John W. Foreman

“What does it mean when customers don't take a deal? Does it mean that they didn't want the product as much as they did want the one they bought? Is a negative signal as strong as a positive one? Perhaps they like Champagne but already have a lot in stock. Maybe they just didn't see your e-mail newsletter that month. There are a lot of reasons why someone doesn't take an action, but there are few reasons why someone does. In other words, you should care about purchases, not non-purchases. The fancy way to say this is that there's an “asymmetry” in the data. The 1s are worth more than the 0s. If a customer matches another customer on three 1s, that's more important than matching some other customer on three 0s. What stinks though is that while the 1s are so important, there are very few of them in the data—hence, the term “sparse.”
― John W. Foreman, Data Smart: Using Data Science to Transform Information into Insight