Machine Learning


With Machine learning, software applications can predict outcomes accurately. Machine learning models leverage historical data as the input to predict output values. The performance of such models improves with time as the number of samples processed by these models increases with time.

Machine learning is of two types:

Supervised learning

Supervised learning builds a model that makes predictions based on labeled datasets. Both the input and output datasets are defined in the model. Based on the datasets, the model makes predictions for similar input data.

The following models in CDP use supervised learning:

Unsupervised learning

Unsupervised learning extracts patterns in data. In this method, input datasets do not have labeled responses.

Clustering is an unsupervised learning technique that finds patterns in data and also groups similar datasets to form clusters.

The following models in CDP use unsupervised learning: