AI for Student-Major Fit: Placing the Right Student in the Right Field


“If I were to do it all over again, I would select another major”. “My dream job needs another major, but this is what may parents want me to do”. “My friends chose this field of study, and they convinced me to follow suit”…!!! According to BestColleges Survey (2020), “[If] schools help students align their majors with their ideal career paths — rather than just emphasizing graduating on time — it could improve overall satisfaction in the major.” Accordingly, helping students choose the right major can contribute to a delightful learning experience, graduates with the needed knowledge, skills, motivation for life-long learning, and passion to excel in the job. If employability as a university KPI means empowering students with the skills and knowledge needed in demanded jobs, then success in the job requires additional critical factors:  commitment and passion!


This project intends to design an innovative means to help students choose the right major; bridge the gap between required skills and provided ones; and achieve a higher level of satisfaction with the major.

Using AI, and a system of neural networking and a data warehouse, along with learning and skills analytics, system training will be initiated so as to analyze the major choice by students in comparison to abilities, values, interests, passion, economic considerations, and employability of the major graduates. Data collected will include information from surveys distributed to alumni, Master students, present undergraduate students, and high school students. Machine learning and data analytics will be deployed to relate major choice, major transfer, and satisfaction to personal, economic., major characteristics, motivation, abilities, career interests,…. and so on. The system learning will help predict with a certain level of accuracy the success and matching level of the student to the major and expected career success.


  1. Develop a repository of main attributes associated to various (entry) career profiles:
    1. Involve experts from corporate HR, career guidance officers, professional syndicates, and psychology to define the factors of importance and frame dataset scope.
    2. Data collection from employers and company records
  2. Develop a repository of main attributes associated to students (student profiling):
    1. Involve experts from education, academic guidance officers, academic programs’ representatives, and psychology to define the factors of importance and frame dataset scope.
    2. Data collection from schools and universities
  3. Develop a neural network system and train the system using machine learning techniques until a high level of classification and prediction accuracy is achieved.


Enhance learners’ academic performance and commitment to future career objectives and enhance alignment between students capabilities/skills and career requirements.

Desired Disciplines

Team Leader

Dr. Manal Yunis

Team Co-leaders

Dr. Wael Nuweihed

Industry Partners

LAU and CIATEK (Tentatively)