303 Quiz 3 -- The main four learning techniques (classification, regression, clustering, association rule mining)

When do I use classification?

Use this learning technique when you need to categorize data into predefined classes based on historical data.

What are some real-life examples of classification?

Examples include predicting loan defaults, categorizing customer reviews, diagnosing diseases based on symptoms,

classifying emails as spam or not spam, images as cats or dogs, or customer reviews as positive, negative, or neutral.

What are some examples of classification algorithms?

• Logistic Regression

• Neural Networks

• Naive Bayes

• Support Vector Machines (SVMs)

• K-Nearest Neighbors

• Decision Trees/Random Forests

When do I use regression?

Use this learning technique when you need to predict a continuous (meaning it can take on any value within a range) value based on input features.

What are some real-life examples of regression?

Examples include Predicting house prices, forecasting weather, estimating fuel efficiency of cars.

What are some examples of regression algorithms?

• Ordinary Least Squares

• Ridge

• Lasso

• Decision Trees

• MLP

• Bayesian

• SGD

When do I use clustering?

Use this learning technique when you need to group similar instances together without predefined labels.

What are some real-life examples of clustering?

Segmenting customers, grouping similar products, organizing social media posts.

What are some examples of clustering algorithms?

• K-Means

• Gaussian Mixture Model

When do I use Association Rule Mining?

Use this learning technique when you want to discover relationships between items or events in categorical data.

What are some real-life examples of association rule mining?

Identifying frequently bought together products, finding patterns in retail transactions.

What are some examples of association rule mining algorithms?

Apriori and FP Growth

What learning techniques use labeled data?

Supervised learning models such as classification and regression.

What learning techniques use unlabeled data?

Unsupervised learning models such as clustering and association rule mining.