We’ve all experienced predictive use case in our personal lives. Netflix, Amazon, Google Now, Microsoft Cortana. However do you know what the most common predictive technique used by businesses today is?
It’s not Logistic Regression, Random Forest or Principal Component Analysis. It’s actually called S.W.A.G. Wikipedia’s definition (https://en.wikipedia.org/wiki/Scientific_Wild-Ass_Guess) for SWAG is “Scientific Wild-Ass Guess – an American slang meaning a rough estimate made by an expert in the field, based on experience and intuition.”
It’s a very interesting definition – and to me machine learning takes this concept to the next level and helps predict on much larger scale, with consistency.
At a high level here’s how I would translate the key terms in the SWAG definition:
- estimate = probability
- expert = domain knowledge
- experience = data
- intuition = models and algorithms
springML creates a new definition for SWAG: Scientific Wildly Accurate Guess!!