Why were Support Vector Machines considered the king of machine learning before deep learning?

The answer

Support Vector Machines (SVMs), formalized by Vladimir Vapnik in the 1990s, became the dominant machine learning algorithm throughout the 2000s due to their strong theoretical foundations and excellent performance on small-to-medium datasets. SVMs work by finding the optimal hyperplane that maximally separates classes in high-dimensional space, using the 'kernel trick' to handle non-linear boundaries. They won numerous competitions and were the go-to method for text classification, image recognition, and bioinformatics until deep learning surpassed them around 2012.