24 Aug 2026
Three lessons from our AI projects
What we learned from dozens of AI projects: start with the decision, treat data quality as an organisational issue and arrange management in advance.
Latest blog posts,
What catches our eye in data and AI, and what you can do with it.
18 Aug 2026
From pilot to production: why most AI projects stall
Most AI projects stall not because of the technology, but because of data, teams and processes. Read what it takes to move from pilot to production.
25 Jun 2026
Responsible AI: from principles to practice
AI is developing rapidly. New models emerge almost every week, and more and more organisations are experimenting with AI.
12 Mar 2026
GACS explained: building data and energy management
Buildings generate increasing amounts of data. Energy flows, climate data and the status of building systems are often already available.
22 Dec 2025
An AI Christmas card as a gift from Data Science Lab
This Christmas card generator was developed by Data Science Lab, a data and AI partner for organisations making a difference with AI.
11 Nov 2025
Demand forecasting that works
Discover how demand forecasting with state-of-the-art algorithms helps organisations optimise inventory, costs and profits.
10 Nov 2025
Why your forecasting model is accurate, but your stock levels aren't.
Building a good forecasting model is one thing, yet a product still goes out of stock or the warehouse ends up full. Where does it go wrong?
18 Sep 2025
GenAI in fashion: from photoshoot to campaign in minutes
Fashion industry, take note: realistic backgrounds, outfit changes and fully generated campaigns are possible with AI.
31 Jul 2025
AI in the cultural sector: time for a data-driven approach
At DSL, we help the cultural sector work in a data-driven way. Not as a one-off project, but as an integral part of the organisation.
29 Jul 2025
From hype to value: how to keep GenAI realistic and relevant
Since the launch of tools such as ChatGPT, interest in generative AI (GenAI) has been enormous. The applications seem endless: from content generation and software development to strategic analysis. The rise of generative AI (GenAI) and large language models (LLMs) has fundamentally changed the data and technology landscape. But where buzzwords thrive, unrealistic expectations arise too. And that’s exactly...
17 Jul 2025
Working efficiently with MLflow 3.0
MLflow 3.0 was recently released with new features, including GenAI and LLMs. Read about all the changes here.
1 Jul 2025
AI in the legal profession: if you don’t act now, you’ll fall behind
AI and data-driven ways of working in the legal profession. How can you put them into practice? Explore the first steps and use AI to strengthen your firm.
27 Jun 2025
GenAI opportunities you can make the most of today
GenAI - the opportunities it offers. Which ones can you make the most of today? Want personalised advice? Get in touch.
10 Jun 2025
PySpark basics: upserting data on Databricks
In this blog, Tim (Data Engineer) explains how data engineers and data scientists can move from pandas to PySpark. Although the two libraries have similar syntax, there are important conceptual differences, especially when processing large volumes of data through distributed computing. How...
21 May 2025
AI in healthcare: opportunities and challenges
AI can help make healthcare smarter, more efficient and more personalised. But how do you put AI into practice? And what challenges do we face?
10 Apr 2025
Data & hops: brewing another data-driven beer sensation with Uiltje
Four years after brewing the first Dutch data-driven beer, Brouwerij Uiltje and Data Science Lab are joining forces again. This time, there’s an innovative twist: two hyperlocal beers tailored to the taste preferences of people in Haarlem and Amsterdam. By combining advanced data analysis with the expertise of local specialists, the result is...
4 Apr 2025
Managed DevOps Pool - Efficient and secure DevOps pipelines?
A Managed DevOps Pool is an ideal solution for managing the infrastructure you need to run a DevOps pipeline. No hassle maintaining servers or machines – Azure handles that. You can run your pipelines on your own compute resources and focus entirely on development and deployment. Why...
28 Feb 2025
Deep dive into DeepSeek
DeepSeek is the latest LLM competitor. What does its technical architecture look like? And why are these models so efficient and fast?
25 Feb 2025
CLIP - The AI that connects images and language
CLIP is a model that understands images without specific training for each category. An AI that connects images and language.
13 Feb 2025
Key insights from the AI Action Summit in Paris
The key insights from the AI Action Summit for your organisation. We’ve brought them together for you.
17 Dec 2024
Create your personalised AI Christmas card in one click
UPDATE 2025: We've made an AI Christmas card generator for you again this year. 👉Click here to create your Christmas card! You know how it goes: Christmas is coming, and once again you've left it too late to send Christmas cards. Meanwhile, your parents, Aunt Jannie and your colleagues are sending you all kinds of GIFs and twee Christmas videos. But...
6 Dec 2024
Reducing churn - with insights from a churn analysis
Why is reducing churn so important? Churn has a direct negative impact on your organisation’s revenue and profitability.
15 Nov 2024
GenAI in your organisation: Internal LLMs and the power of RAG
Discover how internal Large Language Models (LLMs), combined with Retrieval-Augmented Generation (RAG), create value for organisations.
28 Oct 2024
Model monitoring: maximise your models’ performance
Discover how effective model monitoring within an MLOps cycle keeps your ML models reliable and accurate. With practical tips!
18 Sep 2024
The future of the F&B industry: using data to distinguish between looking good and being good.
In the competitive world of food and supplements, data offers brands unprecedented opportunities to stand out. For brands focused on transparency, sustainability and innovation, data is not just a tool: it drives strategy and growth. With the right data insights, F&B brands can: Predict consumer preferences Optimise the supply chain Promote transparency: ...
11 Jul 2024
The power of data strategy
You know your organisation needs to do something with the data it has. We often hear: “Maybe we should do something with data.” But how? Where do you start? Every organisation has data, but what really matters is what you do with it. The bigger question For us, it starts with the bigger...
7 Jun 2024
Computer vision on a farm?
The Floating Farm in Rotterdam is the world’s first floating farm. Its priorities are animal welfare, circularity, sustainability and innovation. We wanted to explore what you can do with computer vision on a farm. The aim? To understand the feeding process so we can optimise it and ultimately prevent feed waste. Time to get started and collect data...
7 Jun 2024
How do you choose the right LLM for your organisation?
Large language models (LLMs) such as ChatGPT are popular, not only for personal use but also within organisations. It’s easy to see the value of using these models to search company documents for specific information, summarise large volumes of text or process customer data more efficiently. But can you simply use LLMs in your organisation...
15 Feb 2024
The importance of data-driven working
Why data-driven working is about more than dashboards: culture, decision-making and the first steps towards a data-driven organisation.
29 Jan 2024
Computer vision: the line between humans and computers is blurring
Computer vision enables computers to understand images. The techniques behind image recognition and what organisations can do with it today.
18 Jan 2024
DSL Pilot: A battle between GitHub Copilot and Codeium
We tested AI coding tools for you. What began as a pilot with GitHub Copilot soon became a battle between Copilot and Codeium. Curious which one our team thinks wins? >
13 Jan 2024
Fokker X Data Science Lab
This series is for data professionals, by data professionals. We talk to data professionals, managers or founders at our partner organisations about the data challenges they face. We look back and look ahead. Where are the opportunities for data science? And how does Data Science Lab help? Find out here. We kick off...
28 Nov 2023
Use LLMs to share knowledge within your organisation
How can you use LLMs to make internal knowledge easy to find and use? Explore knowledge assistants, RAG and the first steps in your organisation.
26 Sep 2023
Predictive Maintenance
Machine maintenance is vital for many organisations, particularly in aerospace. Airlines spend a substantial share of their total operating costs on maintenance, repair and overhaul (MRO). According to the International Air Transport Association[1] (IATA), global aviation is expected to double over the next twenty years. This will...
21 Sep 2023
DSL pilot: GitHub Copilot
GitHub Copilot is a hot topic among developers, and at DSL we can’t ignore it. As data enthusiasts, we’re always looking for innovative tools to improve our work and use data more intelligently. That’s why we’re testing GitHub Copilot for you this month in our GitHub Copilot pilot.
15 Sep 2023
From a pilotage trip to predictions
Together with Fenna Miedema, my fellow data scientist at Port of Amsterdam, we went on a pilotage trip. We are working on a project to predict shipping traffic, focusing on the arrival and departure times of large seagoing vessels. If we can predict these accurately, we can optimise our services and, among other things, reduce delays in...
30 Aug 2023
AI in Retail
It is hardly news that bricks-and-mortar retail is under pressure. Consumers are rapidly moving from physical shops to online stores, forcing physical shops to compete with online businesses that can offer products anytime, anywhere, at low or lower margins. Bricks-and-mortar retailers need to optimise their processes...
20 Jan 2022
Adding machine learning to your apps? 5 reasons why!
Already have an app but want to get more out of it? We’re seeing machine learning used more and more in app development, for these 5 reasons: 1. Up to date and more intelligent Your app stays up to date because machine learning models can process the latest data straight away. This makes your...
6 Jan 2022
The origins of data visualisations
These days, everyone is a bit of a data analyst. At primary school, you learn to read and fill in tables. At secondary school, drawing line graphs is often one of the first things you learn in maths. But even outside school or work, you encounter data visualisations every day; on the news, there are almost...
30 Dec 2021
Introducing Skippa
Summary Every data scientist is probably familiar with pandas and scikit-learn. The usual workflow starts with cleaning data in pandas, followed by further pre-processing using pandas or scikit-learn transformers such as StandardScaler and OneHotEncoder. Then you move on to a machine learning algorithm (scikit-learn). There are a few problems with this workflow: 1....
21 Dec 2021
All about the Data Driven NEIPA
Fully data-driven beer: the data-driven NEIPA The first fully data-driven beer is here. Uiltje Brewing Company and Data Science Lab have worked together to develop the perfect – data-driven – New England India Pale Ale.Would you like to taste the beer? Would you like to try it and see whether it really is the perfect NEIPA for you...
17 Dec 2021
Meet the data-driven NEIPA
The first fully data-driven beer is here. Uiltje Brewing Company and Data Science Lab have worked together to develop the perfect – data-driven – New England India Pale Ale. Beer is often brewed on instinct, drawing on a brewer’s knowledge and skill, and sometimes a little luck, but that is not the case for...
15 Nov 2021
Buddyhuis app is live
Finding love through apps like Tinder, Happn or Grinder is now as normal as meeting someone in the pub. During the first wave of COVID19, Femke Riel, a buddy and founder of Buddyhuis, thought: surely this should be possible for people going through the same thing — or rather, for buddies. Digital contact between people with cancer who understand each other,...
21 Sep 2021
Het Digitale Buddyhuis
When you hear you have cancer, your world is turned upside down. That was true for Femke Riel too. A few days after her diagnosis, she sat anxiously in the waiting room at St. Antonius Ziekenhuis, waiting for her MRI scan results. Hester was there: ‘a radiant woman wearing a cap’. ‘She had such a positive...
17 Aug 2021
Gender Data Bias
Data plays an increasingly important role in our lives. Personal, business and even policy decisions are increasingly made by algorithms. But surely an algorithm with hardly any human involvement can’t be ‘biased’? Unfortunately, it can. Every algorithm is based on certain assumptions. Algorithms are...
17 Aug 2021
Viral Escape
We're almost there. By now, almost everyone in the Netherlands has had the chance to get vaccinated, the 1.5-metre distancing rule is being lifted and the government aims to lift the other measures too. That sounds like the end of COVID-19, doesn't it? Or does it? Unfortunately, SARS-CoV-2 (the coronavirus that causes COVID-19...
17 Aug 2021
Super-resolution
If you watch series such as CSI, you’ll recognise scenes like this: detectives are on the perpetrator’s trail and look expectantly at security camera footage. At first glance, the footage doesn’t seem to show the information they need, but then they spot a barely visible detail. They zoom in, enhance...
11 Aug 2021
Automotive
In recent years, the automotive industry has had access to vast amounts of data in many forms. This ranges from inventories of specific cars to in-car sensor data collected to provide information. More and more car manufacturers use this data to develop smarter, more efficient cars. This is reflected not only in the futuristic design of...
13 Jul 2021
Predicting Formula 1 races
As a Formula 1 fan, I spend every race weekend on the sofa, on the edge of my seat. Of course I’m cheering on Max Verstappen, but I’m also trying to beat my family at NU.nl’s GP game. Although I’m certain I’m the biggest Formula 1 expert in my family, I often let maths give me a...
28 Jun 2021
The power of embeddings
Natural Language Processing (NLP, also known as text mining) is an umbrella term for techniques used to extract insights from text data. These techniques have been applied in practice with varying degrees of success. In recent years, rapid advances in neural networks (particularly by tech giants such as Google) have led to several significant breakthroughs. What’s behind this...
21 Jun 2021
Ethics in AI
AI systems are now so widespread and embedded in everyday life that we often overlook the need for interaction between people and algorithms. Algorithms shape your social media feed, tell you what to buy next on Amazon and show you the best way to get from A to B. There is a lot of trust in AI, but is...
17 May 2021
Explainable AI: explained
Imagine your mortgage application is rejected. The first question you would probably ask is: why? A mortgage lender can explain why you do not meet the requirements for a mortgage. But what if that decision is made by a machine learning model? We won’t settle for “computer...
4 May 2021
Data Driven Double IPA
Data-driven beer? Brewing a data-driven beer? That will probably raise plenty of questions. Is the beer brewed by computers? Is it even drinkable? Brewing beer is a craft — shouldn’t we leave it to brewers? No worries, grab a drink: this blog looks at the beer that’s being...
13 Apr 2021
Slippery rails
Detecting slippery rails with Real Time Monitoring. Two months ago, the Netherlands had become a winter wonderland. We finally had the chance to go ice skating again, throw snowballs or build a snowman. Unfortunately, this weather also brings risks: taking a bend on your bike beside an icy canal, or getting to the supermarket without a scratch. But you...
7 Dec 2020
Pharmaceuticals
AI in the pharmaceutical industry Healthcare is becoming increasingly complex with the arrival of new treatments, changing roles for healthcare professionals, new laws and regulations, and payment models. Artificial intelligence (AI) is also being used more often. The applications that result can often perform one specific healthcare task effectively. In many cases, this task is already...
23 Nov 2020
Data Science 3.0 with MLOps
Implementing MLOps MLOps is a relatively new term that has been appearing more and more often lately. And for good reason! Given the current state of data science, it is a useful way to make data science processes more effective, efficient, secure and reliable. Sounds interesting, but what exactly is MLOps, how does it work and how...
4 Aug 2020
Deep dive into GANs
This dog does not exist Generating people, animals, B&Bs or art with AI is one of the many interesting developments in machine learning. The neural networks used on these websites are Generative Adversarial Networks, also known as GANs. The idea behind GANs was developed in...
12 of 57
Sign up for our newsletter.
Want to be the first to hear about a new blog post?
Thanks for signing up!