Join the COVEO Team!


COVEO is a Quebec City-based enterprise software-as-a-service (SaaS) company that offers a cloud-based platform for making digital experiences more intelligent, and provides specific software built on that platform. The Coveo Relevance Cloud™ utilizes search, analytics, and machine learning technologies to unify disparate content and data, and to automate the delivery of relevant, personalized information. Coveo provides solutions for ecommerce, customer service, and workforce proficiency.

Industry : Enterprise software
Founded : 2005


Are you interested in solving concrete industrial problems while developing a unique work experience? Fill in the participation form below. We will review your eligibility and provide you with the registration link later.


Analysis of eCommerce clickstream data for intent prediction and recommendations

Coveo is sharing a rich anonymized dataset on eCommerce behavior for research purposes. The dataset includes more than 30M single product interactions by real shoppers – the clickstream data is enriched by (vectorized) catalog meta-data and by fine-grained search behavior, showing not only products clicked after a query is issued, but also products seen and not clicked (i.e. negative feedback). 

In continuity with previous research (from Coveo and the community) and with the 2021 SIGIR Data Challenge, we welcome research addressing two challenges :

  1. a session-based recommendation task, where a model is asked to predict the next interactions between shoppers and products, based on the previous product interactions and search queries within a session;
  2. a cart-abandonment task, where, given a session containing an add-to-cart event for a product X, a model is asked to predict whether the shopper will buy X or not in that session.

Participants are encouraged to read the following peer-reviewed articles : ( and to get a better understanding of the underlying theoretical and practical issues: class imbalance, conversion rate, etc. The SIGIR Data Challenge paper contains extensive literature review, in-depth details about the dataset, and discussions about the target use cases; the SIGIR Leaderboard can be consulted for quantitative benchmarks (test files to replicate the submission phase can be requested to Coveo); the SIGIR open source repository contains detailed explanation on the dataset, ready-to-use baseline models and links to successful implementations.

  • Coveo welcomes all types of contributions, namely, extensions of Coveo’s previous work through adding more features or different model architectures, exploring entirely different approaches.
  • Given the nature of the company, they also welcome contributions addressing explicitly the cost vs accuracy trade-off inherent in the problem for example, “method X from the literature is more accurate, but comes with additional feature/training/maintenance overhead, while instead we propose method Y, which has reasonable accuracy for a fraction of the cost/time/data”.
  • Please consult the SIGIR paper for a tentative list of interesting topics to explore in connection with the challenge.

The Coveo dataset “SIGIR eCOM 2021 Data Challenge Dataset” is freely available online under a research friendly license. Participants are free to download the data and use it in compliance with the Terms and Conditions.


Hyunhwan Aiden Lee
Assistant Professor – Department of Marketing, HEC Montreal.

Sébastien Paquet
Director – Machine Learning, Research and Development, COVEO.

Jacopo Tagliabue
Lead A.I Scientist, COVEO.

Jean-Francis Roy
Team Leader – Machine Learning, COVEO.

Patrick John Chia
Machine Learning Developer, COVEO.

Guillaume Poirier
Partnership Advisor, IVADO.

Ahana Ahluwalia
Bachelor in Computer Software Engineering, Thompson Rivers University.

Martin Dallaire
M.Sc. in Computer Science, Université de Montréal.

Prakash Gawas
PhD. in Applied Mathematics, Polytechnique Montréal.

Yang (Tina) Zhou
PhD. in Mathematics, University of Bath.