The main purpose of evaluation indicator is to test the validity of algorithm.
Evaluation indicators can be divided into two categories: the internal evaluation indicators and the external evaluation indicators.
the internal evaluation indicators
It can’t absolutely judge which algorithm is better when the scores of two algorithms are not equal based on the internal evaluation indicators.
There are three commonly used internal indicators.
- Davies–Bouldin indicator the data that has even density and distribution
- Dunn indicator requires computing distances between all pairs of clusters and within all clusters. This can be a limiting factor for very large datasets.
- Silhouette coefficient
the external evaluation indicators
The external evaluation, which is called as the gold standard for testing method, takes the external data to test the validity of algorithm.
- Jaccard indicator is a measure of similarity between two sets
- Hamming similarity for the data of string
- Rand indicator
- F indicator
- Fowlkes–Mallows indicator
- Mutual information
- Confusion matrix