Machine Learning

Machine Learning Blogs

Distributions in d3

March 30, 2014
By
Distributions in d3

Something that often comes up is visualizing in 3 dimensions. I don't mean like 3dprinting. I mean more like heatmaps. With heatmaps, you can easily change two variables (the x and y dimensions) and see its impact on a third variable, usually denoted by color. You can also add texture and size to increase the number of dimensions, but let's not go overboard. (Here's one of my favorite heatmaps by…

Read more »

TV analysis

February 17, 2014
By

TV attribution is one of the hardest problems to get right in all web analytics. To be clear, attribution is how marketers make sense out of their spend, so they know where to invest more or less in the future. Since attribution, for most companies, is...

Read more »

Reinforcement Learning in R: Markov Decision Process (MDP) and Value Iteration

January 7, 2014
By
Reinforcement Learning in R: Markov Decision Process (MDP) and Value Iteration

How can we find the best long-term plan? In the last post, we looked at the idea of dynamic programming,...

Read more »

Spite.

December 24, 2013
By

Congress. Wait, before you lose your lunch, bear with me. This dysfunctional legislative body has been making headlines in the news recently. And when Congress is mentioned, rarely, if ever, is it of the positive persuasion. The shutdown, for example, didn't go over too well with people. And of course there's those pesky little (dis)approval ratings. However it's not like some members of Congress planned on the shut down. And…

Read more »

Doing Yeoman’s work.

December 23, 2013
By

They work hard for their money. Or, maybe they just work for their money. Either way, members of Congress get paid. There are many ways to measure the amount of work congressional members do. One way is by looking at the number of Bill's they pass per session. Much has been made this year about the 113th Congress doing little more than showing up to work. Even that was difficult…

Read more »

Social media popularity, revisited.

November 29, 2013
By
Social media popularity, revisited.

You might remember my post on Twitter mentions in New York Times articles from a few months back. I simply accessed the NYT API and plotted a graph showing the rise in mentions over the past few years. At the time, I used R's very popular plotting library, ggplot to chart it. It's great, easy to use and intuitive. There was one big problem though - it was a static…

Read more »

Want to work with me? Count to 3.

October 24, 2013
By

This stumps job applicants all the time (although probably not after this post). I flip a coin two times. Given that at least one of the flips is heads, what's the probability that both flips are heads. 50% you say? Sorry, but no. Don't feel bad...

Read more »

Messing with d3

October 15, 2013
By

I recently began messing around with d3.js, which is a Javascript library that makes it possible to create lovely visualizations based on data. In fact, D3 stands for Data Driven Documents. More likely than not, many of the cool graphics and interactive visualizations that you've encountered online, most notably those that are driven by complex data, are powered in part by d3. So naturally, I figured it would make sense…

Read more »

Discrimination

August 23, 2013
By
Discrimination

Sometimes it's cool to discriminate. (I mean, if Abercrombie does it...) There I said it. I'm sick and tired of people being all PC(A) about it. I think Linear Discriminant Analysis is a great way to classify your data, and I don't care who knows it. ...

Read more »

Principally speaking, red or white?

August 5, 2013
By
Principally speaking, red or white?

So it's been a while since I posted. Life, summer, stuff, so it goes. But you're not here to listen to me make excuses. You're here to learn about the efficacy of dimension reduction via orthoganol rotations. You just don't know it yet. And how exactl...

Read more »


Subscribe

Email:

  Subscribe