Rapid Insight at Ellucian Live

If you’re planning on attending Ellucian Live next week, we’d like to invite you to check out our session “Bringing Predictive Analytics In-House: A Case Study with Dickinson College”, co-presented by Michael Johnson, Director of Institutional Research at Dickinson College, and Michael Laracy, Founder and CEO of Rapid Insight. The session will take place on April 9^th at 10:50am in Room 204C.

As an Ellucian Community Partner, Rapid Insight provides Ellucian customers with predictive modeling solutions that are easy to implement. Join this session to see what is possible when you bring the right kind of predictive modeling in-house.

Attendees will discover how they can successfully use predictive modeling in all parts of the enrollment management process, including student retention, as well as to boost fundraising effectiveness.

We hope you’ll join our session and stop by Booth 102 to say hello!

*

For those who aren’t attending Ellucian Live, be sure to check out our case study and webinar with Mike Johnson on his experiences with building predictive models at Dickinson College. 

Customer Webinar: Predictive Modeling for SEM

Our next customer webinar, "Strategic Enrollment Management: St. Michael's College and Predictive Analytics" will be given by Bill Anderson, CIO of Saint Michael's College today at 2pm EDT and will be re-broadcasted on Tuesday, March 26th, and Thursday, May 2nd. 

I got the chance to ask him a couple of questions about his session, which will describe the ways in which Veera and Analytics are utilized on campus to produce predictions and other analyses for the scoring team. 

What types of models have you been building?
Almost entirely enrollment management - mostly apply to enroll. We've been building them on and off for about five years now. I have someone on campus that I collaborate with and when we first started, she was using SPSS for the statistical analysis, but we've since abandoned that. 

How has model building changed your Enrollment and/or Financial Aid practices?
There have been a number of ways that we've used the models - one as a sort of verification of what our consultant has been doing, two to be able to do some sensitivity and what-if analysis (and suggest different practices or emphases on where the aid awards should go), and three to help confirm in-semester and in-process prediction on where the class is going to end up. 

In some occasions, this has impacted size of waiting list or the way we thought about awarding wait list spots, including the total number of admits. This last year, our model suggested that we could be more selective than we had been in the past. 

What do you hope attendees will learn from your presentation?
One thing is that you can do it on your own - it's not that hard. You have to have a background that supports responsible interpretation of the results, but you can sit down and do it. That's one element: just do it. I think there's another element that says once you start thinking this way, it can become infectious. In our enrollment management meetings, we have the opportunity to appeal to the data or look at a Veera job that identifies the applicants we could avoid accepting. This changes the internal conversation - from a culture of anecdote, you can change the conversation with data. The use of the products has been fabulous in terms of making the data accessible to people. 

Rapid Insight's 5th Annual User Conference

Let the countdown to the 5th annual Rapid Insight User Conference begin! Here’s what you need to know about this fun and informative event:

We are making one big change this year: we’ve outgrown our space here in NH and are hosting the conference on the campus of Yale University in New Haven, Connecticut. It will kick off at 9am on Thursday, June 27^th and wrap up by 4pm on Friday, June 28^th. The cost of the conference is $150 per attendee.  In addition to the presentations and hands-on labs, we’ll be providing a continental breakfasts and an evening reception to all registrants.

For User Conference lodging, we recommend the Omni New Haven Hotel at Yale. We have arranged a special rate of $169/night + tax available through 5/26. You’ll find the dedicated Conference link to guarantee this rate, along with additional travel information, on the official User Conference webpage.

Be sure to check the Conference webpage frequently for updates on specific sessions and activities as the date draws near. We look forward to seeing you there!

Six Predictive Modeling Mistakes

As we mentioned in our post on Data Preparation Mistakes, we've built many predictive models in the Rapid Insight office. During the predictive modeling process, there are many places where it's easy to make mistakes. Luckily, we've compiled a few here so you can learn from our mistakes and avoid them in your own analyses:

Failing to consider enough variables

When deciding which variables to audition for a model, you want to include anything you have on-hand that you think could possibly be predictive. Weeding out the extra variables is something that your modeling program will do, so don’t be afraid to throw the kitchen sink at it for your first pass.

Not hand-crafting some additional variables

Any guide-list of variables should be used as just that – a guide – enriched by other variables that may be unique to your institution.  If there are few unique variables to be had, consider creating some to augment your dataset. Try adding new fields like “distance from institution” or creating riffs and derivations of variables you already have.

Selecting the wrong Y-variable

When building your dataset for a logistic regression model, you’ll want to select the response with the smaller number of data points as your y-variable. A great example of this from the higher ed world would come from building a retention model. In most cases, you’ll actually want to model attrition, identifying those students who are likely to leave (hopefully the smaller group!) rather than those who are likely to stay.

Not enough Y-variable responses

Along with making sure that your model population is large enough (1,000 records minimum) and spans enough time (3 years is good), you’ll want to make sure that there are enough Y-variable responses to model. Generally, you’ll want to shoot for at least 100 instances of the response you’d like to model.

Building a model on the wrong population

To borrow an example from the world of fundraising, a model built to predict future giving will look a lot different for someone with a giving history than someone who has never given before. Consider which population you’d eventually like to use the model to score and build the model tailored to that population, or consider building two models, one for each sub-group.

Judging the quality of a model using one measure

It’s difficult to capture the quality of a model in a single number, which is why modeling outputs provide so many model fit measures. Beyond the numbers, graphic outputs like decile analysis and lift analysis can provide visual insight into how well the model is fitting your data and what the gains from using a model are likely to be.

If you’re not sure which model measures to focus on, ask around. If you know someone building models similar to yours, see which ones they rely on and what ranges they shoot for. The take-home point is that with all of the information available on a model output, you’ll want to consider multiple gauges before deciding whether your model is worth moving forward with.  

-Caitlin Garrett, Statistical Analyst at Rapid Insight
Photo Credit: http://www.flickr.com/photos/mattimattila/

Have you made any of the above mistakes? Tell us about it (and how you found it!) in the comments. 

Facebook's Graph Search and Prospect Research

“Facebook’s mission is to make the world more open and connected. The main way we do this is by giving people the tools to map out their relationships with the people and things they care about. We call this map the graph. It’s big and constantly expanding with new people, content, and connections. There are already more than a billion people, more than 240 billion photos, and more than a trillion connections. Today we’re announcing a new way to navigate these connections and make them more useful.”  [Facebook]

Introducing Graph Search

Last week, Facebook unveiled their new Graph Search tool, which allows users to search for Facebook users by interests, likes, relationship status, and location, among other qualifiers. Examples of searches include “Friends who like yoga who live in Chicago”, “Pictures of friends taken before 1998”, or “Friends who like Make-A-Wish”. The results of these searches can reveal full names, addresses, employers, friends and family, and photographs. Creative searching can yield some very telling results, as evidenced by a popular Tumblr site’s investigation into search possibilities.  Currently, graph search is still in beta, and you can join the waiting list here.

Specifics on Graph Search Data

In truth, all of the data gathered by Graph Search has been available for quite some time.  But the lack of an all-encompassing search feature made this data fairly obscure and hard to collect - until now.  So far, researchers aren’t sure how users will react to their personal data being more easily mined. Many users are likely to get a bit freaked out by their inclusion in these “big net” searches.  They’ll respond by making their information more private using Facebook’s existing privacy settings.  Chances are that most will passively accept this feature as an acceptable part of living in an age of social connectivity.  A few may even begin sharing more information in an effort to provide and receive more of the purported benefits.

Potential users of Graph Search need to remember the caveats.  Facebook’s information can be incomplete, deceptive, and even fictitious (“ironic likes” for example).  Then there are the obvious limitations – users need to like pages to generate searchable connections.   But the breadth and depth of data Facebook offers can’t be found anywhere else.  Leveraging the interlacing interests of individuals, businesses, and organizations into some very powerful insights is simply too valuable to ignore.

Using Graph Search for Prospect Research

So what does Graph Search mean for prospect researchers?  It means effectively mining the 8+ years of data that Facebook has been collecting just got a whole lot easier.  There are several ways that I see it helping immediately.

The ease of collecting data makes it easier to patch holes in current constituent datasets. With a little creativity, leveraging the new search options may make more imputation of variables possible, particularly by examining constituent relationships and interests. For example, age can be imputed by graduation year, which will become searchable.  

There will be better opportunities for identifying new constituents based on searches. Possible search ideas include: friends of those who are already involved with the organization, people who live nearby, people whose interests coincide with your institution’s mission, or any combination of the above. Finding friends of users who like a page is a quick search, and aggregating this list to people who live nearby will become a piece of cake.

Your Institution’s Facebook Page

On the flip side, the interest and ability of others to find you through a Graph Search should not be overlooked.  Information about fundraising organizations is about to become a whole lot more visible. The number of channels by which organizations can be searched will also greatly increase, which can mean more traffic for your page. Here are a few steps to take in preparation for the widespread release:

• Fill out the basic information section of your page, and include as many relevant keywords as needed. This includes selecting a category and sub-categories if you haven't already. 
• Make sure your address is up to date. Because users can search by address, you'll want this information to be as accurate as possible. 
• Got photos? Label them with descriptive text, tag the people in them, and add a location to them. Photos are fair game for searches, and the more information you can provide at a glance, the better. 
• If you haven't already, update your page's URL to be customized, preferably containing the name of your organization. This will also improve your SEO on Google. 
• Check your content. Gathering and retaining followers is more important than ever. Make sure to keep things relevant and interesting to keep people engaged. 
• Once Graph Search becomes available to the whole Facebook community, try constructing searches that you would hope your page would appear in. If it doesn't, look to those whose pages did appear and imitate what they did to list so well - the sincerest form of flattery!

For more information on Graph Search, visit https://www.facebook.com/about/graphsearch .

For follow-up questions, or help working with your data for this purpose, contact Caitlin Garrett at caitlin.garrett@rapidinsightinc.com. Our next exploration will be on using Graph Search for Enrollment and Recruiting. Please feel free to comment if you have thoughts on additional ways to use the tool. 

Caitlin Garrett, Statistical Analyst at Rapid Insight