methods offer new ways to bring light into the darkness of our genome and to elucidate the structure of genes and their regulation. However, the interpretability of deep models and difficulties with modeling long, variable-length sequences hinder the use of deep learning in biology.
We are working on new approaches to deal with these issues. Examples are sequence classification using convolutional neural networks and generative models for variable-length sequences using recurrent variational autoencoders. In this talk, we will give an overview of biological sequences, their fascinating properties and their relevance for disease biology. We will demonstrate some of our methods and their application. Finally, we will show some general ideas drawn from our research which are relevant for other topics.

Bio:

Martin Preusse: PhD in computational biology. Currently working on data solutions for biomedical research at Helmholtz Zentrum München and the startup KNOWING. Using Python and noSQL databases.

Gökcen Eraslan: PhD student in computational biology at Helmholtz
Zentrum München with the main research focus of machine learning
applications to computational biology problems.

Suresh Pillai - Marketing Analytics – Putting the science into data science

Abstract:

Suresh will present examples from his broad experience in Marketing Analytics to demonstrate that creativity and a scientific mindset is required to get closer to the truth with analytics.

· The on-line poker ecosystem: Minnows, Dolphins, & Sharks

· Marketing channel incrementality: It's about the customer, not the channel

· Multi-click attribution: don't be a monkey

· Multiple Scale of Understanding: Attribution, Personalisation, The Customer

Bio:

Suresh leads the Media & Marketing Analytics team at ProSiebenSat.1 Media SE. As ProSiebenSat.1 expands its digital portfolio, Suresh's mandate is to understand in depth the impact of TV advertising on the performance of assets in this portfolio. This includes the interaction of TV with online marketing through complex attribution models.

Prior to this, Suresh led the European Customer Analytics team at eBay. His focus was on optimising customer understanding and customer experience, through CRM and personalisation. In addition, he made substantial contributions to eBay's understanding of attribution and incrementality.

Suresh has over 10 years experience in predictive modeling, social network science, and self-adaptive algorithm design; plus a broad understanding of science, computing, and technology, enabling him to motivate and coordinate diverse teams to analytics innovation. He is always eager to bring a fresh & unique perspective from his background in theoretical physics and complexity sciences.