ICFAI researchers develop AI/ML tool for student learning insights

A faculty team from the Institute of Chartered Financial Analysts of India (ICFAI) has developed an AI/ML-based architecture to analyse learning outcomes at the student and question levels, with the aim of making Outcome-Based Education (OBE) more student-centric and useful for improving teaching and learning.

The research, titled “Exploring the Deployment of AI/ML Architecture for Granular Computation of Learning Outcomes in a Foundational Online MBA Course", was presented by Prasad R at the International Conference on Educational Technology and Online Learning (ICETOL 2026), held in Bremen, Germany, from August 17 to 20.

The project was jointly developed by Rakesh P., Sunitha U. L. and Prasad R. The conference received more than 500 research papers from 54 countries and had around 900 participants.

Also read ICFAI Law School Hyderabad hosts 11th NJ Yasaswy Memorial Moot Court, Parul Institute beats all

ICFAI AI/ML architecture tracks learning outcomes

According to the research team, conventional OBE systems largely focus on measuring outcome attainment for accreditation and institutional reporting. The new architecture instead seeks to use outcome data to identify gaps in learning and improve course design.

Prasad R said, “The key question is what the solution is designed for—whether it is primarily to meet accreditation needs or to improve the quality of learning design and experience. The latter includes the former, but is far more powerful because it empowers both the student and the teacher in creating pathways to outcomes."

The research was conducted across five MBA courses , with 70 students in each course. The study analysed 927 questions covering six question and assessment types, including formative and terminal assessments.

The system mapped course outcomes and Bloom's Taxonomy levels at the question level. It then calculated learning outcomes for individual students, questions, question types, evaluation types and the overall course.

OBE analysis identifies gaps in higher-order learning

The study found that attainment of the five course outcomes at the overall batch level ranged from 56% to 63%. Across the six Bloom's Taxonomy levels, attainment ranged from 43% to 62%.

The analysis also showed comparatively lower attainment at the “evaluating” and “creating” levels.

The researchers said such detailed data could help faculty identify gaps between intended learning outcomes and actual student achievement. It could also help them assess the effectiveness of teaching and assessment methods and redesign courses for future batches.

For students, the system could provide greater visibility into performance across question types and rubric elements. This could enable more targeted feedback and support self-directed learning.

AI used for different types of assessments

The architecture uses different AI and machine learning approaches depending on the assessment format. The research used GPT-based models for multiple-choice questions, a course-configured custom GPT for long-form descriptive answers, and a multi-call agentic pipeline for project evaluation.

The outputs were reviewed and validated by faculty members.

The researchers highlighted the potential of AI to reduce the time required for granular OBE analysis. According to the team, manually carrying out the process for one course can take around 152 hours, after the initial learning curve.

By automating much of the computation while retaining faculty involvement in design and validation, the architecture could make detailed learning outcome analysis more practical across a larger number of courses.

Also read India added 196 public universities in 15 years, but most barely functional; private ones outnumber them

ICFAI researchers propose institutional OBE ecosystem

The team said the architecture could eventually be used beyond individual courses. It is designed to retain greater institutional and contextual ownership of data and provide different levels of outcome information to students, faculty and academic leadership.

The researchers envisage an OBE system where outcome measurement becomes part of a continuous cycle of learning, feedback, course redesign and quality improvement, rather than being used mainly for accreditation and compliance reporting.

Disclaimer: This content was distributed by the ICFAI and has been published as part of Careers360’s marketing initiative.