Student Performance Predictor

Your Name
October 2026

An Interactive Data Product

Course: Developing Data Products

This project demonstrates how R, regression modelling, and Shiny can be combined to build an interactive student performance estimation tool.

Why Build This Application?

The Problem

  • Students may want to explore how study habits relate to examination performance.
  • Static reports do not let users change assumptions and immediately see the resulting estimate.
  • An interactive application makes the analysis easier to explore.

The Proposed Solution

The Student Performance Predictor lets users adjust study hours, attendance, and previous exam scores to explore a model-based estimated score.

How the Application Works

Inputs and Outputs

User inputs

  • Study hours per day
  • Attendance percentage
  • Previous exam score

Server calculations

  • Fits a linear regression model to illustrative data.
  • Calculates an estimated score using the selected inputs.
  • Updates the result and plot reactively.

Application link

Replace this text with your deployed shinyapps.io URL.

Demonstration and R Results

Exploring the Data

The application uses illustrative data to demonstrate the relationship between study hours and exam scores.

summary(cars$speed)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    4.0    12.0    15.0    15.4    19.0    25.0

The following expression calculates the average speed in R's built-in cars dataset:

mean(cars$speed)

[1] 15.4

These evaluated expressions demonstrate how R code and its output can be embedded directly in a presentation.

Conclusion

Key Takeaways

  • Shiny provides interactive user inputs.
  • Server-side R calculations respond to those inputs.
  • Regression and visualisation help communicate results.
  • The model is educational and is not validated for real-world academic decisions.

Future Improvements

Use real student data with appropriate consent, evaluate prediction accuracy, and validate the model before using it for practical decisions.

Thank you