[ Tech stack ]
LightGBM
Microsoft's gradient-boosting framework, built for training speed on very large datasets.
LightGBM trains gradient-boosted decision trees using a histogram-based approach: continuous values are bucketed into bins, which sharply cuts memory use and compute time. Leaf-wise tree growth, GOSS and EFB techniques for sampling gradients and bundling sparse features, and distributed learning make it a very fast, memory-efficient booster. It's our choice as soon as the data exceeds a million rows or hundreds of features and iterations need to stay short.
[ Why LightGBM at Dexon ]
What this technology does well, and why we use it.
Typical usage: Large-scale scoring, ranking and recommendation, forecasting, anomaly detection.
- 01
Histogram-based approach: features bucketed into bins, lower memory and compute.
- 02
Leaf-wise tree growth: fewer iterations to reach the same loss.
- 03
Native categorical feature support, no one-hot encoding required.
- 04
Distributed and GPU training, Python, R and C++ APIs, scikit-learn compatible.
[ Complementary technologies ]
The building blocks we often mobilise alongside.
A stack rarely exists alone. Here are the technologies Dexon most often pairs with this one, through pipeline habits, usage similarity or internal mastery. Click on a building block to see its scope.
[ Reassurance ]
- 0+
- custom projects delivered
- 30
- engineers, designers, project managers
- 80 %
- from top French schools
- 24 h
- average reply time
[ They trust us ]
More than 100 French and European companies trust us
[ Press ]
They talk about us.
Nationwide coverage by BFM Business, Le Figaro, Challenges, La Tribune and CNews. An outside reading of our work and our innovations.
