The Data Science Team recently released its set of predictions for the 6-year graduation probabilities of the 2020 Freshman cohort. Below is a snapshot of the current cohort's predictions, in blue, with the 2019 Freshman cohort's predictions, in red. 

The vertical axis represents the end of 2nd semester prediction probability; the horizontal axis is the end of the 3rd semester prediction. 

The black diagonal line indicates the point on the graph at which the second semester and third semester predictions are equal. If a dot, representing an individual student, rests on the line there was no change in the student's predicted probability of graduating between their second and third semester. Points above the line mean a student's predicted 6-year graduation probability decreased from semester 2 to semester 3. 

The group of students above the line, particularly in the Moderate and Low probability color bands, are of concern as their predicted probabilities of graduation have declined over their last two completed semesters. 

The 2020 Freshman cohort was the first freshman class during COVID and one of the concerns is the effect COVID may have on student performance in later semesters. From the predictions chart there seems to be reasons for optimism. Looking at the dispersion of points, there is a greater concentration of students in the High and Very High likelihood buckets compared to the 2019 cohort, as shown by the clustering of blue dots in the upper right corner of the chart. 

However, some concern may remain. Students whose predictions fall in the Low and Moderate buckets have experienced sharper declines in predicted likelihood to graduate than students from the 2019 cohort (because the blue dots, 2020 cohort, are much further above the diagonal line than the red dots, 2019 cohort). 

The diagram we've shown in this post is produced by a tool developed by the Data Science Team.  The tool allows staff with broad student success responsibilities to identify groups of students who may need additional support to achieve their goals.  The tool is available at analytics.umbc.edu in the student success section.  Access to it requires permission.  

(NOTE: Please join us Friday, March 18th from 12-1pm, for the fourth in our series of our Spring 2022 Data Science Workshops. This predictive model will be the topic of the session. Go to this link - https://my3.my.umbc.edu/groups/instructional-technology/events/101281 to register)

Len Mancini

Data Scientist and Statistical Specialist

The Analytics, Business Intelligence, and Student Success Technologies Group is part of the Provost;s Office and the Division of Information Technology.  Our component parts include the Business Intelligence/Data Warehouse Team, the Analytics/Data Science Team, the PeopleSoft SA/Salesforce Team, and since late 2021, the myUMBC/Campus Information Portal Team.  

We're very pleased to provide you with our "annual" report (delayed by the pandemic, like so many other things).  The report details selected projects and initiatives from 2019 through mid-year 2021, our goals, and our projects going forward.  As the report is part of our assessment activities, we welcome your comments.

We are grateful to our many collaborators and partners across the campus.  Success is never final, but it is also surely a joint effort.

First-year retention is UMBC’s single biggest point of loss during the lifetime of a freshman cohort and a key focus area of the university’s student success efforts. To support this work the Data Science Team (from DoIT and the Provost's Office) and its campus partners have worked with our HelioCampus to produce the first of a series of predictive analytics reports or “playbooks.” 

The first playbook, just deployed on analytics.umbc.edu, predicts the likelihood of a first-time full-time freshman returning for their second year.  It is being used by the Academic Advocates in Undergraduate Academic Affairs to help identify students who may be at risk of not returning next fall. (Access to the playbook is role-based.)

On February 25th, at noon, the REX Analytics Group will meet to explore the factors that make these predictions change the most, how to read the dashboards, and how to interpret and use the playbook.  Please join us! Contact lmancini@umbc.edu or kjoseph@umbc.edu for meeting details.

Len Mancini

Data Scientist and Statistical Specialist

HelioCampus is a data analytics platform that provides UMBC with the next-generation decision support services.  Helio integrates our enterprise data warehouse with advanced reporting and visualization tools.  

With Helio, we can use information from our systems to answer key questions through analytics, data storytelling, and data science and do it easier and faster.  Helio is a key component of an integrated infrastructure for academic planning, assessment, and analytics.  

We’re delighted to tell you that the project and platform are starting to roll out to the campus. 

We have deployed the platform and provided initial training to a first wave of approximately two dozen people who are active users of our existing data warehouse.  This initial training focused on four key sets of dashboards:  Admissions, Enrollment, Student Retention, and Graduation.  

We will continue to conduct training sessions to additional waves of the community and provide resources for self-guided training in the use of Helio and Tableau, the platform’s visualization tool.  Tableau is easy to use, and you can learn the basics in as little as 45 minutes using our curated self-training curriculum.  

Access to the Helio platform can be found at analytics.umbc.edu.  Request access to the platform or a Tableau license at https://analytics.umbc.edu/support/request/.  Please note that there is a role-based approval process similar to that granting access to REX.

We’re grateful to our campus partners who participated in the validation and “soft launch” phase of the project.

Mathematics is a powerful tool.  We use applications from math all day, every day, like when we drive over a bridge or look at our email.  

Math is very difficult for many people, and they struggle with it.  Many students at our university (and almost all others) need to repeat a math class to progress in their program and complete their degrees.

Our research has uncovered some important facts:

• Many students repeating math classes often must do so more than one time, which extends their time to degree and could prevent them from graduating.  

• Students who use the Math and Science Tutoring Center improve their chances of passing their math courses.

• The positive effect from math tutoring is especially large for students who are repeating a course.  “Repeaters” increase their chances of success by roughly 15 to 20 percentage points!

• But, we found, only about 10 percent of students repeating math were going to tutoring

The Data Science Team, supported by DoIT and the Provost's Office, designed a pilot program in conjunction with the Math Department to “nudge” students repeating 100-level math courses to use tutoring.  

A nudge is a message designed to provide information to many people at very low cost that changes behavior over time.  An example of a nudge you see in everyday life is the roadside sign that says “Click it or ticket.”  Our nudges let students know not just that tutoring is effective, but also how effective it is.

This semester (Spring 2021) we sent nudges to 114 students using a myUMBC personal post.  About 70 percent of students receiving the nudge read them, and we have evidence that suggests that the nudge leads to an increased use of math tutoring by roughly 30 percent.  

The pilot is now in its 8th semester.  During that time we’ve nudged over 1800 students repeating their courses.  

In addition to this program, we’re using what we’ve learned about nudges to help students in other ways that support their success, including combining them with predictive analytics for enhanced early alerts.

By Bob Carpenter