{"id":69,"date":"2026-04-03T11:11:19","date_gmt":"2026-04-03T11:11:19","guid":{"rendered":"https:\/\/gigz.pk\/ml\/?post_type=lesson&p=69"},"modified":"2026-04-07T10:29:12","modified_gmt":"2026-04-07T10:29:12","slug":"decision-trees","status":"publish","type":"lesson","link":"https:\/\/gigz.pk\/ml\/lesson\/decision-trees\/","title":{"rendered":"Decision Trees"},"content":{"rendered":"\n

Decision Trees are a popular and intuitive supervised Machine Learning algorithm<\/strong> used for both classification and regression tasks. They work by splitting the data into subsets based on the value of input features, forming a tree-like structure of decisions.<\/p>\n\n\n\n

How Decision Trees Work<\/h2>\n\n\n\n
    \n
  1. Root Node:<\/strong> The top node represents the entire dataset and selects the feature that best splits the data.<\/li>\n\n\n\n
  2. Splitting:<\/strong> The data is split into subsets based on a feature and a threshold (for numerical features) or categories (for categorical features).<\/li>\n\n\n\n
  3. Internal Nodes:<\/strong> Each internal node represents a decision based on a feature.<\/li>\n\n\n\n
  4. Leaf Nodes:<\/strong> Leaf nodes represent the final output or prediction.<\/li>\n<\/ol>\n\n\n\n

    The algorithm chooses the best splits using metrics like Gini Impurity<\/strong>, Entropy (Information Gain)<\/strong>, or Mean Squared Error<\/strong> (for regression).<\/p>\n\n\n\n

    Advantages of Decision Trees<\/h2>\n\n\n\n