Thoughts & Writing

Blog & Articles

Reflections on technology, teaching, AI, and the intersection of education and industry.

Featured Article Mar 2025

Predicting Student Depression Using Machine Learning

Dammar Khadayat & Prakash Poudel

Student depression has a measurable effect on academic performance, social life and wellbeing, yet conventional diagnosis is slow and subjective. This study tested whether it can be predicted from routine data instead.

The Problem

In Nepali higher education, student mental health remains an under-researched area. Many students experience academic pressure, sleep disruption, financial stress and social isolation — yet few seek formal support. Early detection could help institutions intervene before a crisis.

Methodology

Using a dataset of approximately 27,900 student records covering demographic, academic and lifestyle variables, we compared three classification models:

  • Logistic Regression — baseline binary classifier (accuracy: 0.75)
  • Random Forest — ensemble method (accuracy: 0.73)
  • Gradient Boosting — sequential ensemble (accuracy: 0.75)

Key Findings

All three models performed in a similar band around the mid-0.70s, but the feature analysis proved the more actionable result:

  • Academic pressure emerged as the single strongest predictor of depression
  • Sleep duration was the second most influential feature
  • Financial stress and family relationships contributed meaningfully but less strongly
The finding that academic pressure and sleep are the strongest predictors suggests that institutional interventions — workload management, sleep hygiene campaigns, flexible assessment — could have a measurable impact on student wellbeing.

Implications

These results suggest that routine institutional data can serve as an early-warning system. Rather than relying solely on self-reporting or clinical assessment, colleges could use predictive models to identify at-risk students and provide targeted support.

Limitations & Future Work

The dataset was cross-sectional, limiting causal inference. Future work will explore longitudinal models and the integration of real-time data from learning management systems. The fairness implications of predictive models in educational contexts also warrant further investigation.

Machine Learning Student Mental Health Predictive Modelling Educational Data Python scikit-learn

Model Performance

Logistic Regression0.75
Gradient Boosting0.75
Random Forest0.73

Sample Size

27,900

student records

Key Predictors

  • Academic pressure
  • Sleep duration
  • Financial stress
  • Family relationships

Published

March 2025 — ResearchGate

More Articles

Technology Feb 2024

Laravel Command Lists

A practical reference of essential Laravel artisan commands for routing, database migrations, queue management, caching and deployment.

Read Article
Education Feb 2024

Top Digital Marketing Courses in Nepal

A guide to the most effective digital marketing courses available in Nepal, covering curriculum quality, practical exposure, and career outcomes.

Read Article
Industry 2024

Web Development Workshop for IT Students

A recap of the comprehensive workshop covering front-end technologies, back-end PHP Laravel, version control, deployment and security best practices.

Read Article
Strategy Apr 2023

Social Media Marketing Strategy for Businesses

Insights on creating and managing impactful social media strategies that enhance brand visibility and engagement across platforms.

Read Article
Education Ongoing

AI in Nepali Classrooms: How Generative Tools Are Changing Learning

Reflections on how generative AI tools are reshaping the way undergraduates in Nepal learn to code, and the opportunities and risks.

Read Article