ML-based recommender system for SaaS in the higher education vertical

Thousands of scholarships worldwide require students to submit documentation that they can’t use multiple times. This leads to fewer applications and lesser chances to win a scholarship.

There are also many conditions to consider before applying – the best scholarships for a wished area of study, submission deadlines, special requirements and limitations, amount of grants and awards…

How can we make the process smoother – both for students and educational institutions?

Our client

The company created a personalized scholarship matching service and application management tool. They needed an ML algorithm for their recommender system.

Challenge

Because of the effort required to draft scholarship documentation (that can’t be used multiple times) and the number of information and grants available, students decide to apply to fewer scholarships or not to apply at all.

Our challenge was to make students aware of similar (and even identical) scholarships where they can submit the same documentation and help them narrow down their choices to the ones that match their preferences.

How we solved the challenge

We created a personalized recommendation system that matches the applicants’ interests and their data with adequate scholarships.

The system uses profile data such as age, an area of study, the name of the university, an average score grade, and demography, as well as historical data of previous preferences and activities.

We created a similarity engine that does the matching. It finds the most similar scholarship to the ones the student has already applied to.

Results

The recommendation system drastically reduced the time needed to find adequate scholarships and discover new ones.

Students reported a higher rate of success with fewer efforts – because they used the same documentation (or most of it) to submit to multiple places that matched their exact interests.


Here’s what our client said about the collaboration

“Applying to scholarships should be easy for every student. SmartCat helped us achieve that.”

Product Manager in our client’s company

Get in touch with SmartCat

Great recommender systems increase your overall bottom line and the satisfaction of your users. Just think of Amazon or Netflix.

We’re SmartCat and we’re a brain-powered AI company with offices in the Netherlands, USA, and Serbia.

We keep 3 departments crucial for AI development under one roof – Data Science, Data Engineering, and DevOps and that makes a one-stop shop for AI development projects.

 

Interested in creating an ML-based recommender system? Reach out to us today at info@smartcat.io

 

Let’s get started.

Tell us what you’re working on, we’ll answer right away.

← Previous

Optimus Power

Other success stories

See all stories→
Email sentiment analysis
User projects

Email sentiment analysis

Read post →
Churn of business customers
User projects

Churn of business customers

Read post →
FAQ chatbot with back-office
User projects

FAQ chatbot with back-office

Read post →
Search ranking for a large-scale job platform
User projects

Search ranking for a large-scale job platform

Read post →