Blog Archives

How Do You Know if Your Data Has Signal?

August 10, 2015
By
How Do You Know if Your Data Has Signal?

Image by Liz Sullivan, Creative Commons. Source: Wikimedia An all too common approach to modeling in data science is to throw all possible variables at a modeling procedure and “let the algorithm sort it out.” This is tempting when you are not sure what are the true causes or predictors of the phenomenon you are … Continue reading...

Read more »

Working with Sessionized Data 2: Variable Selection

July 15, 2015
By

In our previous post in this series, we introduced sessionization, or converting log data into a form that’s suitable for analysis. We looked at basic considerations, like dealing with time, choosing an appropriate dataset for training models, and choosing appropriate (and achievable) business goals. In that previous example, we sessionized the data by considering all … Continue reading...

Read more »

Working with Sessionized Data 1: Evaluating Hazard Models

July 8, 2015
By

When we teach data science we emphasize the data scientist’s responsibility to transform available data from multiple systems of record into a wide or denormalized form. In such a “ready to analyze” form each individual example gets a row of data and every fact about the example is a column. Usually transforming data into this … Continue reading...

Read more »

Wanted: A Perfect Scatterplot (with Marginals)

June 11, 2015
By
Wanted: A Perfect Scatterplot (with Marginals)

We saw this scatterplot with marginal densities the other day, in a blog post by Thomas Wiecki: The graph was produced in Python, using the seaborn package. Seaborn calls it a “jointplot;” it’s called a “scatterhist” in Matlab, apparently. The seaborn version also shows the strength of the linear relationship between the x and y … Continue reading...

Read more »

Does Balancing Classes Improve Classifier Performance?

February 27, 2015
By
Does Balancing Classes Improve Classifier Performance?

It’s a folk theorem I sometimes hear from colleagues and clients: that you must balance the class prevalence before training a classifier. Certainly, I believe that classification tends to be easier when the classes are nearly balanced, especially when the class you are actually interested in is the rarer one. But I have always been … Continue reading...

Read more »

The Geometry of Classifiers

December 18, 2014
By
The Geometry of Classifiers

As John mentioned in his last post, we have been quite interested in the recent study by Fernandez-Delgado, et.al., “Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?” (the “DWN study” for short), which evaluated 179 popular implementations of common classification algorithms over 120 or so data sets, mostly from the UCI … Continue reading...

Read more »

Estimating Generalization Error with the PRESS statistic

September 25, 2014
By
Estimating Generalization Error with the PRESS statistic

As we’ve mentioned on previous occasions, one of the defining characteristics of data science is the emphasis on the availability of “large” data sets, which we define as “enough data that statistical efficiency is not a concern” (note that a “large” data set need not be “big data,” however you choose to define it). In Related posts:

Read more »

Vtreat: designing a package for variable treatment

August 7, 2014
By
Vtreat: designing a package for variable treatment

When you apply machine learning algorithms on a regular basis, on a wide variety of data sets, you find that certain data issues come up again and again: Missing values (NA or blanks) Problematic numerical values (Inf, NaN, sentinel values like 999999999 or -1) Valid categorical levels that don’t appear in the training data (especially Related posts:

Read more »

Trimming the Fat from glm() Models in R

May 30, 2014
By
Trimming the Fat from glm() Models in R

One of the attractive aspects of logistic regression models (and linear models in general) is their compactness: the size of the model grows in the number of coefficients, not in the size of the training data. With R, though, glm models are not so concise; we noticed this to our dismay when we tried to Related posts:

Read more »

Bandit Formulations for A/B Tests: Some Intuition

April 24, 2014
By
Bandit Formulations for A/B Tests: Some Intuition

Controlled experiments embody the best scientific design for establishing a causal relationship between changes and their influence on user-observable behavior. – Kohavi, Henne, Sommerfeld, “Practical Guide to Controlled Experiments on the Web” (2007) A/B tests are one of the simplest ways of running controlled experiments to evaluate the efficacy of a proposed improvement (a new Related posts:

Read more »