Which of the following is an example of unsupervised learning?
Select one:
a. Loan Default Prediction
b. Predicting House Prices
c. Classifying the image as a cat or dog
d. Finding communities or groups in large social networks
The Correct Answer and Explanation is :
The correct answer is:
d. Finding communities or groups in large social networks.
Explanation:
Unsupervised learning is a type of machine learning where the model is given data without labeled outcomes or categories. The goal is to identify patterns, relationships, or structures within the data itself, rather than predicting a specific outcome. Unsupervised learning is often used for tasks like clustering, dimensionality reduction, anomaly detection, and association.
In the context of the options given:
- a. Loan Default Prediction: This is typically a supervised learning task because it involves predicting a known outcome (whether or not a loan will default) based on labeled data (e.g., loan characteristics, past repayment history).
- b. Predicting House Prices: This is another example of supervised learning. Predicting house prices involves using historical data with known labels (house prices) to train a model that can predict future prices based on features like size, location, and condition.
- c. Classifying the image as a cat or dog: This is also a supervised learning problem. It involves using labeled images (cat or dog) to train the model, so the model can classify new, unseen images.
- d. Finding communities or groups in large social networks: This is an example of unsupervised learning. In this case, the goal is to detect natural groupings or communities within a network (for example, groups of users with similar interests or behaviors). The algorithm doesn’t require predefined labels for each group. Instead, it identifies clusters of individuals that share common patterns, and this grouping is the primary objective of the task.
Unsupervised learning algorithms include clustering methods like K-means, Hierarchical clustering, and DBSCAN, and dimensionality reduction techniques like PCA (Principal Component Analysis). These algorithms aim to find hidden patterns without relying on labeled data.
In social network analysis, unsupervised learning can be used to detect communities of users that have a higher density of connections among themselves than with the rest of the network, which is a typical clustering problem.