DEV Community


Posted on • Updated on

List of Evaluation Metrics for Classification and Regression

Machine Learning is the science of teaching computers to perform certain tasks without being explicitly programmed. It can be basically divided into 3 parts-

  • Supervised Learning
  • Unsupervised Learning
  • Reinforcement Learning

Supervised learning is the part that is majorly taught everywhere and consists of two very important tasks Classification and Regression. To know more about these tasks and a simple introduction to how to perform them using Python read my article given below.

We need to assess the performance of our machine learning models and here I am giving a list of evaluation metrics for classification and regression tasks.

Evaluation Metrics for Classification

  1. Accuracy
  2. Precision (P)
  3. Recall (R)
  4. F1 score (F1)
  5. Area under the ROC (Receiver Operating Characteristic) curve or simply Area Under Curve (AUC)
  6. Log loss
  7. Precision at k (P@k)
  8. Average precision at k (AP@k)
  9. Mean average precision at k (MAP@k)

Evaluation Metrics for Regression

  1. Mean absolute error (MAE)
  2. Mean squared error (MSE)
  3. Root mean squared error (RMSE)
  4. Root mean squared logarithmic error (RMSLE)
  5. Mean percentage error (MPE)
  6. Mean absolute percentage error (MAPE)
  7. R-square (R^2)

For a much more detailed explanation of Performance metrics you can read the article given below.

Top comments (0)