Unsupervised learning is a subset of machine learning where the unlabeled data are provided to the statistical\machine learning\deep learning or reinforcement learning models. In unsupervised learning a few common techniques are for as follows, clustering, density estimation, representation learning, dimensionality reduction, predictive modelling, probabilistic forecasting and hidden markov models [https://en.wikipedia.org/wiki/Markov_model]
Since no labels are provided, there is no specific way to compare model performance in most unsupervised learning methods. Use-cases of unsupervised learning are dimensionality reduction, motif discovery, discord discovery, hierarchical learning and outlier detection.
In situations where it is either impossible or impractical for a human to propose trends in the data, unsupervised learning can provide initial insights that can then be used to test individual hypotheses.
Introduction to Anomaly Detection: Concepts and Techniques
Machine Learning has four common classes of applications: classification, predicting next value, anomaly detection, and discovering structure. Among them, Anomaly detection detects data points in data that does not fit well with the rest of the data. It has a wide range of applications such as fraud detection, surveillance, diagnosis, data cleanup, and predictive maintenance.
However, with the advent of IoT, anomaly detection would likely to play a key role in IoT use cases such as monitoring and predictive maintenance.
Link to working code repository:
https://github.com/aayushkumarjvs/deep-learning-with-python-notebooks/blob/master/unsupervised_anomalydetection.ipynb