Data Science – List of Key Machine Learning Algorithms

• Supervised learning
• Unsupervised learning

Following are some of the key tasks that are performed by machine learning algorithms falling under supervised and unsupervised learning:

• Classification: Place input data in a set of discreet categories. For example, whether an input data related cancerous cells represents benign or malignant cancer, or whether a hockey team will win or not, or whether a person will default on loan or not. Read further about classification on wikipedia page for classification
• Regression: Predict numeric value of target feature based on input values of other features. Read further details on wikipedia page for regression analysis
• Clustering: Divide input dataset into one or more homogenous groups. This is sometimes used for segmentation analysis which identifies groups of individuals with similar purchasing, donating, or demographic information such that promotion campaigns can be tailored to particular group of people. Read greater details about cluste analysis on wikipedia page
• Pattern Detection: Focuses on the recognition of patterns and regularities in data

Following is a list of algorithms listed under above categories:

• Supervised learning: Following algorithms can be used for performing classification and numerical value prediction tasks:
  • Classification tasks:
    • Nearest Neighbor
    • naive Bayes
    • Decision trees
    • Classification rule learners
    • Neural networks
    • Support vector machine
  • Numeric prediction tasks:
    • Linear regression
    • Regression trees
    • Model trees
    • Neural networks
    • Support vector machine
• Unsupervised learning: Following algorithms could be used for patterm detection and clustering tasks.
  • Association rules (pattern detection)
  • k-means clustering (clustering)