Search research articles

Related Concept Videos

Multiple Regression

Multiple Regression

Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same journal

From pixels to length: Body length estimation of aquatic macroinvertebrates from digital images for ecological applications.

MethodsX·2026

Same journal

Sorbent-coated metal discs for time-integrated VOC sampling: A reproducible workflow coupled to SPME-GC/MS.

MethodsX·2026

Same journal

Step-by-step <i>En face</i> O red oil method for aortic plaque staining and quantification in ApoE knockout mouse.

MethodsX·2026

Same journal

Optimized protocols for culturing and sectioning mouse intestinal organoids: enhancing efficiency and structural integrity.

MethodsX·2026

Same journal

MCLF: Montage consistent CNN-Liquid fusion for long-term scalp EEG seizure detection.

MethodsX·2026

Same journal

Facile synthesis of model polystyrene nanoparticles for nanoplastics research.

MethodsX·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 10, 2026

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Published on: June 16, 2018

A multi-factor machine learning framework for predicting and profiling student academic performance using behavioral,

A L Akash Devaraje Urs¹, Akshay Sudharshan¹

¹Amrita Vishwa Vidyapeetham Mysuru, India.

|November 26, 2025

Summary

This summary is machine-generated.

This study uses machine learning to predict student academic performance by analyzing lifestyle, financial, and wearable data. It identifies at-risk students and creates profiles for early intervention in higher education.

Keywords:

CGPA prediction Machine learning in higher education Student academic performance prediction Wearable technology in learning analytics

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jan 10, 2026

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Published on: June 16, 2018

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Area of Science:

Educational Data Mining
Machine Learning in Education
Student Performance Analytics

Background:

Academic success is influenced by multifaceted factors beyond traditional metrics.
Integrating diverse data sources offers a holistic view of student well-being and performance.
Existing predictive models often lack comprehensive data integration.

Purpose of the Study:

To develop and validate a machine learning framework for predicting student academic performance (CGPA).
To profile students into distinct academic and stress-risk categories using behavioral, financial, and wearable data.
To establish an interpretable and reusable predictive analytics pipeline for educational institutions.

Main Methods:

Data preprocessing and feature engineering, including creation of Financial Stress and composite stress indices.
Benchmarking multiple regression models (Random Forest achieving R² ≈ 0.30) to predict CGPA.
Employing unsupervised clustering (K-Means, Agglomerative) for student segmentation and analyzing wearable data correlations.

Main Results:

Random Forest model demonstrated the highest accuracy in predicting CGPA.
Identified significant relationships between lifestyle, financial, and physiological data and academic outcomes.
Successfully segmented students into interpretable academic and stress-risk profiles.

Conclusions:

The proposed multi-factor machine learning framework effectively predicts student academic performance.
Student profiling aids in the early detection of at-risk individuals for timely support.
The adaptable blueprint supports educational institutions in implementing advanced predictive analytics.