AI-based Student Success Prediction System- ON-484

Project type: Research
Desired discipline(s): Engineering - computer / electrical, Engineering, Computer science, Mathematical Sciences, Economics, Social Sciences & Humanities
Company: ApplyBoard Inc.
Project Length: 4 to 6 months
Preferred start date: As soon as possible.
Language requirement: Flexible
Location(s): Kitchener, ON, Canada; Canada
No. of positions: 1-3
Desired education level: Master'sPhDPostdoctoral fellow
Search across Mitacs’ international networks - check this box if you’d also like to receive profiles of researchers based outside of Canada: 
No

About the company: 

ApplyBoard Inc. provides a software platform that simplifies the study abroad search, application, and acceptance process by connecting international students, recruitment partners, and academic institutions on one platform. The platform is designed to help students, partner schools and recruitment agents to succeed through intuitive and personalized user experience. Through the structured vetting system, students have a 95% chance of receiving an offer letter to their program of choice.

Describe the project.: 

The objective of the project is to develop an AI-based ecosystem to predict a international student's success (the notion of success varies based on the intended system user) after completing a given program at a given post-secondary education (PSE) institution. Multiple systems will be used to build this model. Input 1) success rates of the programs & schools; 2) value of skills acquired during their program; 3) market demand projections.

Through this research project, the primary goal of the company is to obtain knowledge and deliver a predictive AI model about chance of success for the student in not only completing their studies, but by doing so, developing skills that are in demand in the labour market at the time of graduation. This model will help the student to yield the greatest chance of employment when applying for PSE programs, which is ultimately the highest order goal of international students. Additionally, this system will also offer PSE institutions valuable insights to scale and adjust their program offering to better solving labour market skills shortages.

The main tasks to be performed by the candidate should include 1) research literature review; 2) collect and cleansing data to be obtained from schools regarding anticipated success level for multi-factor analysis; 3) collect and cleansing labour market information from various sources; 4) develop possible Machine Learning (ML) implementations or algorithm design to allow for the different stages of prediction; 5) integrate multiple ML systems into a single ecosystem; 6) test the product against real-life data to establish success; 7) establish secure connection to student information (from ApplyBoard platform) such that students can choose school based on their success chances.

The standard data science methodology should be applied throughout the course of this research project. The proper machine learning method/technique is to be determined and experimented based on the literature review and the data collected. Agile software development methodology also applies with possible integration with the ApplyBoard software platform. 

Required expertise/skills: 

A preferred candidate should have extensive experience and knowledge in data science, computer science, mathematics, statistical analysis, as well as some knowledge in economics.