hAIgopala › AI terms › Rapid Fire (3 terms per short) › Day 7

Gradient Boosting (XGBoost, LightGBM)

Classic ML AlgorithmsChapter 2: First Smart RulesTerm 34 of 253

Builds trees one after another, each fixing the previous one's errors. Top choice for tabular data.

At Sunrise School

Gopal asks

What's the most accurate model for our spreadsheet data?

Bit answers

Gradient boosting: each new tree fixes the previous trees' mistakes. For tables like admissions history, it's usually the winner.

In the real world

Kaggle competition favourite.

Watch the short

Short coming soonSeason 5 · Day 7Follow @haigopala

Taught together with

Ensemble Methods · Logistic Regression

Practise it

Try this term and all 253 others in the free Model Training Arena.

Open the Arena →

Follow Bit daily: YouTube English · తెలుగు · हिंदी  |  Instagram English · తెలుగు · हिंदी