The purpose of the Spam Filter Web Service is to assist colleges in making accurate and informed decisions on whether an application coming in through CCCApply is fraudulent or not. At the heart of the web service is a machine learning, continuous retraining model that does NOT make any decisions, it just predicts whether an application meets the "identifiers" that have been collected by the model based on thousands of confirmed spam by the colleges. The User Interface gives the colleges the ability to review each application that has been identified as fraud, and through continuous learning allows the model to grow and learn based on the college's determinations.
The articles below provide more details about the spam filter web service and the user interface.
- Issue: Rise in Fraudulent Applications in CCCApply
- Ways We Are Addressing Fraud in CCCApply
- Machine Learning Research Study
- Spam Filter Web Service & User Interface
- Pilot Project & College Participation
- Next Steps: Collecting Feedback for Future Enhancements
Message to Colleges
Even if your college is not having a problem with fraud today, there is a chance you may have a problem in the future. The spam filter web service will give you the tools and knowledge to address fraud now and in the future.