Munich AI Summit 2019. Telefónica Deutschland Team Shares Their Experience of Using AI & Analytics

We continue presenting a series of articles on talks delivered at the Munich-AI Summit 2019 hosted by Develandoo – AI Innovation LAB on October 8th. Our previous article was devoted to the role of women in AI by Vidya Munde-Mueller.

This time we’re going to explore how and what Germany’s biggest mobile telecommunications operator, Telefónica Deutschland is doing in the field of artificial intelligence. Patrick Walch and Laura-Luisa Velikonja will help to understand it by sharing their experience through an interactive talk with demos, codes, and slides.

Patrick is Lead Data Scientist in the Data Analytics & Artificial Intelligence unit at Telefónica Germany. In his studies of Economathematics at Ulm University he specialized in Operations Research, Game Theory and Heuristic Algorithms. After his diploma, he joined the German Research Foundation’s research group “Modeling, Analysis and Simulation in Economathematics” where he was applying Game Theory in Financial Mathematics. After his studies, in 2008 he started working for a Munich based consultancy in data analytics and one of his first projects was for Telefónica Germany. In 2010 he joined Telefónica’s Business Analytics unit as a data analyst, then became the functional lead for analytical models and later manager of the Advanced Analytics & Data Science team. Since July 2016, he holds the position of Lead Data Scientist.

After completing her mathematics degree at the Technical University of Munich, Laura-Luisa Velikonja first learned the craft of data science at Data Science Consultancy Alexander Thamm GmbH. After participating in the TEFDatathon 2016, she moved to Telefónica Germany, where she now works as Senior Data Scientist in the Data Analytics & Artificial Intelligence department. There she supports the internal departments in making data-based decisions and thus generating added value for the company. As a product owner, she manages various data science use cases that detect process errors and anomalies at an early stage. At the same time, together with a colleague, she founded the in-house community TelefónicaConnects to promote gender diversity. The aim of TelefónicaConnects is to further promote the proportion of women, especially in their field, and thus contribute to greater diversity.

10 billion network activities (phone calls, messages, data connections, handover, etc.) and almost 50 million customers. Patrick says Telefónica Germany team is dealing with such numbers on a daily basis, and the numbers rapidly increased in the last 2 years.

‘’We’re about 80 or even more data scientists, data engineers, data analysts and we’re delivering analytical insights all across Telefónica, Germany. We’re trying to read customers’ wishes out of those 10 billion network activities each day’’.

He says during the last 10 years’ period their mission hasn’t changed, instead, the vision has changed a lot due to the greater use of AI.

”Actually, this slide didn’t really change in the last 10 years since I met this company. AI wasn’t there. It was something like descriptive statistics or something of forecasting. And the data part was also smaller. It was like a huge part-internal data and very small part-external data. We were doing measuring, counting and so on, in other words, mostly descriptive. Then a few years later, we came to the next step; advanced analytics. My team was called Advanced Analytics and Models. So we are serving the classical consumer business as well as the partner business, the B2B business, but also like networks, IT, HR, corporate health management, the top management strategy and so on. For example, if the B2C department wants to improve the tariff portfolio, we’re trying to read out of the data what the customers want in their tariff. If the network department wants to optimize the network, we’re reading out of the data where the network should be built”.

He says the good thing about their department is that they don’t just have a vision and a mission, they also have some kind of a roadmap to get from one point to another.

”There are five important steps, five elements on our roadmap from the mission to the vision. There will always be analytical services and consulting. There will always be a department that asks a question that can be solved with descriptive statistics or linear regression where we don’t need a neural network. And we can see from the problem-solving side if we need one or if we don’t. And if we don’t, we don’t use it. We’re using traditional analytical services and consulting. That’s absolutely clear. Then we have the second layer cognitive intelligence platform and a deep learning platform explains Patrick.

So our next speaker Laura further goes deep explaining the anomaly detection process at Telefónica.

This was just a snippet from our speakers’ talk. If you want to learn more about the topic, you can visit our youtube channel where you’ll find the videos of all the Munich AI Summit talks.

We are thankful to all our sponsors (Fujitsu, Women in AI, Liquid Newsroom, Scylla and Urgestain, Wayra Germany), participants and the speakers for attending our Munich-AI Summit 2019, the one and only free event in Munich area related to AI.

As we have already informed, we have many big plans related to this initiative. We’re officially launching AI Summit in different countries. In 2020 our destination is Yerevan, the beautiful capital of Armenia. So stay tuned to our blog where we’ll share further details of our upcoming event.


Develandoo is the leading AI company in Armenia. As an innovation lab, Develandoo has successfully created over 30 products for global enterprises such as KPIT Germany and Welocalize USA.

Develandoo has also incubated three in-house startups which are leading the markets in their areas of expertise:

  1. Scylla – World’s leading gun detection system
  2. Cibola – World’s first in-store analytics system
  3. Protogen – Generic Tabular Data platform

For more information, please visit –




  • Topics:
  • Meetup

Top Stories

High Five! You just read 2 awesome articles, in row. You may want to subscribe to our blog newsletter for new blog posts.