Imagine getting into your car and saying, “Take me to work,” and then enjoying an automated drive as you read the morning news. We are getting very close to that kind of scenario, and companies like Ford expect to have production vehicles in the latter part
Driverless cars are just one popular example of machine learning. It’s also used in countless applications such as predicting fraud, identifying terrorists, recommending the right products to customers at the right time, and correctly identifying medical
symptoms to prescribe appropriate treatments.
The concept of machine learning has been around for decades. What’s new is that it can now be applied to huge quantities of data. Cheaper data storage, distributed processing, more powerful computers and new analytical opportunities have dramatically
increased interest in machine learning systems. Other reasons for the increased momentum include: maturing capabilities with methods and algorithms refactored to run in memory; the reduced cost of abundant computing power; and the simple fact that there is more data for computers to learn from.
This paper is based on presentations given over the last few years. Wayne Thompson, Manager of Data Science Technologies at SAS, introduces key machine learning concepts, explains the correlation between statistics and machine learning, and describes SAS® solutions that enable machine learning at scale.