Towards the end of 2020, Melissa Perotti and I held a talk on Product Development for Data Science Products at GoDataFest – the (this time virtual) festival of Data Technology. We elaborate on how we follow a 7-phase process to take Data Science projects from idea to prototype and from prototype to production. About the talk In every industry, a remarkably large share of Data Science (DS) projects fail. There are various reasons why DS projects may come to a halt: Data quality or size is insufficient, the model doesn’t…Read more
We use Data Science & AI to give our customers the best shopping experience and customer service.
At this year’s Spaces Summit, I presented a talk on Streamlit: a new web application framework in Python, which is perfect for making data science demos. About the talk As Data Scientists, we often need to quickly prototype ideas and showcase those projects to the business. Yet, Python scripts are not very visually appealing and Powerpoint is not always suitable. You also don’t want to spend weeks setting up that throw-away, unmaintainable Flask application, just for the purpose of showcasing your idea. Fortunately, there’s a solution to all of these…Read more
This year at Spaces Summit, the bol.com annual internal IT conference, I presented a talk about the work our team, Team SmartAds, has been doing in creating a new marketing attribution truth for our platform. About the talk How do we verify that we are using our marketing budget effectively? As bol.com, we are spending a considerable amount of our budget on digital marketing. Because of this, we need to be able to allocate this budget in the most effective, data-driven way possible. The four main methods for determining marketing…Read more
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…Read more
In many systems at bol.com the response speed of our systems is very important. This blog is about the data structures and algorithms we used to make a specific analysis step a lot faster: Finding the longest matching string prefix.Read more
In this post, I will explain how bol.com is going to interpret what the user says using Machine Learning and Natural Language Processing.Read more
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.Read more