Logo
IDARE Enterprise AI predictive analytics platform background
Use Case

Predicting Dropout and Success Rates of Students

Improving retention strategies in educational institutions by predicting student performance.

1Overview & Strategic Importance

Predicting Dropout and Success Rates of Students
Classification Solution Student Data

Problem Statement

Institutions of higher education face a critical challenge in identifying and supporting students at risk of dropping out. Dropouts result in unfulfilled academic potential and wasted resources and impact the reputation and operational efficiency of the institution. Early intervention is key, but it requires actionable insights derived from data. To support students effectively, institutions must focus on key indicators such as financial status (e.g., 'Tuition fees up to date') and academic performance (e.g., 'Curricular units approved'). These factors can provide an early warning system, enabling proactive measures to improve retention and foster success.

Required Solutions

  • Identify students at risk of dropping out early enough for intervention.
  • Enable support strategies such as financial counseling, tutoring, and mentorship.
  • Offer scenario analysis to help institutions assess the impact of interventions and refine support systems.

Solution Objectives

  • Conduct exploratory data analysis to identify key predictors.
  • Build a predictive model to forecast student outcomes.
  • Create an AI application to facilitate scenario-based analysis and targeted interventions.

Understanding the Problem

Student dropout is a significant concern in higher education. Research indicates that factors such as financial difficulties and academic challenges play a major role. For example, students who keep tuition fees up-to-date and maintain strong academic progress (as indicated by approved curricular units) are more likely to succeed. An AI-powered system can simulate different interventions, such as increasing financial support or adjusting academic workloads, to predict their impact on student retention. This enables institutions to act decisively and support students before dropout becomes inevitable.

2About the Data

Data Collection

This dataset provides a comprehensive view of students enrolled in various undergraduate degrees offered at a higher education institution. It includes demographic data, social-economic factors and academic performance information that can be used to analyze the possible predictors of student dropout and academic success.

Dataset Source

Major Parameters Description

Download Training Data
Marital status

The marital status of the student. (Categorical)

Application mode

The method of application used by the student. (Categorical)

Application order

The order in which the student applied. (Numerical)

Course

The course taken by the student. (Categorical)

Daytime/evening attendance

Whether the student attends classes during the day or in the evening. (Categorical)

Previous qualification

The qualification obtained by the student before enrolling in higher education. (Categorical)

Nationality

The nationality of the student. (Categorical)

Mother's qualification

The qualification of the student's mother. (Categorical)

Father's qualification

The qualification of the student's father. (Categorical)

3Using iDareAI

Guided Mode Initialization

AUploading Dataset

Click on the **'Upload CSV or Excel Data'** button → Select a source for the dataset → Upload `student_dropout_train.csv`. The system automatically analyzes the file, extracts column descriptions, and identifies the top value-adding targets for prediction.

Upload UI

BChoosing Analysis Mode

Choose between autonomous machine learning or manual building. In autonomous mode, simply ask a question like:
  • How can institutions act in time to support students who are at risk of dropping out?
  • What factors have the strongest influence on whether a student graduates or drops out?

Operation Using Autonomous Guided Mode

AQuery Response

To support students at risk of dropping out, institutions can leverage predictive analytics derived from the trained machine learning models. By identifying key factors such as 'Curricular units 2nd sem (approved)' and 'Tuition fees up to date', institutions can proactively engage with at-risk students.

Auto Analysis

BAI Application

Running the query generates an on-demand AI application. Users can adjust sliders to test different scenarios and see real-time updates to predictions without technical knowledge.

Auto Application

Model Fine-Tuning/Manual Model Building

ASelecting Prediction Target

Analyzing the automated response to the query generated from the problem statement, the 'Target' column was selected as the target.

Target Selection

BSelecting Analysis Type

The analysis target is a categorical column with three values, 'Dropout', 'Enrolled', and 'Graduate'. Hence, the 'Classification' analysis type is selected.

Analysis Type

CSelecting Model Group/Item

No item/group is required for this dataset.

Model Group

DSelecting Features

Select the following features: Course, Father's occupation, Admission grade, Tuition fees up to date, Age at enrollment, Curricular units (1st & 2nd sem), GDP, Inflation rate, and Debtor.

Feature Selection

ESelecting Training Level

The training process uses advanced algorithms, including Xtreme Gradient Boosting, and Decision Tree. It applies 5-fold cross-validation with 80% of the data for training and 20% for testing on unseen data, ensuring robust and reliable student dropout predictions.

Training Level

AI Modeling Details

The analysis highlights that while the Xtreme Gradient Boosting model achieves the best performance with relatively low error rates, there is still room for improvement through refined feature selection and model optimization.

Modeling Details

Training Analysis Details

APredicted Target

Predicted Target

BROC AUC

ROC AUC

CError Trend

Error Trend

DFeature Importance

Feature Importance

Finalize Models

Once satisfied with performance, click 'Deploy'. The system saves and deploys models for future demand analysis or production environment.

Finalize Models

4AI APPLICATION

Manual Model Building

In Manual Training Mode, users can modify sliders for variables like Admission Grade, Tuition Fees, and Age. Clicking ‘Get Response’ triggers an updated analysis.

Manual App

AI Application Demo

  1. The initial state shows 'Graduate' as the most likely outcome.
  2. Using the slider, adjust the 'Tuition fees up to date' feature.
  3. The predicted outcome changes to ‘Dropout,’ demonstrating the impact.

Saving the Project

Save your project by clicking the icon at the bottom left corner of the textbox.

Saving

Sharing the Project

Share the application for single on-demand predictions once the analysis is saved.

Sharing

Interested in similar AI solutions?

Explore our full suite of AI capabilities designed to transform your business operations.