Analytics Guide

Track student performance, identify trends, and make data-informed decisions

Published

July 19, 2026

Overview

Kai’s analytics provide insights into student learning, engagement patterns, and class-wide trends directly within the app. These tools help you understand what’s working and where students need support—without needing to export data or write queries.

Why Analytics Matter

Benefits for Instructors: - Identify struggling students early - Track learning progress over time - Measure intervention effectiveness - Optimize teaching strategies with data - Allocate support resources efficiently

Benefits for Students: - Visualize their own progress - Understand strengths and weaknesses - Track improvement over time - Stay motivated with tangible metrics

Accessing Analytics

Navigate to the Analytics section from the instructor dashboard. You can view analytics at the individual student level, class level, or across a date range.

TipStart with the Overview

Begin with the Course Overview to get a high-level picture before diving into individual student data.

Student Performance Analytics

Individual Student Dashboards

For each enrolled student, Kai tracks:

  • Current grade and trend: Whether performance is improving, stable, or declining
  • Assessment breakdown: Separate averages for quizzes, assignments, and participation
  • Topic mastery: Which concepts a student has mastered, is developing, or needs support with
  • Engagement metrics: Participation rate and resource usage

Dashboard Visualization:

STUDENT PERFORMANCE DASHBOARD: Jane Smith
Course: Statistics 101 | Period: Fall 2024

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OVERALL PERFORMANCE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Current Grade: 87.5% (B+)        Trend: ↗ Improving (+2.3 pts this month)
Predicted Final: 88.5%           Risk Level: ● Low

Grade History:
Week 1-4:   ████████░░ 80.2%
Week 5-8:   █████████░ 85.1%
Week 9-12:  █████████░ 87.5%

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
ASSESSMENT BREAKDOWN
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Quizzes:        85.2% (12 completed) ━━━━━━━━━━━━━━━━━░░░░
Assignments:    88.3% (8 completed)  ━━━━━━━━━━━━━━━━━░░░░
Exams:          82.0% (2 completed)  ━━━━━━━━━━━━━━━━━░░░░
Participation:  92.0%                ━━━━━━━━━━━━━━━━━━░░

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
TOPIC MASTERY
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

✓ Descriptive Statistics      ██████████████████ 92% Mastered
○ Inferential Statistics      ██████████████░░░░ 78% Proficient
◇ Regression Analysis         ███████░░░░░░░░░░░ 55% Developing ⚠
  Hypothesis Testing          ████████████░░░░░░ 68% Proficient

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
ENGAGEMENT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Participation Rate:    88%     ████████████████░░░░
Time on Platform:      32.5h   ████████████████░░░░
Resource Usage:        High    ██████████████████░░
Help Seeking:          3.2/wk  ███████████████░░░░░

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
INSIGHTS & RECOMMENDATIONS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Strengths:
• Strong calculation accuracy
• Excellent participation and engagement
• Consistent upward trajectory

Areas for Growth:
⚠ Regression analysis needs attention (55% mastery)
→ Recommended: Review Module 6, Practice Set 3
→ Suggested: Office hours this week

• Interpretation skills developing
→ Focus on connecting calculations to context

Class-Level Performance Analytics

Aggregate metrics for the entire class section show:

  • Class average and distribution: Grade spread across A/B/C/D/F bands
  • Assessment type averages: How the class performs on quizzes, assignments, and exams
  • At-risk students: Students whose performance or engagement signals they need support
  • Topic difficulty profile: Which concepts the class struggles with most

Class Overview Example:

COHORT COMPARISON REPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

                    Section 001    Section 002    Difference
Average Grade       82.3%          79.8%          +2.5%
Median Grade        84.0%          81.5%          +2.5%
Std Dev             8.5            11.2           -2.7 (more consistent)

Completion Rate     89%            84%            +5%
Participation Rate  85%            78%            +7%

Topic Mastery:
- Descriptive       87%            82%            +5%
- Inferential       75%            71%            +4%
- Regression        68%            65%            +3%

At-Risk Students    2 (6%)         5 (16%)        -10%
High Achievers      8 (25%)        6 (19%)        +6%

Learning Trend Analysis

Progress Over Time

Kai tracks how students develop throughout the course:

  • Grade trajectory: Weekly averages showing whether the class is improving overall
  • Mastery progression: How quickly concepts are mastered on average
  • Engagement trends: Whether participation is steady, rising, or declining—with suggested intervention points

Student Trajectory Types

Kai groups students into trajectory patterns to help you focus your attention:

Pattern Description
Steady improvers Consistent upward trajectory throughout the semester
Quick starters Strong early performance that holds
Late bloomers Struggle early but improve significantly
Concerning patterns Declining performance that needs intervention

Predictive Analytics

Kai’s early warning system identifies students who may need support before they fall behind. It considers factors such as:

  • Declining quiz scores over multiple attempts
  • Reduced engagement or participation below normal
  • Missed assignments
  • Low resource usage
  • Absence of help-seeking behavior

When a student is flagged as high or medium risk, Kai suggests appropriate actions—from a check-in email to immediate outreach.

ImportantPredictions Inform, Not Decide

Use predictive analytics as one signal among many. Always apply your own professional judgment and knowledge of the student before acting on any risk flag.

Engagement Metrics

Participation Analytics

Track how students interact with course materials and activities:

  • Active users: Daily, weekly, and monthly counts
  • Session duration and frequency: How often and how long students engage
  • Peak usage times: When your class tends to study, useful for scheduling
  • Activity breakdown: Completion rates for quizzes, assignments, and resources

Engagement Segments

Kai groups students into engagement tiers to make it easy to identify who needs attention:

Segment Characteristics
Highly engaged 95%+ participation, comprehensive resource use, avg grade ~90%
Moderately engaged 85% participation, selective resource use, avg grade ~82%
Low engagement Below 60% participation, minimal resource use, avg grade ~71% — needs attention

Participation vs. Performance Correlation

Kai surfaces the relationship between engagement and grades for your class, helping you demonstrate to students that showing up—literally and digitally—correlates with better outcomes.

Resource Usage Analytics

Understand which course materials students find most valuable:

  • Which videos are rewatched most (and at which timestamps)
  • Which readings are opened and for how long
  • Which practice problems are attempted most
  • Which supplementary materials are accessed

This helps you identify what’s working and what might be replaced.

Student-Facing Analytics

Students can view their own progress dashboard in the Kai Student app. This shows:

  • Current grade and trend compared to their personal goal
  • Topic mastery levels with recommended focus areas
  • Participation rate and resource usage
  • Personalized next steps

Student data is never compared to peers publicly—all views are individual and growth-focused.

Student View Example:

Your Progress Dashboard
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Current Grade: 87.5% (B+)
Trend: ↗ Up 2.3 points this month - Great progress!

Your Goals:
• Target for course: 90% (A-)
• Gap to close: 2.5 points
• On track: Yes ✓
• Estimated weeks to goal: 3 weeks at current pace

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
What You've Mastered
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

✓ Descriptive Statistics       92% Excellent!
✓ Data Visualization           88% Strong
○ Inferential Statistics       78% Good - keep practicing
◇ Regression Analysis          55% Developing - focus here

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Recommended Next Steps
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

1. Focus on Regression Analysis (55% mastery)
   → Review Module 6: Linear Regression
   → Complete Practice Set 3 (15 problems)
   → Estimated time: 45 minutes

2. Strengthen Interpretation Skills
   → Watch: "Connecting Calculations to Context" (8 min)
   → Try: Interpretation Quiz (10 questions)

Privacy and Data Handling

ImportantPrivacy First

All analytics features comply with FERPA, GDPR, and institutional privacy policies. Student data is never shared without proper consent.

Key privacy principles:

  • Student performance data is visible only to that student and their instructor
  • Aggregated data does not identify individuals
  • Students can request data deletion
  • All data is encrypted in transit and at rest
  • Students can opt out without academic penalty

Best Practices

Effective Analytics Use

TipStart with Questions

Begin with specific questions you want to answer, then find the relevant analytics. Avoid drowning in data without clear purpose.

Recommended Workflow:

  1. Identify Questions:
    • “Which students are struggling?”
    • “Which topics are most challenging?”
    • “Is engagement declining over time?”
    • “Are interventions working?”
  2. Select Relevant Metrics:
    • Match analytics to questions
    • Focus on actionable insights
    • Avoid vanity metrics
  3. Set Regular Review Times:
    • Weekly: At-risk student check
    • Biweekly: Topic difficulty review
    • Monthly: Overall trend analysis
    • End-of-semester: Comprehensive evaluation
  4. Act on Insights:
    • Don’t just observe — intervene
    • Document what works
    • Adjust strategies based on data
    • Close the feedback loop

Interpreting Analytics Wisely

  • ✅ Context Matters: Consider external factors (holidays, exam weeks, etc.)
  • ✅ Trends Over Snapshots: Look for patterns, not single data points
  • ✅ Combine Quantitative and Qualitative: Numbers + student feedback
  • ✅ Respect Privacy: Never publicly compare students
  • ❌ Avoid: Over-relying on predictions without human judgment
  • ❌ Avoid: Labeling students based on early data
  • ❌ Avoid: Using analytics punitively

Data-Informed, Not Data-Driven

Analytics inform decisions but don’t replace professional judgment. When Kai flags a student as at-risk, the right response is to reach out with support—not to reduce expectations or give up. Use data as one input alongside your direct knowledge of the student.

Troubleshooting

Missing Data

Problem: Analytics showing incomplete or missing data

Common Causes: - Recent course setup (insufficient data collected yet) - Student privacy settings blocking data collection - Students not engaging with the platform

Solutions: - Allow 2-3 weeks of activity before drawing conclusions from analytics - Check that students are enrolled and actively using the app - Verify that the course has received feedback or quiz responses

Inaccurate Predictions

Problem: Predictive analytics not matching reality

Solutions: - Allow 3-4 weeks for the model to calibrate - Ensure sufficient student activity data exists - Treat predictions as one signal—combine with direct observation

Overwhelming Amount of Data

Problem: Too many metrics to track effectively

Solution: Focus on the two or three metrics most relevant to your current teaching question. The at-risk student list and the topic mastery summary are the most actionable starting points for most instructors.

Support Resources

Next Steps: - Set up personalization features informed by analytics - Review best practices for data-informed teaching