blending database systems to prepare for predictive
play

Blending Database Systems to Prepare for Predictive Modeling - PowerPoint PPT Presentation

Blending Database Systems to Prepare for Predictive Modeling Kristen Salomonson Dean of Enrollment Services Ferris State University Jon MacMillan Senior Data Analyst Rapid Insight June 11 th , 2019 Agenda About Rapid Insight The Data


  1. Blending Database Systems to Prepare for Predictive Modeling Kristen Salomonson Dean of Enrollment Services Ferris State University Jon MacMillan Senior Data Analyst Rapid Insight June 11 th , 2019

  2. Agenda • About Rapid Insight • The Data Imperative • Putting Data Into Action • Demonstrating Success • What ’ s Next? • Software Demonstration

  3. About Rapid Insight Predictive analytics and data preparation software company empowering professionals of all skill levels to turn raw data into actionable insights Serving thousands of Code free Founded in 2002 users worldwide, (but code friendly) and headquartered ranging from self-service in Conway, NH healthcare to higher analytics platform education The Veera platform enables users to easily build predictive models, perform advanced data analysis, and share insights

  4. The Veera Platform Veera Construct enables everyone from citizen data scientists to PhD statisticians to turn any data into actionable information Veera Predict enables users of any skill level to analyze data and build predictive models in a fraction of time required by other tools Veera Bridge empowers organizations by democratizing data with its cloud-based collaboration platform

  5. The Veera Platform Data Data Sources Destinations Data Preparation Predictive Modeling

  6. Upcoming Events Rapid Insight User Conference - June 23-25 th North Conway, NH An opportunity for users, old and new, to learn about the benefits and pitfalls of bringing real data analysis to their organization More information at: rapidinsight.com/riconf/

  7. Blending Database Systems to Prepare for Predictive Modeling

  8. About Ferris State University • Located in Big Rapids, Michigan • Mid-sized four-year public university • Offers Associate to Doctoral Degrees

  9. The Data Imperative Percent Change High School Graduates, 2013-2032 Source: WICHE

  10. In 2013 From 2013 to 2025 From 2025 to 2032 CA 456,000 -25,000 -5% -37,000 -9% TX 314,000 61,000 19% -6,000 -2% NY 212,000 2,000 1% -14,000 -7% FL 176,000 17,000 10% -16,000 -8% Hard IL 153,000 -10,000 -7% -18,000 -13% Demographic PA 146,000 -6,000 -4% -8,000 -6% Truths OH 135,000 -16,000 -12% -9,000 -8% MI 111,000 -14,000 -13% -10,000 -10% NJ 109,000 -6,000 -6% -12,000 -12% NC 101,000 9,000 9% -8,000 -7% • Predicted decrease in the number of high school graduates Source: WICHE • Michigan on a percentage will experience the largest decline

  11. How do we do what we know we have to do?

  12. Challenges to Making Data More Agile Multiple systems generating data about a greater number of recruitment and retention activities than ever before. Many existing analytic tools use only a small fraction of available data for predictions with wider error margins. Limits on in-house staff with the time and knowledge to do the work.

  13. • NRCCUA, ACT & SAT • Salesforce • Ellucian Banner • Target X Events • Orientation Registration (Homegrown) • Advantage Design Orientation Module You Want Data • SMS Magic Text • Marketing Cloud We’ve Got Data • Pardot • Ten Fold Call Management • Google analytics • Consumer databases • Blackboard • Adirondack

  14. Connect the Data, Solve the Problem Manage institutional Answer strategic data silos enrollment questions Perform sophisticated and broad analytics

  15. So, About those Silos… The Veera The data platform enables delineation process It’s flexible so we us to create is surprisingly can add and automatic linkages enjoyable and remove what we with our multiple include. extremely useful. data sources.

  16. example Rapid Insight into Action Initial Apply to Enroll Model New Data Source & Instant Connection • Using the Quick Start Banner got us • Residence Life implemented off to a fast start. Yada this year for roommate match. • We wanted to include more data from our CRM. • New source was seamlessly • Discovered a hidden data gem with connected so we could the first model. integrate the data into our Apply to Enroll model. *Greater # of people brought to event – higher likelihood of enrolling

  17. Rapid Insight tools help us to take advantage of our multiple data sources Analytics With… and use them to create the best possible models to enhance predictive utility. Our Apply to Enroll model analysis included Breadth. over 150 variables. We are squeezing out Sophistication. every last drop of predictive utility. An earlier off-the-shelf model gave us 6. Why Not Both ? The results enable us to target individual applicants, segments, colleges and institution-wide performance.

  18. example Rapid Insight into Real-Time Impact Likelihood to Enroll Tailored Action Impact on FTIAC Model Output Score Generated Paths Deployed Enrollment Select applicants Rapid Insight Daily Scores loaded targeted with robust Fall 17: +24 (1.5%) predictive model into Salesforce for outreach to increase Fall 18: +70 (4%) enrollment developed Recruitment Staff probability Not Just Higher Student Counts 1. Higher Net Tuition Revenue 2. Reduced Recruiting Costs per Student

  19. Individual – A sought-after student in one of your top programs hasn’t signed up for Orientation. Q: What is the likelihood that Applicant K will enroll in the Fall? Action: Score in range where a personal call is warranted. Assists with Group – A recruiter wonders how to make time management Answering decisions to optimize their yield. Q: How many Applicants in my territory are at least 70% likely to enroll? Questions Action: Reaches out via text to these students and asks if there are follow-up questions. in Real Time Institution – A budget director asks for assistance in estimating tuition revenue next year. Q: What is the predicted enrollment of new and returning students? Action: Fuse results from Admissions and Retention Models to develop an estimate. 2018/19 estimate was off by .2%.

  20. What Comes Next? • Expand data integration with digital advertising metrics • Roll out model outputs deeper into the academic colleges and departments • Explore using discrete models for admission and retention of our Test Optional pathway • Utilize model results to inform and assess enrollment goals in the new strategic plan

  21. Software Demonstration

  22. Questions?

  23. Thank You! Jon MacMillan Kristen Salomonson Rapid Insight Ferris State University Senior Data Analyst Dean of Enrollment Services Jon.MacMillan@rapidinsight.com KristenSalomonson@ferris.edu To get a free trial of the Veera platform, visit www.rapidinsight.com/free-trial

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend