I was happy to be invited at Frankfurt Data Science meetup to talk about data science, meetups, and how to build a data science-oriented startup. The event was held at Frankfurt School on March 1st, 2018. In my talk I gave an overview of the meetup scene in Amsterdam, briefly presented Amsterdam Data Science and its activites, and then I shared my experiences on founding and developing 904Labs, before I delved into one of my favorite topics: machine learning and search.
It was a packed room, with more than 200 registered people for the event, and the talk was broadcasted live on YouTube. There will soon be a video, which I will share here. The audience was from diverse backgrounds, and I enjoyed the interactions very much. I was happily surprised by the professional organization of the event, and the ambition for making Frankfurt one of the leading centres in data science in Europe. All the best to the organizers and I hope to see more collaboration on data science between Frankfurt and Amsterdam in the near future!
The talk is online on YouTube (thank you Frankfurt Data Science for making this happen!):
Emakina, one of the largest web agencies in Europe, works with internationally acclaimed brands on their branding and electronic presence. To keep their customers ahead of the curve, Emakina has recently started a series of meetups where experts in a wide range of fields come and talk about the latest developments in their field. The last meetup was held last Thursday, 8 February 2018, and with the topic: “A.I. for Commerce”, three talks were scheduled: one from Emakina, one from 904Labs, and one from Salesforce.
In our talk, I described the importance of search in e-commerce by giving examples of failed searches in a number of settings, from finding advertized items using onsite search to mobile search. I followed by with why people choose Amazon to start their product search and highlighted that 54% of them choose Amazon because of their great search functionality–that is the reason number five for people to go to Amazon. Then, I explained why optimizing the ranking manually is close to impossible for humans by laying out the insane amount of options available and enumerating the search space (which can be at millions of millions of choices). With this as foundation, I talked about machine learning and the particular type of machine learning that we use at 904Labs for optimizing search rankings in real-time. I followed up with describing our query intent engine, which is powered by 904Sense, and our automatic synonym extraction engine. In my conclusions, I re-iterated that A.I. for Search can boost search-driven revenue by 30% and that search is becoming part of platforms. In this angle, it is important for online retailers to test the claims of their vendors by doing A/B tests before they opt in for a solution.
I was happy to be invited at the Amsterdam City A.I. Event on December 11, 2017. My talk revolved around our experiences at 904Labs in building a A.I. focused company. It was fun to be among A.I. enthusiasts and to see that people identified with our experiences–which means that we are on good track!
The talk is online on YouTube (clicking the link will start at my talk):
eci is one of the largest online book specialists in the Netherlands and Belgium, with an estimated yearly revenue of 15m euro for the Dutch part. For their site search, eci relied on a manually optimized Apache Solr, integrated into Intershop.
During a three-week A/B test we’ve shown a 38% improvement in revenue and a 34% increase in conversion rate compared to the in-house Apache Solr search engine. This shows once more that adding A.I. to your search engine really makes a difference! Read the full story here.
AI2Future is a local, Croatian, initiative for disseminating the importance and for grounding the use of Artificial Intelligence. The conference brings together researchers, A.I. start ups, and large corporates from all around Croatia to share experiences and learn from each other on what A.I. can and cannot do.
I was invited to give one of the two keynote talks. The first keynote focused on conversational agents and natural language processing and mine followed up with insights how search powers a large spectrum of applications from search, question and answering, and recommendations. I focused on the work we do at 904Labs and illustrated the principles of online learning to rank through real-world examples from our experimences with our customers.
I got many questions after the talk which is a sign that the audience understood the topic and was intrigued by what A.I. can do for search. Some of the questions were brought to the following breaks with some of them leading to follow up meetings in the next days.
I much enjoyed the conference, and I hope that the organizers will follow up with another version next year. I believe that we do need more of this type of initiative to disseminate what A.I. is and A.I. can and cannot do so that organizations shape a better picture of how they can use it to solve challenges that they face.
I’m happy to share some great results with regards to the utility of self-learning search and revenue on e-commerce sites. 904Labs self-learning search improves revenue by 36% when compared to a highly, but manually, tuned Apache Solr search engine. Good job 904Labs team!
The Dutch-Belgian Information Retrieval Workshop was held this year in Delft. A nice lot of people from all around the Netherlands, Belgium, and a handful from abroad came together to share their research highlights from this year. It was a nice programme, filled with interesting short talks (about 15mins) that were great to give us a summary of what everybody is working on.
My personal highlight was Chato’s keynote speech on algorithmic bias. Although a lot is discussed on the topic, there is yet no to little work that presents some sort of foundation that describes the issue, frames it and offers some theoretical framework from which we can start thinking about solutions. Chato’s work laid the ground works on this area. He started with explaining what algorithmic bias is and stressed how coupled it is with data collection. I’m looking forward to seeing more on his work on the subject.
This summer I was happy to be back at the Special Interest Group in Information Retrieval (SIGIR), this time, in Pisa, Italy. Last time I was at SIGIR was in Portland back in 2012, where I was presenting the work I did at Yahoo! Barcelona. SIGIR is the top international conference on search engines, and it’s always good fun to hear the latest developments and exchange new ideas.