IOI 01010 101010 010101 10101 010 SIH. AI-based drop-out prediction and counseling system. 

Scene 1

IOI
01010
101010
010101
10101
010
SIH

AI-based drop-out prediction and counseling system

Problem Statement ID –25102 Problem Statement Title-AI-based drop-out prediction and counseling system Theme-Smart Automation PS Category- Software Team ID- Team Name (Registered on portal)-DROP GUARD AI

AI-based drop-out prediction and counseling system. 

Scene 2

Proposed Solution Uses AI/ML models trained on academic, attendance, financial, and  psychometric test of behavioral data to predict dropout risk. Generates risk scores with explainable factors (e.g., GPA decline, absenteeism, fee overdue). Uses chat bot to  simulate human conversation using text or voice Integrates a counseling workflow (notifications, 1:1 sessions, referrals, progress tracking).

Addresses the Problem Early identification of at-risk students → proactive support before dropout occurs. Personalized interventions based on top risk drivers (academic, financial, social, health). Optimizes counselor resources by prioritizing high-risk cases. Data-driven decision-making improves institutional retention rates.

Innovation & Uniqueness Hybrid AI approach: combines predictive modeling with survival analysis to forecast when dropout risk rises. Closed-loop counseling system: prediction → intervention → feedback → retraining. Scalable & adaptable: works across programs, institutions, and different student populations.

TECHNICAL APPROACH. 3. @SIH Idea submission- Template. 

Scene 3

Student Data Collection

 Academic, Attendance, Financial, Behavioral, Psychometric

 Data Processing & Feature Engineering

 Cleaning, Normalization, Feature Extraction.

 AI/ML Prediction Engine

 Risk Dashboard & Alerts

 Counseling Workflow

 Feedback & Model Retraining

 Logistic Regression, XGBoost, Survival Analysis

 Interfaces for Admins, Counselors, Students

 Counseling sessions, Follow-ups

 Continuous improvement using new data

FEASIBILITY AND VIABILITY. 4. @SIH Idea submission- Template. 

Scene 4

Ensure strict data governance & compliance . Integrate with digital counselling platforms & recruit peer mentors

IMPACT AND BENEFITS. Impacts Reduced Drop-out Rates Personalized Support Enhanced Student Outcomes. 

Scene 5

Impacts Reduced Drop-out Rates Personalized Support Enhanced Student Outcomes

Benefits Social: Reduce inequality, stronger Communities, Better mental health. Economic: Lower public costs Scientific: Improves AI models, Data-driven insights Environmental: Digital efficiency

RESEARCH AND REFERENCES. 6. @SIH Idea submission- Template. 

Scene 6

Method Focus Limitations Proposed Solution Advantage Attendance & Marks Monitoring Academic only Misses personal, financial &  behavioral issues Holistic (academic + non-academic factors) Generic Counseling Manual sessions Reactive, not predictive AI-driven early alerts, proactive support Financial Aid Fee support Doesn’t address emotional/ academic causes Integrated counseling + academic support Proposed  AI System Multi-dimensional (AI/ML) New deployment challenges Personalized, predictive & adaptive

Predicting Student Dropout Risk With A Dual-Modal Abrupt Behavioral Changes Approach” — Jiabei Cheng, Zhen-Qun Yang, Jiannong Cao, Yu Yang, Xinzhe Zheng (arXiv, May 2025).  “AI-based identification and support of at-risk students: A case study of the Moroccan education system” — Elbouknify, Berrada, Mekouar, et al. (2025).  “Deep Learning for School Dropout Detection: A Comparison of Tabular and Graph-Based Models for Predicting At-Risk Students” — Pablo G. Almeida et al. (arXiv, August 2025).  “A model for predicting dropout of higher education students” — ScienceDirect, March 2025.

SMART INDIA HACKATHON 2025

Scene 1 (0s)

Scene 2 (18s)

Scene 3 (1m 3s)

Scene 4 (1m 22s)

Scene 5 (1m 32s)

Scene 6 (1m 47s)