LightGBM in Python

A Gradient Boosting Decision tree or a GBDT is a very popular machine learning algorithm that has effective implementations like XGBoost and many optimization techniques are actually adopted from this algorithm. The efficiency and scalability of the model are not quite up to the mark when there are more features in the data. For this specific behavior, the major reason is that each feature should scan all the various data instances to make an estimate of all the possible split points which is very time-consuming and tedious. To solve this problem, The LGBM or Light Gradient Boosting Model is used. It uses two types of techniques which are gradient Based on side sampling or GOSS and Exclusive Feature bundling or EFB.