eci increases revenue substantially with A.I. for Search

How do you make sure that you find the best results from a 730,000-product catalogue? This is the main question with which eci was struggling. They had reached the limits of manually tuning the onsite search engine, it was time for a more intelligent solution. eci has chosen 904Labs for its latest A.I. search technology, and its easy integration with their Intershop site. 904Labs' new search solutions increase revenue by more than 30% and improved conversion rate by 34%...

30 October, 2017

Self-learning synonyms

Couch or sofa, sneakers or sports shoes, sweater or hoodie. Synonyms are a major challenge for e-commerce search technology. Manually maintaining lists of synonyms is a lot of (boring) work, and the list is never complete. It is therefore good to know that our systems themselves learn synonyms directly from your visitors...

7 August, 2017

Google kills Instant Search

Seven years after its launch, Google kills Instant Search, the feature that shows search results while you're still typing....

2 August, 2017

Self-learning search improves revenue for e-commerce

We are happy to announce comparative results from using 904Labs self-learning search and a highly, but manually, tuned Apache Solr search engine on an e-commerce site. Over a period of one month, and with almost 55,000 unique visitors, 904Labs self-learning search engine helped increase revenue by 36% and purchases by 31%. This is an impressive achievement, and solid evidence that self-learning search can benefit revenue and user engangement for online retailers....

13 April, 2017

Google Site Search alternative

When it comes to search, there's one name that always comes to mind: Google. Over the last couple of years, Google provided several options for onsite search, most notably Google Search Appliances (GSA) and Google Site Search (GSS). With the name Google attached to these products, companies did not hesitate to get them in place. But now they're gone...

2 March, 2017

Best learning to rank results on LETOR4.0

Our academic background forces us to thoroughly check the algorithms and systems we develop, and this is what we do. Recent experiments on publicly available data (LETOR4.0) revealed that our self-learning search engine substantially outperforms state-of-the-art search algorithms. What does this mean? That you'll probably...

19 August, 2016

The latest developments in search from SIGIR 2016

904Labs was at SIGIR 2016 in Pisa. To stay in touch with the latest developments in search engine technology we love to go to scientific conferences. This time, Manos visited SIGIR, the top-tier international conference on search engine technology. Many interesting talks came by in...

5 August, 2016

MKB Innovatie Top 100 2016

Every year, the Dutch Chamber of Commerce (KvK) publishes a list of the 100 most innovative SMEs (MKB Innovatie Top 100). 904Labs has been nominated for the 2016 edition of this innovation list. We're proud to be among the 100 most innovative companies in the...

6 July, 2016

MIT grant with CTcue

We've been awarded an MIT grant for R&D collaboration with e-Health startup CTcue worth €170K. CTcue offers intelligent information access to electronic health records (patient files), an area closely related to our field of expertise. Being part of the same incubator, we've shared many thoughts before...

1 February, 2016

Vasco joins the team

As of January 1, 2016 Vasco Visser has joined the 904Labs team. We're very pleased with this new addition to the team! Vasco holds a master's degree in Computer Science and has plenty of experience in setting up infrastructures to deal with big data, and then...

1 January, 2016

Launchpad Meetup at Oracle

Launchpad Meetups are a new series of meetups, where startups pitch to a corporate's use case. It is a way to get startups in touch with large corporates, while these corporates have a quick way to find out which startups are of interest to them...

1 December, 2015

904Labs supports LivingLabs

Research in the field of search engine technology has been dependent on manually constructed test collections for many years (read our blog post on offline search evaluation). These collections are used to measure the search quality of systems and to compare various algorithms. Although these..

25 November, 2015

WSDM 2016 paper accepted

The paper "Learning Dynamic Collective Entity Representations for Entity Ranking" is a cooperation between authors from the University of Amsterdam (David Graus, Maarten de Rijke), Yahoo! Research (Edgar Meij), and 904Labs. In this paper, we look at entity ranking, i.e., successfully positioning a relevant entity at...

4 November, 2015