Sign In Sign Up
Western Leyte College of Ormoc

SMART-CARE
Intelligent Analytics
for Student Success

An Intelligent Analytics System for Identifying College Students at Risk of Academic Attrition Using Machine Learning

Academic attrition remains a persistent challenge in higher education. SMART-CARE leverages machine learning to detect early warning signs of dropout risk — enabling administrators, counselors, and faculty advisors at Western Leyte College of Ormoc to intervene at exactly the right moment.

Attrition Prediction Risk Classification ML-Powered Data Privacy Act Compliant Early Warning Alerts WLC Institutional System
94% Prediction Accuracy
Earlier Intervention
4 Risk Level Categories
12+ Attrition Risk Factors
About the system

SMART-CARE

Academic attrition remains a major challenge in higher education, largely due to the absence of effective systems for the early identification of at-risk college students. SMART-CARE was developed to address this gap.

By applying machine learning to institutional data, SMART-CARE provides administrators, counselors, and faculty advisers with actionable insights through risk classification, dashboards, and early warning alerts.

The system assists — but does not replace — human professional judgment. All student data is processed in compliance with RA 10173 (Data Privacy Act of 2012) and RA 8792 (Electronic Commerce Act of 2000).

Core System Features

Institutional tooling for proactive student success at Western Leyte College of Ormoc

Early Risk Prediction

ML models predict attrition likelihood from academic performance, attendance, and behavioral data.

Student Risk Profiling Dashboard

Visual insights into individual and cohort risk levels for counselors and faculty advisers.

Automated Alerts and Notifications

At-risk students are flagged automatically so stakeholders can act before problems escalate.

Data Integration and Analytics

Academic, attendance, and engagement data unified for institutional reporting and analysis.

Decision Support for Interventions

Advisors receive guidance on selecting the right support actions for each student profile.

Full Audit Trail

Every system action is logged automatically for accountability and compliance review.

How SMART-CARE Works

From institutional data to actionable intervention support

1.Data Collection

Academic records, attendance, and demographic data from WLC systems.

2.Preprocessing

Clean, transform, and organize data for machine learning pipelines.

3.ML Development

Train and validate attrition prediction models on historical cohorts.

4.Risk Classification

Assign Low, Medium, High, or Critical risk levels per student.

5.Dashboards & Alerts

Role-based dashboards and automated early warning notifications.

6.Evaluation

Measure accuracy, usability, and intervention outcomes each term.

7.Decision Support

Deliver actionable insights for timely counselor and faculty intervention.

Who Uses SMART-CARE

Role-based access for every stakeholder in the student success ecosystem

Students

View risk insights, academic standing, and wellness resources.

Faculty / Instructors

Monitor class rosters, at-risk learners, and submit intervention reports.

Counselors & Deans

Cohort analytics, alerts, and decision support for institutional action.

Administrators

User maintenance, subjects, audit logs, and system configuration.

Legal Basis

Built for compliance with Philippine data protection and e-commerce law

RA 10173 — Data Privacy Act of 2012

SMART-CARE incorporates controlled access, data confidentiality, and secure storage so personal and academic information is handled responsibly.

RA 8792 — Electronic Commerce Act of 2000

Digital reports, notifications, and analytics outputs align with lawful electronic records and transactions in educational institutions.