Spaces Talk #1: They took our jobs!

Asparuh Hristov, on 13-07-2020
Category: Blog, Data Science & AI Tags: BigData DataScience Machine Learning forecast

Spaces Summit is our annual internal bol.com conference for IT, by IT, and friends: Two fun days of inspiration, knowledge sharing, bragging, and community. This year we had our first digital version of the summit. My name is Asparuh Hristov and working as a Data Science Craft Lead in the Forecasting team, I keep encountering people that believe Machine Learning can automate all existing jobs, including Data Science itself. I hope that this talk can bring a bit more of understanding what Data Science is, which steps can be automated…

Opening our Data Treasure Chest with Tableau

Peter Brouwers, Peter Paul van de Beek, on 23-04-2020
Category: Podcast Tags: BigData data Business Intelligence BI Tableau Atscale Bigquery

Turning to business analytics this episode, we discover it’s a broad field. Business Intelligence hasn’t been discussed that much yet in our podcast. So, we are excited to learn more. In an earlier episode, we discussed moving our Big Data platform to the cloud. This blog is described how we move our data platform into the cloud. What tools do we need to get the data out and have all our users use it to their advantage? One of the tools is Tableau and together with our guests of the…

Python for Tools, Data Science and more

Peter Brouwers, Peter Paul van de Beek, on 15-04-2020
Category: Podcast Tags: BigData DataScience software engineering python programminglanguage Tools

Let’s look at another programming language we use at bol.com: Python. At bol.com we use Python for Tools, Data Science and more. It has been around since 1991. It was created by a Dutch guy: Guido van Rossum. Its design philosophy emphasizes code readability. The language’s core philosophy is summarized in the document The Zen of Python (PEP 20), which includes aphorisms such as: Beautiful is better than ugly. Explicit is better than implicit. Simple is better than complex. Complex is better than complicated. Readability counts. All well, but what…

Measuring 2.0 – Streaming measurements

Peter Paul van de Beek, Peter Brouwers, on 6-09-2019
Category: Podcast Tags: Web scale Architecture Scalability BigData data Podcast Conversational Measuring recommendations personalization

The big question in this episode is “How can we create 10 million personalized webshops? Tailormade for every one of our customers so it suites their needs best?” In short, the answering is Measuring 2.0. This enables us to measure more accurately how customers are behaving in our webshop. This enables to give them a more personalized experience. We are aiming for a feedback loop of 1 second. So 1 second after and action was performed by a customer in our webshop the data is available for service that handles personalization and recommendations. These…

Cloud as Enabler to become more data driven

Peter Brouwers, Peter Paul van de Beek, on 7-08-2019
Category: Podcast Tags: BigData DataScience cloud Podcast Business Intelligence

Cloud as Enabler to become more data-driven. The adjective data-driven means that progress in an activity is compelled by data, rather than by intuition, personal experience or a gut feeling. Googling data-driven gives you over 637 mln. results so time to add an extra result to this with this episode. But we wanted to make it more specific. We moved our big data into the cloud and we got some nice insights that we wanted to share. We asked our two guests of this episode to do so. It turned…

No more crystal ball for forecasting, data science it is

Peter Brouwers, Peter Paul van de Beek, on 7-05-2019
Category: Podcast Tags: BigData DataScience software engineering Artificial Intelligence Podcast

As long as retail exists, people tried to predict the future. An accurate forecast makes it much easier to buy the correct amount of products from suppliers, know what you need to keep on stock and even know what the sales will do with specific promotions. Over the last couple of years, this domain changed dramatically because of the introduction of Data Science and Artificial Intelligence. In this episode, we chat about this changing playing field to share our experiences with you. Guests Harmen Prins Erick Webbe Hosts Peter Brouwers…

No more crystal ball for forecasting, data science it is

How (not) to sink a data stream to files? Journeys from Kafka to Parquet.

Gabor Hermann, on 30-07-2018
Category: Development Tags: Java Scalability BigData Open source distributed

Last year the Measuring 2.0 team at bol.com has started measuring user behavior on the bol.com website. Of course, we wanted to make the data widely accessible within the whole organization.

Getting organized: cleaning up bol.com with Data Science

Ernst Kuiper, on 20-02-2018
Category: Blog, Data Science & AI Tags: BigData DataScience Machine Learning

Data Science and Machine Learning are becoming more integrated into current businesses. Especially in e-commerce there is huge potential for predictive modeling. It is therefore no surprise that bol.com has given extra focus on significantly expanding its Data Science efforts the coming year. That’s not to say that there aren’t already some interesting Data Science projects running. In this blog post we will take a look at one of the projects I am currently working on with fellow data scientist Joep Janssen: the chunk project.

Big, bigger, scalable

Niels Basjes, on 22-03-2017
Category: Architecture, Development Tags: Scalability BigData

At bol.com we service millions of products to millions of customers, resulting in billions of pages each year. We want to create the most effective service to our visitors we possibly can. So we spent a lot of time preparing the content, monitoring the systems and analyzing how we can support our customers better in finding what they really want.

Nextbuild 2017

On: 20 May 2017 at: High Tech Campus Eindhoven
Category: Events Tags: Event Scalability BigData

On The NextBuild Conference I will host a talk about Designing scalable data intensive applications. At bol.com the datavolumes we need to process exceed the capacity of any single computer. As a consequence we are forced to think about designing our data intensive applications in such a way that they can be run on a cluster of systems and grow to handle much more that the volumes of today. In this talk I will show the main design concepts that bol.com has been using for more than 8 years that are needed to…