Providence: Machine Learning At Stack Exchange

At Stack Exchange, we’ve historically been pretty loose with our data analysis.  You can see this in the “answered questions” definition (has an accepted answer or an answer with score > 0), “question quality” (measured by ad hoc heuristics based on votes, length, and character classes), “interesting tab” homepage algorithm (backed by a series of experimentally determined weights), and rather naïve question search function.

Note: not all nodes are picturedThis approach has worked for a long time (turns out your brain is a great tool for data analysis), but as our community grows and we tackle more difficult problems we’ve needed to become more sophisticated.  For example, we didn’t have to worry about matching users to questions when we only had 30 questions a day but 3,500 a day is a completely different story.  Some of our efforts to address these problems have already shipped, such as a more sophisticated homepage algorithm, while others are still ongoing, such as improvements to our search and quality scoring.

One of our other efforts is to better understand our users, which led to the Providence project.  Providence analyzes our traffic logs to predict some simple labels (like “is a web developer” or “uses the Java technology stack”) for each person who visits our site.  In its early incarnation, we only have a few labels but we’re planning to continue adding new labels in order to build new features and improve old ones.

While we can’t release the Stack Overflow traffic logs for privacy reasons, we believe it’s in the best interest of the community for us to document the ways we’re using it.  Accordingly, this is the first post in a series on the Providence project.  We’re going to cover each of the individual predictions made, as well as architecture, testing, and all the little (and not-so-little) problems we had shipping version 1.0.

We have also added a way for any user to download their current Providence prediction data because it’s theirs and they should be able to see and use it as they like.  Users can also prevent other systems (Careers, the Stack Overflow homepage, etc.) from querying their Providence data if they want to.

First up: What kind of developer are you?

One of the first questions we wanted Providence to answer was ‘What “kind” of developer are you?’.  This larger question also encompassed sub-questions:

  • What are the different “developer-kinds”?
  • How much, if at all, do people specialize in a single “kind” of development?
  • Among these different kinds of developers, do they use Stack Overflow differently?

We answered the first sub-question by looking at a lots and lots of résumés and job postings.  While there is definitely a fair amount of fuzziness in job titles, there’s a loose consensus on the sorts of developers out there.  After filtering out some labels for which we just didn’t have much data (more on that later), we came up with this list of developer-kinds:

  • Full Stack Web Developers
  • Front End Web Developers
  • Back End Web Developers
  • Android Developers
  • iOS Developers
  • Windows Phone Developers
  • Database Administrators
  • System Administrators
  • Desktop Developers
  • Math/Statistics Focused Developers
  • Graphics Developers

The second sub-question we answered by looking at typical users of Stack Overflow.  Our conclusion was that although many jobs are fairly specialized, few developers focus on a single role to the exclusion of all else.  This matched our intuition, because it’s pretty hard to avoid exposure to at least some web technologies, not to mention developers love to tinker with new things for the heck of it.

Answering the final sub-question was nothing short of a leap of faith.  We assumed that different kinds of developers viewed different sets of questions; and, as all we had to use were traffic logs, we couldn’t really test any other assumptions anyway.  Having moved forward regardless, we now know that we were correct, but at the time we were taking a gamble.

The Data

Engage!A prerequisite for any useful analysis is data, and for our developer-kind predictions we needed labeled data.  Seeing that Providence did not yet exist, this data had not been gathered.  This is a chicken and egg problem that frequently popped up during the Providence project.

Our solution was an activity we’ve taken to calling “labeling parties.”  Every developer at Stack Exchange was asked to go and categorize several randomly chosen users based on their Stack Overflow Careers profile, and we used this to build a data set.  For the developer-kinds problem, our labeling party hand classified 1,237 people.

The Classifier

In our experience, naïvely rubbing standard machine learning algorithms against our data rarely works.  The same goes for developer-kinds.  We attacked this problem in three different steps: structure, features, algorithms.

Looking over the different developer-kinds, it’s readily apparent that there’s an implicit hierarchy.  Many kinds are some flavor of “web developer,” while others are “mobile developer,” and the remainder are fairly niche; we’ve taken to calling “web,” “mobile,” and “other” major developer-kinds.  This observation led us to first classify the major developer-kind, and then proceed to the final labels.

Yes, the designer call out is by design

Since we only really have question tag view data to use in the initial version of Providence, all of our features are naturally tag focused.  The breakdowns of the groups of tags used in each classifier are:

  • Major Developer-Kinds
    • Web programming languages (java, c#, javascript, php, etc.)
    • Mobile programming languages (java, objective-c, etc.)
    • Non-web, non-mobile programming languages
    • iDevices
    • Web technologies (html, css, etc.)
  • Mobile Developer-Kinds
    • iDevice related (ios, objective-c, etc.)
    • Android related (android, listview, etc.)
    • Windows Phone related (window-phone, etc.)
  • Other Developer-Kinds
    • Each of the top 100 used tags on Stack Overflow
    • Pairs of each of the top 100 used tags on Stack Overflow
    • SQL related (sql, tsql, etc.)
    • Database related (mysql, postgressql, etc.)
    • Linux/Unix related (shell, bash, etc.)
    • Math related (matlab, numpy, etc.)

For many features, rather than use the total tag views, we calculate an average and then use the deviation from that.  With some features, we calculate this deviation for each developer-kind in the training set; for example, we calculate deviation from average web programming language tag views for each of the web, mobile, and other developer-kinds in the Major Developer Predictor.

Turning these features into final predictions requires an actual machine learning algorithm, but in my opinion, this is the least interesting bit of Providence.  For these predictors we found that support vector machines, with a variety of kernels, produce acceptably accurate predictions; however, the choice of algorithm mattered little, various flavors of neural networks performed reasonably well, and the largest gains always came from introducing new features.

So how well did this classifier perform?  Performance was determined with a split test of job listing ads with the control group being served with our existing algorithm which only considered geography, we’ll be covering our testing methodology in more depth in a future post.  In the end we saw an improvement for 10-30% over the control algorithm, with the largest gains being seen in the Mobile Developer-Kinds and the smallest in the Web Developer-Kinds.

Next up: What technologies do you know?

3 Comments on “Providence: Machine Learning At Stack Exchange”

  1. Interesting writeup!

    “The largest gains always came from introducing new features.” This reflects our experience as well on the majority of problems: many common algorithms get similar levels of performance (but differ based on the computational efficiency and amount of parameter tuning/babysitting required). Adding more features, especially that are derived from orthogonal sources, yields more potential gains.

    It wasn’t quite clear how you went from the automatically tagged profiles of developers to job ads: had you prioritized showing ads to users that had matching tags?

    If so, another approach to this is to have a second machine learning model in place. It would use the automatic tags, the features you used to create the tags, relevant location data, job ad features, etc. as possible inputs & then would be trained to predict the likelihood that a user would be a match for the job. (This “match” could be defined coarsely based on the likelihood of a user clicking on an ad, or have more levels of granularity, e.g. be a heuristic score that is calculated based on ad click, time spent on ad, whether the user clicked to apply to the job, etc.)

    • This is the first in a series of posts. We’ll be going over other features, the final person-to-job matching algorithms, testing, architecture, and so on over the next week or two.

  2. Some years ago, I did some experiments with the stack overflow dump to cluster users (using tags co-occurrence ). Several tags are common for some clusters but the weight of the relationships in tags made interesting networks that led to name some of the groups (PHP developers, Java Web, iPhone, Android, among others). I had almost 50 clusters 😛 of users, but I never tested my hypothesis that routing questions improves engagement.

    I find this pretty similar (although categories are based on euristics), I would like to see results.