01Interactive analytics at scale
Engineers explore years of sensor data in the browser, without downsampling by hand.
Flex Analytics · Ghent, Belgium
Making large-scale data analytics
ordinary.
Data engineering, private AI, interactive analytics and time-series machine learning, for teams whose data is too large or too fast for the tools they have. Built on the open-source libraries Flex Analytics maintains.
What Flex Analytics does.
Four capabilities, on data that has outgrown the tooling around it.
02Time-series machine learning
Models on long, irregular sensor and wearable signals, validated the way the domain expects.
03Data engineering
Sensor and operational data lands raw, auditable, and ready for analysis on a medallion architecture.
04Private and on-device AI
Language and vision models run where the data already is.
What we’ve achieved.
-
Open-source impact
Tools the industry runs on
tsflex, plotly-resampler, tsdownsample and argminmax, with FlexViz built on top. 34M+ PyPI downloads across the Python tools and 14M crates.io downloads of argminmax.
argminmax ships inside Polars. Engineers at Mercedes-Benz, BETA Technologies, SpaceX, Airbus, Blue Robotics, Colruyt, JPMorgan, Nvidia, Renson, Virtual Vehicle and WorldQuant have filed issues, contributed or written in about the tools.
-
Competitions
1st place in both UbiComp 2024 HASCA challenges
The SHL and WEAR challenges at UbiComp/ISWC 2024, both using tsflex for feature extraction. 3rd of 816 teams in the Kaggle Tabular Playground Series of April 2022, and 11th of 807 in BirdCLEF 2022, a gold medal.
-
Research
Twelve peer-reviewed publications and a filed patent
Nine as shared first author, plus a filed US patent on intraocular lens power prediction. Time-series visualization, sleep staging, activity recognition, wearable data quality and clinical decision-making.
The tools behind the work.
Five open-source projects: FlexViz under Apache-2.0, and plotly-resampler, tsflex, tsdownsample and argminmax under MIT. They are what the consulting work is built on, and they stay open.
Who is behind it.
Flex Analytics BV is Jeroen Van Der Donckt, PhD in Computer Science Engineering from Ghent University and maintainer of plotly-resampler, tsflex, tsdownsample, argminmax and FlexViz. Based in Ghent, Belgium. The firm takes on consulting in data engineering, private AI, interactive analytics, and time-series machine learning.
The tools began as research at Ghent University, in the predict-idlab group. plotly-resampler, tsflex and tsdownsample stay under predict-idlab on GitHub; FlexViz and the newer work live under flex-analytics.
Flex Analytics BV · Ghent, Belgium · BE 1017.198.418
Start a conversation.
A short description of your data, what you are trying to do with it, and where the current approach stops is enough to start.
Sent. You will hear back within a few working days.
Something went wrong. Please email [email protected] instead.