Support vector algorithms are a relatively recent concept, like so many other machine learning techniques. Cortes and Vapnik (
Cortes, 1995) provided one of the first formal introductions to the concept while investigating algorithms for optical character recognition at the AT&T Bell Labs.
The term “support vector machine” is a confusing name for a predictive analytics algorithm. The fact is this term is very much a misnomer: there is really no specialized hardware. But it is a powerful algorithm that has been very successful in applications ranging from pattern recognition to text mining. A support vector machine (SVM) emphasizes the interdisciplinary nature of today’s advanced analytics by drawing equally from three ...