Responsive Menu
 

INDUSTRY: Education

How Accelirate’s RPA and ML Automate Enrollment Process for Leading Education Firm, Delivering $1.2M ROI Annually

112,000+

Monthly Work
Hours Saved

$1.2

Million Annual
ROI

Client Overview

The client is a leading online education provider in the United States, affiliated with over 300 schools. They receive more than two million applications annually, each requiring multiple supporting documents. Managing and processing these applications, particularly during peak enrollment periods, required substantial human resources.

Key Takeaways

  • Integration of machine learning, computer vision, and RPA automate enrollment process and streamline document submissions.
  • Significant reduction in manual processing time and operational costs.
  • Automated system ensures compliance with document guidelines, reducing errors and improving application approval rates.
The client, a leading online education provider, faced difficulties with the manual processing of enrollment applications, especially during peak times. With 120 part-time officers and 35 full-time employees dedicated to processing applications, the workload was overwhelming. Each application required meticulous document handling, including image adjustments to meet strict guidelines. To manage this situation, the client engaged Accelirate, a global automation provider, to implement a comprehensive solution.
Accelirate combined machine learning, computer vision, and RPA to automate enrollment process effectively. This innovative approach was necessary due to the unique nature of each document submitted, which existing solutions could not adequately address.

Overcoming Manual Overload with Automated Enrollment Process through Integrated ML and RPA

The existing enrollment process of the client was filled with multiple challenges that significantly affected efficiency and accuracy. The client receives over two million applications annually, each accompanied by various supporting documents, such as birth certificates and school transcripts. Processing these student applications was time-consuming due to stringent document approval guidelines. Each affiliated school required documents to meet specific criteria, including proper alignment in portrait mode, no skewing, no visible background, and standard US letter size (8.5×11 inches).
Given that 85% of the documents were submitted via mobile devices, many images were poorly aligned, skewed, or had visible backgrounds, causing frequent rejections and requiring extensive manual adjustments.
During peak enrollment periods, the client employed 120 part-time enrollment officers in addition to their 35 full-time staff to manage the overwhelming volume of applications. This led to inefficiencies and frustration for both staff and applicants.
To address these challenges, Accelirate implemented a comprehensive automation solution that combined machine learning, computer vision, and RPA, to automate student enrollment. The solution was categorized into four parts.
automatic rotation
automatic rotation

01- Automatic Rotation and Skew Detection

Deep learning-based Machine Learning Models were trained with historic images that were manually processed by the enrollment department in previous years. Computer Vision Algorithms were used to rotate images and remove their identified skew to meet the document image guidelines.

02 - Document Image Automatic Cropping

Machine Learning and Computer Vision-based edge and corner detection algorithms were applied to locate the corners and edges of the document in the image accurately. The image is then cropped precisely up to the document edge to remove any part of the image that is not part of the document photographed.

03 - Document Classification

Machine Learning-based document classifiers were created and trained using the client’s large database of correctly labeled and accepted or rejected documents and application submissions. The bot labels each document correctly, matches it to the list of acceptable documents for each category (ex. “School X” might only accept a utility bill or a bank statement as an adequate submission to provide proof of address. So, if a photo of a parent’s driver’s license is submitted, even though it has their resident addresses listed on it, it is not an accepted form by that school and is rejected) and then accepts or rejects the application depending on whether or not all the documents match the accepted forms for each application category.

04 - Document Intake and Upload Pipelines

Bot intakes all the applications uploaded to Salesforce using APIs and executes all the steps above as each is an independent python module in the RPA workflow. The processed documents with attached remarks (either to accept or reject) are then uploaded to the school’s respective application.

Delivering Measurable Outcomes and Value Addition from Enrollment Automation

By integrating machine learning, computer vision, and RPA, the client not only streamlined their operations but also significantly enhanced the accuracy and speed of application processing. The unique aspect of this solution was its ability to handle the diverse and complex nature of the documents submitted, ensuring compliance with each school’s specific guidelines and enabling admissions automation in the education sector. This tailored approach led to a substantial reduction in manual workload, allowing enrollment officers to focus on more strategic tasks and improving overall customer satisfaction.

01 - Significant Time Savings

Achieved over 112,000 workhours saved per month, freeing up resources for higher-value tasks and reducing the need for extensive overtime.

02 - Annual ROI Impact

Experienced an impressive annual ROI of $1.2 million, demonstrating the substantial financial benefits of the automation solution.

03 - Enhanced Processing Speed

Increased the speed of document processing by eliminating manual adjustments and rejections, leading to quicker application turnaround times.

04 - Error Reduction

Decreased the error rate in document processing, ensuring more accurate and reliable application handling and reducing the frequency of application rejections.

05 - Improved Document Handling Efficiency

Streamlined the management of document images with automatic rotation, cropping, and classification, enhancing overall workflow efficiency.

06 - Scalable Automation

Implemented a scalable solution that can handle increased volumes of applications and adapt to future changes in processing requirements without compromising performance.

07 - Customer Satisfaction Boost

Enhanced the experience for applicants by reducing processing delays and minimizing the need for resubmissions, leading to higher satisfaction rates.

08 - Optimized Resource Allocation

Allowed for better allocation of resources by reducing the dependency on manual labor and improving the efficiency of the enrollment department.
machine learning integration

Enhancing Operational Success and ROI with Accelirate’s RPA in Education

This case study showcases how Accelirate successfully automate enrollment process for a leading online education provider by leveraging advanced technologies such as machine learning, computer vision, and RPA. By addressing the unique challenges of document processing and compliance with specific school guidelines, the customized automation solution streamlined operations, significantly reduced manual workloads, and improved overall efficiency. RPA in Education has been rapidly gaining momentum and partnering with a trusted automation provider like Accelirate can ensure seamless transformation. Got more questions? Connect with us today!

Need a Quick Reference?

Download the mini version of our case study for easy sharing with your team.