This report provides a comprehensive analysis of learner performance and program completion outcomes across ALX Nigeria programs, focusing primarily on the AI Career Essentials (AICE) track. The insights are derived from a cleaned hypothetical dataset of 5,002 learners, excluding those who deferred
Executive Summary
With an overall graduation rate of 38%, this analysis reveals key performance patterns and learner behaviours in the AICE program. Among the findings:
The Data Science track had the highest graduation rate at 40%, followed by AICE at 39.8% and Cloud Computing at 36%.
Resubmission of assignments and consistent LMS usage are strong indicators of graduation.
Data Overview
The dataset analyzed in this project was sourced from the ALX Nigeria Learning Comunity Experience Intern role application, specifically focused on understanding program completion, performance, and graduation outcomes. It includes learner-level data across multiple variables that help track engagement and success across various learning tracks.
Dataset Overview
- Total Records (Learners): 5,002 learners
Key Columns:
"program" The specific program the learner enrolled in (e.g., Data Science, AI Career Essentials, etc.)
"assignment_type" The specific type of assignment the learner submitted (e.g., Milestone or Test)
"Is_assignment_resubmitted" A binary flag indicating whether the learner resubmitted an assignment.
"Learner_dropped_off" A binary flag indicating whether the learner was dropped off based on learning criteria.
"overall_score" A numeric value representing the learner’s total performance across assessments.
"graduated" A binary flag showing whether the learner completed the program.
Additional features: learner demographics (age group, gender, state), learning track, attendance indicators, etc.
Data Cleaning and Preparation
To ensure the data was analysis-ready, the following steps were taken:
Deferred learners were excluded from the analysis as they are not considered for this cohort’s analysis.
Three columns ("Dropped Off", "Overall Score", "Graduated") were derived using definitions provided in the dataset description.
New metrics such as completion rates and performance distributions were calculated.
This cleaned dataset was then used to explore trends in learner performance and dropout patterns within the AI Career Essentials program.
Key Findings
1. Overall Performance
The ALX program achieved a 38% graduation rate among the 5,002 learners in this dataset. While this indicates that nearly 2 in 5 learners successfully complete their programs, the 62% attrition rate represents a significant opportunity for improvement.
Graduation status
Program completion status: 38% of learners graduated, while 62% did not, revealing a considerable attrition rate that needs addressing.
However, this varies significantly by program type, with the Data Science program having the highest completion rate at 40% while the Cloud Computing program has the lowest at 36%.
Graduation rate distribution across programs
The AI Career Essentials program, with 354 total learners, graduated 141 students (39.8%), slightly above the overall average.
Graduation rate across the AICE program
Key Performance Indicators show :
49.2% of learners completed the required milestones 1-3
9.3% of learners did not meet graduation requirements despite completing milestones.
2. Learner Engagement and Platform Usage(AICE)
LMS Engagement Patterns:
96.61% of learners actively logged into the Learning Management System
Non-LMS users had only a 0.0% graduation rate, highlighting the critical importance of platform engagement
LMS engagement patterns
Assignment Resubmission Behaviour:
Learners resubmitted 48% of all assignments
Learners who resubmitted assignments had an 82.46% graduation rate vs 66% for those who didn’t
This suggests that learners who engage with feedback and iterate on their work are more likely to succeed
Press enter or click to view image in full size
3. Performance and Scoring Insights(AICE)
Overall Score Distribution:
Average overall score across all learners: 40.29%
Graduated learners maintained an average score of 87.3%
Non-graduated learners averaged 9.1%
A clear performance threshold exists around the 75% requirement for graduation
Overall score distribution across the AICE program
4. Demographic and Geographic Patterns(AICE)
Gender Distribution:
Female learners: 35% of total enrollment, 40% graduation rate
Male learners: 64.7% of total enrollment, 37% graduation rate
unknown learners: 0.3% of total enrollment, 0% graduation rate
Minimal gender gap in performance outcomes
Gender distribution across learners
Age Group Performance:
18-24 age group: 22% of learners, 38.4% graduation rate
25–29 age group: 41.8% of learners, 38.5% graduation rate
30–34 age group: 28.5% of learners, 37.6% graduation rate
35+ age group: 7% of learners, 59.25% graduation rate
Late-career learners (35+) show the highest success rates despite lower enrollment
Age group performance
Late-career learners (35+) showed the highest graduation rate at 59.25%, despite not being the largest enrolled group. Younger learners (25–29) made up nearly half of enrollment but had lower graduation success.”
Geographic Distribution:
Lagos State: Highest enrollment (28%) with 45% graduation rate
Sokoto: Highest graduation rate(50%) with 3% enrollment rate
Abuja: 9% enrollment with 45.7% graduation rate
Rivers State: 13% enrollment with 38.29% graduation rate
Urban centres show slightly higher completion rates
Press enter or click to view image in full size
Enrollment by state
5. Risk Factors and Early Warning Indicators
Critical Risk Factors Identified:
Assignment resubmission: Strongest predictor of completion(83% completion rate)
No resubmissions: Learners who never resubmit work show 42.6% lower completion rates
Program selection: Cloud Computing consistently shows lower performance across metrics
Learner Journey Analysis:
Most successful learners follow a pattern:
Consistent LMS login → milestone completion → assignment resubmission when needed → gradual score improvement
At-risk learners can be identified as early as the first month based on engagement patterns
Visualizations Summary
Key charts and graphs created for this analysis include:
Graduation rates by program (bar chart)LMS engagement vs graduation correlation (grouped bar chart)
Assignment resubmission behaviour(horizontal stacked bar chart)
Overall score distribution by graduation status (density plot)
Gender distribution(donut chart)
Geographic performance (horizontal grouped bar chart)
Recommendations
1. Immediate Actions (0-3 months)
Boost LMS Engagement:
Implement mandatory weekly LMS check-ins.
Create a mobile-friendly platform to increase login frequency.
Send automated reminders for learners who haven’t logged in within 48 hours.
Early Warning System:
Deploy predictive analytics to identify at-risk learners within the first 2 weeks
Flag learners with low first-milestone scores or minimal LMS engagement for immediate intervention
2. Medium-term Improvements (3-6 months)
Program-Specific Interventions:
Redesign the Cloud Computing curriculum with additional foundational modules
Implement a peer mentoring system connecting high-performing Data Science learners with struggling Cloud Computing students
Create program-specific study groups and office hours
Enhanced Feedback Loop:Encourage resubmissions through structured feedback and revision processes
Implement automated feedback systems for common assignment issues
Provide clear rubrics and examples for each milestone
3. Long-term Strategic Changes (6-12 months)
Comprehensive Support Systems:
Develop state-specific support networks, particularly for lower-performing regions
Create age-group-specific learning cohorts and mentorship programs
Implement career counselling to help learners choose programs aligned with their strengths
Performance Optimization:
Raise the overall graduation rate target from 38% to 55% within 12 months
Establish program-specific performance benchmarks
Regular curriculum reviews based on learner feedback and performance data
4. Measurement and Monitoring
Key Performance Indicators to Track:
Monthly LMS engagement rates
First-milestone performance as a graduation predictor
Program-specific completion rate improvements
Geographic performance trends
Resubmission rates and their impact on final outcomes
Conclusion
The ALX Nigeria program shows strong foundational elements, with significant opportunities for improvement. The 38% graduation rate offers a clear starting point for enhancement. The strong correlation between assignment resubmission and graduation presents an actionable area for intervention, while performance disparities between programs suggest areas for curriculum improvement.
The data reveals that learner success is driven more by behavioural factors (platform usage, resubmission, consistent participation) than by demographic variables, making success more predictable and scalable. By prioritizing LMS engagement, early risk detection, and program-specific interventions, ALX can realistically target a 15–20 percentage point increase in graduation rates in the next academic cycle
Top comments (1)
This is a solid breakdown. The resubmission signal stands out a lot.
I’ve been seeing a similar pattern while running stress tests on a system, where early signals show up well before actual failure, but most people ignore them.
Interesting how in your case LMS engagement and resubmission act as those early indicators. Curious, how early can you reliably detect at-risk learners from these signals?
Feels like most systems give signals early, but we just don’t pay attention to them.