In the competitive landscape of higher education, simply looking at final grades doesn't tell the whole story of why some students succeed while others struggle. This project takes a closer look at how daily habits like study time, sleep patterns, and class attendance actually affect a student's performance and their direct impact on exam performance and cognitive stability.
I took a raw dataset and converted into an easy-to-use dashboard for university administration. Instead of just looking at averages, the goal was to find the exact moments where more effort stops helping and where things like lack of sleep start to seriously affect a student's focus and stability.
In order to improve student success rates and understand why some students perform better than others, the administration wants to know the following:
- Can extra study time actually make up for missing classes?
- At what point does sleep deprivation become a primary driver of academic failure?
- How does attendance impact the required study time?
- EDA (Data Preparation & Cleaning, Feature Engineering)
- Advanced Formulas
- Conditional Formatting
- Multi-Dimensional Pivot Tables
- Data Binning (Grouping)
- Pivot Charts (Combo Charts)
- Heatmaps
- Interactive Slicer Architecture
This project uses a student performance dataset that tracks behavioral habits alongside academic results to identify key success drivers. The raw data includes several spelling inconsistencies and structural issues that were addressed during the initial data cleaning phase.
- Student_id: A unique identification or roll number assigned to each individual student.
- Hours_Studied: The daily amount of time a student dedicated to reading, learning, or exam preparation.
- Sleep_Hours: The average number of hours a student rested per day during the study period.
- Attendance_Percentage: The total percentage of scheduled classes that the student attended.
- Previous_Scores: Academic marks received in earlier exams, representing the student's historical performance.
- Exam_Score: The final marks achieved in the current test.
I implemented a grid-based "Z-pattern" layout to ensure a logical flow of information for university stakeholders. High-level KPIs are positioned at the top for immediate status checks, followed by behavioral trend charts in the center, and deep-dive granular heatmaps at the bottom.
The dashboard features a cross-filtered architecture using interactive slicers. This allows users to drill down into specific student segments, with all charts and heatmaps updating in real-time to show the localized impact of sleep and attendance on scores.
Automated Student Profiling
Using advanced lookup logic, the dashboard automatically generates "High-Performer" and "At-Risk" profiles. These cards provide an instant snapshot of the behavioral thresholds, such as specific study and sleep hour combinations, that correlate with student success or failure.
To make the data easy to explore, I added interactive slicers for Attendance Percentage and Sleep Hours. These act like filters that let the user quickly "zoom in" on specific groups, for example, seeing how much sleep affects only the students who have perfect attendance. This functionality transforms a static report into a responsive analytical tool, allowing the university board to filter specific student segments and receive immediate visual feedback on performance trends.
This pivot chart shows that studying more hours guarantees a higher score. Both the final score and score retention increase with incremental study hours, though the number of students studying more hours gradually decreases.
Background Pivot Table
This pivot chart shows students having an average of 7+ hours of sleep a day achieve score retention of more than 50%. There is an exception for the 4-5-hour group. These students are likely “crammers” who traded sleep before exam for high-intensity study, giving them a temporary retention boost. But students sleeping 5-6 hours a day suffer from sleep deprivation and actually perform the worst.
Background Pivot Table
This pivot chart shows high attendance makes the study time more effective. Students do not have to study 7+ hours daily if they actually attend 90% of the lectures. The 70-80% attendance group also shows better performance because they have the highest average study hours (7.2). Therefore, students must increase study hours to compensate for their lower attendance.
Background Pivot Table
I created two main matrices to help spot trends that a simple list of numbers might miss:
-
Study vs. Sleep:
This shows the "sweet spot" for knowledge retention. It clearly highlights how even the hardest-working students start to lose their edge if they aren't getting enough rest.
-
Attendance vs. Study:
This helps visualize the balance between being in class and self-study. It reveals which students are successfully using extra study time to make up for missed lectures, and which ones are hitting a "burnout" point.
By using color scales, these heat maps clearly distinguish "danger zones" (low scores in red) from "success zones" (high scores in green). This high-contrast visualization ensures that critical insights are instantly accessible, enabling the university administration to make rapid, evidence-based decisions.
|
|
| Score Retention by Study & Sleep Hours | Final Score by Attendance & Study Hours |
- Maintain 7+ daily study hours to secure Score Retention above the 55% benchmark.
- Prioritize 6–7 hours of sleep to ensure cognitive stability and consistent performance outcomes.
- Target 90% attendance to retain higher scores even with moderate study hours.
- Students with low attendance must scale study hours accordingly to make up for the missed classes.
This study confirms that academic success is a balance of disciplined study habits, consistent attendance, and biological recovery. The data reveals that while high attendance acts as a performance multiplier, maintaining a minimum of seven study hours and six to seven hours of sleep daily is essential for peak cognitive retention. Ultimately, these insights provide a clear roadmap for students to optimize their efforts and for administrators to implement targeted, data-driven support strategies.