For those who read my blog or Facebook, you probably noticed that I haven’t been posting very regularly for the past several weeks. This is mostly due to my new job with Heald College Online, where colloquially I will say there has been a “steep learning curve”, or more appropriately a “steep development curve”.
This morning I emailed Dr. Baker, the President of the International Educational Data Mining Society, the following open letter that encourages the society to rename itself to the International Educational Data Science Society, which I hope will spark dialogue within the educational data science/mining community.
Recently I started reading Data Science for Business, and it struck me that the example it gives of a company wanting to predict customer churn is quite a bit like what a school might want in predicting whether a student is likely to dropout.
For some time, I’ve been fascinated with the idea of using data to solve human problems. We know that the current economy runs on data science; Facebook and Google are quite upfront that they want to predict what you want, so they can show you ads. Brick and mortar stores are doing it too, as Target can predict when its customers are pregnant, and send appropriate coupons. I believe it must be possible to use data science in a manner that is less profit driven and more humanity driven. And so this brings me to this question, can data science save dropouts?
Looking at an example, in the Twin Rivers school district, I did some rough calculations, and it looks like the district loses approximately 1,000 students from kindergarten to high school graduation. This is 1,000 kids that will generally find the rest of lives much more difficult than if they were able to graduate. Further these 1,000 dropouts cost Twin Rivers over $10,000,000 in lost revenue. If only half of these kids could be recovered, the district would be able to fund at least 50 faculty and staff positions.
So how could the district solve this problem? There are two answers: dropout prevention and dropout recovery. I have personally worked a lot with dropout recovery for adults, and I am currently working on creating an adult-serving charter school that can help solve this problem, which I will talk about more soon in other posts.
Dropout prevention is something that is usually done in very broad strokes, and if these programs are more targeted, with support groups or extra help, they usually aren’t consistently applied across the student population (they often are based upon self-selection, parent selection, or teacher selection).
But what if there were patterns in the existing data about students that might show they were highly likely to dropout? These particular students could more cost-effectively and consistently be targeted with intervention strategies to help them stay in school.
The first question would be whether there were predictors in the current data that could be used? Most traditional demographics should not be used. Gender, race and ethnicity may at times have a correlation with students dropping out, but these are proxies to other societal issues, and any such use of the data would surely have people up in arms about “racial profiling”, etc. Some demographics might play a role in doing this type of analysis, specifically looking at socioeconomic status and English language learners. But since these two variables are so broad and change slowly, they would be useful as a tangential or supporting variable at best. Looking at specific teachers should also not be done as it would be perceived as a form of teacher evaluation, and would probably not be compatible with the contract. As such it would also likely get the ire of the teacher’s union, and getting their support is important to getting a successful outcome.
So I think the answer is to see if there are patterns in student behavior that might be predictors of a student dropping out. A school’s various student information systems has attendance data, grades, the courses students have taken, standardized test scores, etc. By using automated statistical techniques, it could be determined if these variables often have some types of patterns to them when students drop out, and if so, then in almost real-time (although more likely on a weekly basis), the school could look for these patterns, and have counselors or teachers work with the students who were determined to be most at-risk to see if these student can be saved from dropping out.
I am going to share this post with some of the folks with Twin Rivers, and I hope to post more soon about how such a project like this might be able to be done, and which specific steps would be involved. Maybe, I’ll even be able to be involved with working with Twin Rivers to do it… We will see!
My recent post about advice to a new teacher got me thinking more about how the “agile” method of doing things: using feedback loops to make iterative improvements, generally quickly and on a small scale, is a theme of how education can be improved at many levels. I think I need to explore this idea more. In fact, I gave some thought to using the idea for my doctoral thesis, but I don’t think that is the right platform, as doctoral theses are more “waterfall” in how they are done, with formalization and committees and other bureaucratic factors all over the place, which is in some ways the antithesis of agile… But does it have to be that way? Is there a way to have education be both agile AND accountable? Software development has seemed to have found a way to do both, and one can make the argument that agile software development is more accountable to the end-user. Could agile education be more accountable to the student (and parent(s)?).
This is just a start to the idea. There has been only a little written about the idea in education, at least with the term “agile education” (Although I’m sure the concept probably exists under several other terms, and it will take work with the literature to find these.)
But following agile educational principles, I think I will try to develop my ideas on the topic in an agile way. Such as starting with this blog entry.
Recently a first year ICT teacher contacted me about the class he is about to teach, looking to learn as much as he can before starting that course. Like many CTE teachers, he has a wealth of experience in industry, but not in being a teacher. Here is an excerpt of the email I sent him with my advice, which I hope is both valuable to him, and valuable to other first year teachers (and maybe even veteran teachers). I hope to further expand upon the concept of “Agile Education” in the future, as it seems to be an idea whose time has come:
The following advice I’m going to give you is only my personal advice, and is not the advice you would normally receive from most people in education, and is contrary to what you will likely be told be others, so beware following it. 🙂
The first year of teaching will have so many unknowns to it, that I think you should design your curriculum to be as flexible as possible. For instance, keep your syllabus being basically your course description, and don’t try to detail every day of it. Don’t try and write lesson plans for the whole course. At least not yet. The reason I say this, is that it is inevitable that some of the assumptions you are going to make right now about how the students will learn, will be completely wrong, and if you detail everything up-front, you will either need to stick with the detailed plan that will fail, or change it on the kids, which while changing things is quite valid, it is often confusing for the kids and their parents, and unfortunately while it should logically increase the validity of your as teaching, changing things from what we originally said may make you look less reputable. But this doesn’t mean I’m advocating doing no planning or prepping. But think of your course more as agile development than “waterfall”, and develop it in weekly chunks.
With this development process in mind, the first week should be about getting to know your students. Some of the critical things to learn about them is:
- What background do they have academically? (how are they in math, logic, communication, etc.?)
- What are their current interests?
- What do they see as their future after high school?
Use both “quantitative” and “qualitative” data to make this judgement. For instance, if you can get a hold of their transcripts, to see their past classes, that is a good starting point to know their background, but don’t rely on it alone, a good or bad grade in a previous class often has as much to do with the teacher than the student. So talk with your students, have them type up their answers in a word processing program, and pay as much attention to how they use that program (typing speed, style, software knowledge, and willingness to try things) as to what they say.
Also, be careful to not have this process of evaluation become one where you judge their chances of success. Your job is to help each one to become a success, and while it will be easier and more difficult in different cases, and while realistically you won’t always reach the level of success of teaching you may want with each student, your goal is still for success. So in other words, gathering this data should not be for “filtration” purposes.
Also, remember the answers to these initial questions for each student won’t necessarily be the same after they are done with your course. Very often students will only have a vague idea of what their future after high school will be, and it is that one teacher in their life that inspired them to go on to do great things.
But, the answers you find from this first week will be invaluable to your curriculum, as it can give you ideas for projects you will do with the whole class, or for projects that the students will do individually or in groups. It will also help you structure your curriculum. And it will help you later with how you create groups for group projects, as I recommend you try to balance groups. Your skills in management will be extremely valuable to you with all of this.
Then after your first week, decide what to do your second week. And when you do it the first day of the second week, and you find “bugs” in your methods of teaching, then fix them, even if that means basically repeating a day, but don’t repeat it the same way, as obviously if one method didn’t work, you will need to try another.
And be honest with your students about this process. You may even want to explain how your teaching style is like troubleshooting technology problems or debugging. By using this analogy with them, it will form a congruence that will help them educationally and help them to accept your mistakes, and hopefully accept their own mistakes, because we know in the ICT world, that often we go down several wrong paths before we get to the right one, and the world is really iterative not linear.
I hope this helps, although if you follow my advice, be prepared to defend the logic of it, as again it is not the usual methodology told to new teachers.