Recently I found myself planning a bachelor party. I was aiming to rent a house for 19 friends strewn across the northeastern United States. I wanted to pick a a central location easy for everyone to get to. So, like any normal person (at least one who works in analytics), I wanted to quantitatively determine the most fair location. “In the Middle” Very often, when you want to meet someone who lives elsewhere, we pick a point halfway between....
I teach a class on Data Mining at Stanford. Students in my class are expected to do a project that does some non-trivial data mining. Many students opted to try their hand at the Netflix Challenge: to design a movie… One of my favorite blog posts ever. A very simple idea: it’s easier to win by creatively combining data than by using ever more sophisticated algorithms. This is especially important today due to two major trends in the analytics world:...
A topic that has come up for me multiple times recently is how to best measure affinity in retail or eCommerce. In working with customers, I have seen that many different organizations measure affinity differently, and I wanted to take the time to explore the various models and why they may make sense or not. In the end, affinity comes down to probabilities. Before I dive into this, some background (if you already know about affinity analysis, skip below):...
Think about it: The Economist discusses two interesting facts in an article published a few weeks ago. Income inequality has risen in most countries in the world over the past 10 years. Total global income inequality has fallen over the same period of time. How is that possible? If almost every country has rising income inequality shouldn’t total income inequality be growing globally? (If you want to take a second and try to think about how this is possible, do it now)....