- Utilizing predictive analytics to identify patterns in LMS data, to predict if students will pass a course or not
- Make sense of trends, create customs reports to help several departments make key decisions
- Single environment for data collection and storage, processing, analytics, and forecast. This simplifies the stack, eliminates silos, and lowers cost
- Now proper analysis and prediction of seasonal test demand leads to more efficiency and lower operational costs for the testing center
One of the nation's elite research universities, Florida State University (FSU) preserves, expands, and disseminates knowledge in the sciences, technology, arts, humanities, and professions, while embracing a philosophy of learning strongly rooted in the traditions of the liberal arts and critical thinking. Founded in 1851, it is located on the oldest continuous site of higher education in the state of Florida.
With the responsibility for Learning Management System (LMS) reporting on over 40,000 students and 3,000 instructors, the FSU Office of Distance Learning’s (ODL) limited data technology staff was looking for a way to address challenges and automate processes that had traditionally been manual. For public universities, metrics such as retention rate and graduation rate are important indicators for standing out in the competitive landscape. These success metrics are paramount to bringing in more students, making them successful, and continuing to grow a strong alumni network.
ODL was experiencing challenges with data loss, an inability to do advanced analytics due to limited resources, and needed more information about how to process data from various sources. Data was siloed and the team didn’t have a robust and security compliant environment to properly collect, process, and analyze the data. There was also an issue of space constraints - the LMS application servers and database generated vast amounts of data files, causing capacity limits to be reached on a recurring basis, so decisions had to be made regularly on what could be kept and what had to be sacrificed.
The need to provide better data and help improve student graduation rates as well as maximize retention, pushed ODL to utilize predictive analytics with a more robust and complete big data stack. The university uses the Canvas Learning Management System (LMS) to track student activity in a particular course. With Cloudera’s platform, ODL can now identify patterns in the LMS data, helping them identify students that are at risk of falling behind or failing in a course. Algorithms such as Logistic Regression in Apache Spark ML are used to predict if students will pass a course or not. Similar to financial service fraud analysis, the university can now also monitor cheating - helping to pinpoint and investigate it as needed, thereby also ensuring the quality of its graduates.
Several departments across the university rely on reporting from the ODL technology team to power decision making. Previously, ODL was having to look through spreadsheets, compressed server logs, database output, and manually piece data together to create these reports. With Cloudera’s tools, the data is prepared so it can be utilized with Apache Impala and Apache Hive to build insightful use cases and make sense of trends as well as create custom reports that help the departments make decisions.
Another primary use case where there was a need to store and analyze massive amounts of data was for the testing center. Previously, the testing center hired and scheduled staff without knowing how many students were going to show up. This guesswork created issues and inefficiencies. By utilizing Cloudera’s platform, proper analysis and prediction of seasonal test demand could be conducted. With these insights, the testing center could improve processes and efficiency with better scheduling.