GS 3 Fisher

's separation Fisher's Separation consists of three parts- 1. Initial Search: during the first phase of the approach intended to identify the best features to allow the machine learning algorithm to better identify the target output. 2. Feature Selection: involves selecting a subset of features that maximises the discriminative power of the prediction task. 3. Construction of Model: After feature selection is completed, the appropriate model is chosen and trained on the selected features. This is usually done through supervised learning techniques such as logistic regression or support vector machines. The resulting model can then be used for prediction.