Supervised Learning: Classification

Supervised learning is a type of machine learning where a given algorithm learns from a labeled dataset that consists of input and output pairs;
It is used for regression(predicting progressive numerical values)and classification (Categorization of data into discrete classes)

How does Classification work in machine learning?

(i)Data Preparation where a dataset containing input features and their corresponding class labels is prepared

(ii) Model Training whereby a classification algorithm (e.g., Logistic Regression, Support Vector Machines, Decision Trees, K-Nearest Neighbors) is chosen and trained on the labeled training data, here the algorithm learns the relationship between the input features and the target class labels.

(iii) Evaluation of the model- the performance of the trained model is evaluated based on the testing data. The metrics- accuracy, precision, recall and F1-score are used for evaluation

(iv)Prediction- A model can be used to predict the class label once the model is trained and evaluated

What Models are used for Classification?!
-Logistic Regression
-Decision Trees
-Support Vector Machines (SVMs)
-Naive Bayes
-K-Nearest Neighbors

While precision, recall and accuracy are useful metrics for evaluating classifiers, determining an appropriate balance between false positives and false negatives depends on the particular problem application and the relative costs of each.
Machine learning is important as it results in automation of tasks and enhances accuracy, efficiency and proper decision making; which are key in the most important industries that surround and support human existence in general