Gradient-Boosted Decision Trees (GBDT)

What are Gradient-Boosted Decision Trees?

Gradient-boosted decision trees are a machine learning technique for optimizing the predictive value of a model through successive steps in the learning process. Each iteration of the decision tree involves adjusting the values of the coefficients, weights, or biases applied to each of the input variables being used to predict the target value, with the goal of minimizing the loss function (the measure of difference between the predicted and actual target values). The gradient is the incremental adjustment made in each step of the process; boosting is a method of accelerating the improvement in predictive accuracy to a sufficiently optimum value.


Why are Gradient-Boosted Decision Trees Important?

Gradient-boosted decision trees are a popular method for solving prediction problems in both classification and regression domains. The approach improves the learning process by simplifying the objective and reducing the number of iterations to get to a sufficiently optimal solution. Gradient-boosted models have proven themselves time and again in various competitions grading on both accuracy and efficiency, making them a fundamental component in the data scientist’s tool kit.


How Enables Organizations to Use Gradient-Boosted Decision Trees provides leading enterprise AI technology that enables large organizations to harness and extract value using a wide variety of AI and machine learning libraries, resulting in step-function improvements across business processes. The C3 AI® Suite is a complete, end-to-end platform for designing, developing, deploying, and operating enterprise AI applications at industrial scale. The C3 AI Suite provides comprehensive capabilities enabling organizations to prepare unlimited volumes of data, and then apply advanced AI and machine learning algorithms to generate predictions and insights to drive the business. The C3 AI Suite supports a wide range of third-party and open-source libraries and frameworks for advanced mathematical, statistical and machine learning capabilities, including Spark MLib, TensorFlow, Keras, Scikit-learn, cuDNN, NumPy, SciPy, Caffe, Torch, PyTorch, Lex, Polly, Rekognition, Azure ML,, Stanford Core NLP, NLTK, spaCY, fbProphet, StatsModels, and XGBoost.