Data articles
Learn how French data teams do data engineering and machine learning on production
Categories
Latest articles
Alan - 28 April 2022
Machine Learning at Alan
namR - 25 March 2022
Computer Vision Pipeline with KubernetesTeads - 22 February 2022
Running Spark Pipelines on EMR Using Spots InstancesVeepee - 21 February 2022
Training pipeline orchestration with Kubeflow pipelinesBack Market - 18 February 2022
From Delta Lake to BigQuery
Toucan Toco - 15 February 2022
Youprep: Why it's easier than SQLiAdvize - 11 February 2022
Tableau Data Catalog: Let’s do the jigsaw puzzle!iAdvize - 10 February 2022
Tableau Data Catalog: Diving into workbooks’ complexityiAdvize - 9 February 2022
Tableau Data Catalog: Harvesting Tableau fieldsiAdvize - 8 February 2022
Tableau Data Catalog: Discovering Tableau’s metadata…iAdvize - 7 February 2022
Tableau Data Catalog: How the need came
Voodoo - 13 January 2022
How Voodoo did Airflow 101Doctrine - 4 January 2022
A/B testing experience at DoctrinenamR - 17 December 2021
Prédire la présence d’objets sur les toits de bâtimentsLifen - 13 December 2021
How to fix Interoperability in HealthcareAdevinta - 3 December 2021
Machine Learning: when should you use it?Getaround Europe - 2 December 2021
GDPR compliance and account deletion
Pennylane - 17 November 2021
Data at Pennylane: what it entails, and how we do itContentsquare - 16 November 2021
Behavioral Time Series Segmentation in ClickHouseDoctolib - 5 November 2021
How to ship a machine learning model in days not months?Adevinta - 4 November 2021
Learnings from building machine learning products at scaleDoctrine - 29 October 2021
Semantic recommendation system using CamemBERT
Preligens - 6 October 2021
How we built an AI Factory — Parts 2&3Teads - 5 October 2021
Production A/B Test Analysis Framework at TeadsAlgolia - 1 October 2021
Building real-time Analytics APIs at scaleAdevinta - 21 September 2021
Treating data as a product at AdevintaAdevinta - 16 September 2021
A/B testing to improve recommender productsDeezer - 15 September 2021
Recommending music to new usersPhotoRoom - 13 September 2021
4 times faster image segmentation with TRTorch
Adevinta - 6 September 2021
The collaborative process of building a Machine Learning platform
OVHcloud - 7 June 2021
Network devices overheat monitoringMeetic - 26 May 2021
How to build a useful chatbot
Artefact - 22 February 2021
Introducing NLPretext
Contentsquare - 18 February 2021
Ten Flink Gotchas we wish we had knownDecathlon - 17 February 2021
Building a RNN Recommendation Engine with TensorFlowVeepee - 27 January 2021
Learning to rank at VeepeeAdevinta - 14 January 2021
Tuning related-items recommenders with Bayesian OptimizationCriteo - 12 January 2021
How to compare two treatments?Maisons du Monde - 18 December 2020
Qlik Sense under controlDecathlon - 15 December 2020
Smile detection for image moderationTeads - 3 December 2020
Updating to Spark 3.0 in productionDeepki - 23 November 2020
Application Monitoring : Entre créativité et veille techniqueDeepki - 16 November 2020
L’ETL chez DeepkiDecathlon - 13 October 2020
10 tips to improve your machine learning models with TensorFlowCriteo - 6 October 2020
Out of sight, out of click
Linkvalue - 29 September 2020
Comment prédire un classement global à partir d’estimations locales ?Tweag I/O - 23 September 2020
Announcing Lagoon - A tool for centralizing semi-structured datasetsAXA - 22 September 2020
Getting started with NLP.jsDeepki - 24 August 2020
Comment manipuler un DataFrame Pandas avec le MultiIndex ?Voodoo - 17 August 2020
Building cheaper and more performant EMR pipelinesCriteo - 11 August 2020
How Much Can Bad Data Cost Us?Criteo - 6 August 2020
DeepR — Training TensorFlow Models for Production
PhotoRoom - 12 July 2020
The Hunt for Cheap Deep Learning GPUsCriteo - 10 June 2020
Introducing ADA: Another Domain Adaptation LibraryAXA - 4 June 2020
Détection des abandonnistes avec ksqlDBDoctrine - 28 May 2020
Making queries 100x faster with Snowflake
Deezer - 29 April 2020
Detecting explicit content in songs
Cheerz - 2 April 2020
Cheerz simple data stack
Criteo - 10 March 2020
Open sourcing cluster-packOVHcloud - 6 March 2020
Doing BIG automation with CeleryOVHcloud - 26 February 2020
Introducing Director – a tool to build your Celery workflowsMaisons du Monde - 24 February 2020
Road to add form for Airflow’s dagOVHcloud - 14 February 2020
Contributing to Apache HBase: custom data balancingCdiscount - 13 February 2020
Estimating when a message will be consumed in KafkaCriteo - 6 February 2020
Incrementality: a simple question commanding subtle answersTeads - 29 January 2020
Spark UDAF could be an option!Sicara - 27 January 2020
TensorFlow 2.0 Tutorial : Optimizing Training Time PerformanceSicara - 13 January 2020
Optimize Response Time of your Machine Learning API In ProductionDoctolib - 3 January 2020
Redshift : Troubleshouting made simpleDeepki - 17 December 2019
Comment fait-on pour obtenir des courbes de charge en temps réel ?Kapten - 29 November 2019
Why going real time?
Deepki - 27 November 2019
Dask vs Pandas : Fight !Hugging Face - 26 November 2019
How To Write With TransformerCriteo - 14 November 2019
Big Data Quality at CriteoDeezer - 4 November 2019
Releasing Spleeter: Deezer R&D source separation engineDoctrine - 3 November 2019
⚖ Structuring legal documents with Deep LearningLinkvalue - 31 October 2019
From Duels to Sport RacingSicara - 28 October 2019
Deep Learning Memory Usage and Pytorch Optimization TricksHugging Face - 18 October 2019
Benchmarking Transformers: PyTorch and TensorFlowPreligens - 10 October 2019
Super-resolution for satellite imagery analysisCriteo - 30 September 2019
Boosting image processing performance, from ImageMagick to LibvipsSicara - 26 September 2019
Face Detectors: Understand DSFD and the State-of-the-art AlgorithmsAlan - 25 September 2019
Alan’s solution to sharing data knowledgeCriteo - 19 September 2019
Lessons learned from annotating 5 million imagesPreligens - 3 September 2019
Improving the description of satellite images using GIS dataDailymotion - 9 August 2019
Getting started with Data LineageHugging Face - 9 August 2019
From TensorFlow to PyTorchDeezer - 31 July 2019
Women & Hip-HopSicara - 30 July 2019
Few-Shot Image Classification with Meta-LearningGlose - 19 July 2019
How to evaluate readers text comprehension?Sicara - 16 July 2019
Image Registration: From SIFT to Deep LearningGlose - 20 June 2019
How to Evaluate Text Readability with NLPnamR - 21 May 2019
Why data quality matters?Glose - 14 May 2019
️ Fast bag-of-words using spaCy and cythonCriteo - 13 May 2019
Upgrading Kafka on a large infraDeepki - 13 May 2019
Du G dans le SI, pour quoi faire ?Snips - 10 May 2019
Snips Open Sources TractOVHcloud - 10 May 2019
Alerting based on IPMI data collectionSnips - 9 May 2019
Infrared Voice Controlled With SnipsCriteo - 16 April 2019
Hyper-parameter optimization algorithms: a short reviewDeepki - 15 April 2019
Accessibilité des données énergétiques aux consommateursSicara - 8 April 2019
How Apache Airflow Distributes Jobs on Celery workersSicara - 12 March 2019
Edge Detection in Opencv 4.0, A 15 Minutes TutorialTeads - 26 February 2019
Give meaning to 100 Billion events a day — Part IICdiscount - 12 February 2019
Détection de botsLifen - 24 January 2019
Storing AI predictions in FHIRleboncoin - 9 January 2019
Data Traffic Control with Apache AirflowSicara - 9 January 2019
How to Perform Fraud Detection with Personalized Page RankCriteo - 8 January 2019
Packaging code with PEX — a PySpark exampleGetaround Europe - 7 January 2019
Why we've chosen Snowflake ❄️ as our Data WarehouseLifen - 16 November 2018
Fake it until you make it