What is Problem Formulation in Machine Learning and Top 4 examples of Problem Formulation in Machine Learning?

Problem formulation is an essential part of the machine learning pipeline. Machine learning problems can be classified into four types: regression, classification, clustering, and ranking. Each type of problem has its own set of challenges and requires a different approach. For example, regression problems involve predicting a continuous value, such as the price of a stock, while classification problems involve predicting a discrete label, such as whether an email is spam or not. Clustering problems involve grouping data points into clusters, while ranking problems involve ordering data points from most to least similar. In each case, the goal is to find a model that can generalize from the training data to the test data. The choice of model will depend on the type of problem and the nature of the data. For instance, linear models are often used for regression problems, while decision trees are often used for classification problems. The challenge in machine learning is to find a model that performs well on the training data but also generalizes well to unseen data. This is where problem formulation comes in. By carefully defining the problem and choosing an appropriate model, we can increase the chances of finding a solution that works well in practice.