[{"data":1,"prerenderedAt":134},["ShallowReactive",2],{"term-x\u002Fxgboost":3,"related-x\u002Fxgboost":120},{"id":4,"title":5,"acronym":6,"body":7,"category":102,"description":103,"difficulty":104,"extension":105,"letter":106,"meta":107,"navigation":53,"path":108,"related":109,"seo":114,"sitemap":115,"stem":118,"subcategory":6,"__hash__":119},"terms\u002Fterms\u002Fx\u002Fxgboost.md","XGBoost",null,{"type":8,"value":9,"toc":96},"minimark",[10,15,19,23,26,30,85,89,92],[11,12,14],"h2",{"id":13},"eli5-the-vibe-check","ELI5 - The Vibe Check",[16,17,18],"p",{},"XGBoost is the specific, ruthlessly optimized software library that turned gradient boosting from a solid idea into the thing that wins Kaggle competitions and quietly powers half the fraud and ranking models in production. It's the same core idea as gradient boosting, but engineered for speed, with built-in regularization to fight overfitting, and it handles missing values without you having to clean them up first.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25],{},"XGBoost, short for Extreme Gradient Boosting, is an optimized, open-source implementation of gradient boosted decision trees, known for its speed, built-in regularization terms that penalize model complexity, native handling of missing values, and support for parallel and distributed training. It became a dominant algorithm for structured, tabular data problems and is a frequent choice in production ML systems and competitive data science.",[11,27,29],{"id":28},"show-me-the-code","Show Me The Code",[31,32,37],"pre",{"className":33,"code":34,"language":35,"meta":36,"style":36},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","import xgboost as xgb\n\nmodel = xgb.XGBClassifier(\n    n_estimators=300, max_depth=6, learning_rate=0.05,\n    reg_lambda=1.0\n)\nmodel.fit(X_train, y_train, eval_set=[(X_val, y_val)])\n","python","",[38,39,40,48,55,61,67,73,79],"code",{"__ignoreMap":36},[41,42,45],"span",{"class":43,"line":44},"line",1,[41,46,47],{},"import xgboost as xgb\n",[41,49,51],{"class":43,"line":50},2,[41,52,54],{"emptyLinePlaceholder":53},true,"\n",[41,56,58],{"class":43,"line":57},3,[41,59,60],{},"model = xgb.XGBClassifier(\n",[41,62,64],{"class":43,"line":63},4,[41,65,66],{},"    n_estimators=300, max_depth=6, learning_rate=0.05,\n",[41,68,70],{"class":43,"line":69},5,[41,71,72],{},"    reg_lambda=1.0\n",[41,74,76],{"class":43,"line":75},6,[41,77,78],{},")\n",[41,80,82],{"class":43,"line":81},7,[41,83,84],{},"model.fit(X_train, y_train, eval_set=[(X_val, y_val)])\n",[11,86,88],{"id":87},"when-youll-hear-this","When You'll Hear This",[16,90,91],{},"\"For tabular data, just try XGBoost first, it beats a neural net here nine times out of ten.\" \u002F \"We tuned the XGBoost learning rate down and it stopped overfitting on the validation set.\"",[93,94,95],"style",{},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":36,"searchDepth":50,"depth":50,"links":97},[98,99,100,101],{"id":13,"depth":50,"text":14},{"id":21,"depth":50,"text":22},{"id":28,"depth":50,"text":29},{"id":87,"depth":50,"text":88},"ai","XGBoost is the specific, ruthlessly optimized software library that turned gradient boosting from a solid idea into the thing that wins Kaggle competitions...","advanced","md","x",{},"\u002Fterms\u002Fx\u002Fxgboost",[110,111,112,113],"Gradient Boosting","Random Forest","Overfitting","Hyperparameter",{"title":5,"description":103},{"changefreq":116,"priority":117},"weekly",0.7,"terms\u002Fx\u002Fxgboost","4RjuFr8vV58vujBI0taYuUa5fiXaIcpQW8xoKt195QY",[121,124,128,131],{"title":110,"path":122,"acronym":6,"category":102,"difficulty":104,"description":123},"\u002Fterms\u002Fg\u002Fgradient-boosting","Gradient boosting builds a model the way you'd improve a rough first draft: you write it, look specifically at what it got wrong, then write a second pass...",{"title":113,"path":125,"acronym":6,"category":102,"difficulty":126,"description":127},"\u002Fterms\u002Fh\u002Fhyperparameter","intermediate","Hyperparameters are the settings you configure BEFORE training starts — as opposed to parameters (weights) which the model learns ON ITS OWN.",{"title":112,"path":129,"acronym":6,"category":102,"difficulty":126,"description":130},"\u002Fterms\u002Fo\u002Foverfitting","Overfitting is when your model gets TOO good at the training data and becomes useless on new data.",{"title":111,"path":132,"acronym":6,"category":102,"difficulty":126,"description":133},"\u002Fterms\u002Fr\u002Frandom-forest","A random forest is what you get when you refuse to trust a single decision tree's opinion and instead grow hundreds of slightly different trees, each train...",1792528136712]