XGBoost
XGBoost is an optimized distributed gradient enhancement library.
In prediction tasks that use unstructured data (such as images or text), this artificial neural network outperforms all other algorithms or frameworks.
It supports several languages, including C ++, Python, R, Java, Scala, Julia.
Clients: Solves many problems in data science and machine learning. Used in production by several companies.
Use cases
Avito.ru
If you don’t know which algorithm to use, try XGBoost.” – Owen Zhang, winner of the Avito contextual advertising improvement competition on Kaggle
Benefits
Well-optimised backend system for maximum performance when resources are limited. It supports distributed training on multiple machines, including AWS, GCE, Azure, and Yarn clusters.
Also, it can be integrated with Flink, Spark and other cloud dataflow systems.
Well-optimised backend system for maximum performance when resources are limited.
