image

3 Presentation Learnings from Teaching

Coding with kids in the IMC Weekend School

What can we teach children? Or what can they teach us? I asked myself the first question when I joined the IMC Weekend School for my lessons on coding. Without knowing, these students actually taught me about interaction, communication, and underestimation. Three learnings I took from this experience that help you become a better presenter.

» Read on Medium

Engineering local recommendations leveraging HEINEKEN’s global scaleThe HEINEKEN Company is innovating its 157 years old business with data and analytics. Recommendation systems increasingly support our business processes by filtering information for...

Engineering local recommendations leveraging HEINEKEN’s global scale

The HEINEKEN Company is innovating its 157 years old business with data and analytics. Recommendation systems increasingly support our business processes by filtering information for insights. For example, a system for our sales squad in advising bars on their beer portfolio. However, our international scale is both a benefit and a challenge. Our goal is to leverage our international presence and harmonize the recommender infrastructure across subsidiaries. With the Machine Learning Operations method, we create standardized recommender systems on the Azure platform. A culture of self-service, automation, and collaboration enables us to scale recommender systems to local subsidiaries fast. This work was accepted to the RecSys conference.

Keep reading

How I Tricked AFC Ajax while Buying Champions League TicketsCybersecurity Risk Analysis of the Ticket Shop
My football team AFC Ajax enjoys successful years hence the demand for tickets is high. I strongly believe that these seats should be...

How I Tricked AFC Ajax while Buying Champions League Tickets

Cybersecurity Risk Analysis of the Ticket Shop

My football team AFC Ajax enjoys successful years hence the demand for tickets is high. I strongly believe that these seats should be affordable and available to real fans. AFC Ajax sells their tickets under a policy via its website, a combination of systems with increasing complexity. Before the 2018–2019 UEFA Champions League matches, I decided to test the security of this ticket shop. With success, I was able to buy more tickets than allowed. A security risk analysis of the vulnerabilities that is relevant in the design of various cloud architectures.

» Read on Medium

Beer & DataInsights using Untappd, Neo4j, Datawrapper, Pandas & Jupyter
Friday drinks are something special on the 3rd floor of RTL Netherlands. That’s where the Data Intelligence team and other colleagues usually gather for the Beer Club. Every week...

Beer & Data

Insights using Untappd, Neo4j, Datawrapper, Pandas & Jupyter

Friday drinks are something special on the 3rd floor of RTL Netherlands. That’s where the Data Intelligence team and other colleagues usually gather for the Beer Club. Every week we share a great new beer. Now 134 beers and counting. Great material for a fun data project! In this blog, I use Jupyter notebook to enrich the dataset with Untappd, analyze with Pandas, visualize with Datawrapper, and explore with Neo4j. The Jupyter notebooks are available on GitHub.

» Read on Medium

Exploring videos with multimodal AITeam RTL @ ICT with Industry workshop
What happens when academia and industry meet for a hackathon? Next week, a new edition of the ICT with Industry workshop will take place. We thought this would be a good moment...

Exploring videos with multimodal AI

Team RTL @ ICT with Industry workshop

What happens when academia and industry meet for a hackathon? Next week, a new edition of the ICT with Industry workshop will take place. We thought this would be a good moment to look back at last year’s workshop. During the 2019 workshop team RTL developed a prototype that improves the search-ability of news videos. A talented team of computer vision researchers extracted multimodal semantics with deep learning, created a search engine, and enabled interactive exploration. It was a week filled with die-hard coding and fun side-activities.

» Read on Medium

RTL at the Spark+AI SummitHow Data is Transforming the Dutch Media Industry
Amsterdam hosted “2.300 data scientists, data engineers, and global business leaders from 63 different countries” for this year’s Spark+AI Summit Europe. A three-day event...

RTL at the Spark+AI Summit

How Data is Transforming the Dutch Media Industry

Amsterdam hosted “2.300 data scientists, data engineers, and global business leaders from 63 different countries” for this year’s Spark+AI Summit Europe. A three-day event with great keynotes, selected community talks, hands-on tutorials, and training sessions. The stage for the latest developments on powerful data tools like Spark, MLflow and Koalas. Sharing knowledge and meeting new people around the corner in our capital.

RTL Netherlands was present with multiple colleagues and data scientist Maurits van der Goes shared our work in the talk ‘How data is transforming the Dutch Media Industry’, part of the AI Use Cases track. It was a behind the scene look with five use cases, including technical details, drawbacks, and challenges.

» Read on Medium

Spark Summit 2018 — 10 Key TalksIn San Francisco I attended the Spark Summit 2018. It’s a candy store for data engineers and scientists, because Apache Spark is a powerful open-source cluster-computing framework. It enables my colleagues and me to...

Spark Summit 2018 — 10 Key Talks

In San Francisco I attended the Spark Summit 2018. It’s a candy store for data engineers and scientists, because Apache Spark is a powerful open-source cluster-computing framework. It enables my colleagues and me to solve complex machine learning problems at RTL. Spark splits jobs into multiple tasks, which results in ‘embarrassingly parallelism’. Originally it was developed by Matei Zaharia around the corner at the University of California, Berkeley. Now it is maintained by Apache, with Databricks as an important contributor.

Spark is popular, proven by a record number of 4000 attendees. Actually the event was called the Spark+AI summit this year, but let’s skip the buzzwords before it’s called the Spark+AI+Blockchain+AutonomousVehicles+… Summit.

The Moscone Center was the theatre of 191 talks in 2 days. Creating a classic fear of missing out. Luckily, all talks are recorded and available online. It was hard to compare many great talks, but these are my favourite ten, in alphabetical order.

Keep reading

My takeaways from Netflix’s Personalization Workshop 2018For the third time Netflix organized its Personalization, Recommendation and Search Workshop. It was awesome to get invited for this event during my tech holiday in the San Francisco Bay Area....

My takeaways from Netflix’s Personalization Workshop 2018

For the third time Netflix organized its Personalization, Recommendation and Search Workshop. It was awesome to get invited for this event during my tech holiday in the San Francisco Bay Area. The experienced data scientists from all over Silicon Valley and beyond made it a knowledge-rich day. With detailed presentations speakers from i.a. Google, Microsoft, Netflix, Spotify, and University of Minnesota shared how to understand and serve your users better. There was one subject that all speakers agreed on: classic matrix factorization (collaborative filtering) reached its expiration date. This blog captures my takeaways on their different approaches for its successor. This includes challenges of multi-armed bandits, an implicit feedback approach, top-N ranking techniques, tyranny of the majority and algorithmic bias.

Keep reading

Waarom ik juist voor data bij RTL koosIn eerste instantie waren mijn vrienden verbaasd toen ik met een technische achtergrond bij RTL ging werken. Ze dachten bijna dat ik een rol naast Lieke van Lexmond in de spotlights ambieerde. Voor velen mogelijk...

Waarom ik juist voor data bij RTL koos

In eerste instantie waren mijn vrienden verbaasd toen ik met een technische achtergrond bij RTL ging werken. Ze dachten bijna dat ik een rol naast Lieke van Lexmond in de spotlights ambieerde. Voor velen mogelijk onbekend, maar achter de schermen steunt RTL al stevig op technologie.

Keep reading

Creating the Best Team Ever with Collaborative Filtering

During Neo4j’s GraphConnect Europe 2016 conference I presented the proposed recommender systems of Part-up. This project is also my graduation research at Delft University of Technology. I designed and developed a recommender system with collaborative filtering algorithms. Running on a Neo4j database and GraphAware engine. The presentation included the architecture, collaborative filtering algorithms and user insights. 

» Questions: @vanderGoes & m@vdgo.es
» Slides