In this video, we will learn about Anomaly Detection algorithm and it’s applications.

Dataset with abnormal behaviors are termed as outliers or anomalous. These occurrences are statistically different from the rest of the observations and very rare. Fraud detection or faulty product identification are some of the examples and real world applications of anomaly detection algorithm.

3 types of anomaly detection algorithms:

1) Supervised - This is kind of classification problem.
2) Unsupervised  - This is done by the clustering algorithm like DBSCAN
3) Semi-supervised - This leverage the benefits of both of these algorithms.

Data imbalance is a very common problem in a dataset in which we are supposed to identify anomalous examples this happen because it is anomalous and happens rarely.

Anomaly detection in Machine learning:
https://www.geeksforgeeks.org/machine-learning-for-anomaly-detection/