Leveraging Data to Improve Educational User Experience

A few years ago, I worked with an online education platform facing challenges with student engagement. While they had a significant number of users enrolling in courses, they struggled with low participation rates in course discussions and activities, leading to a decline in course completion rates. The platform needed to identify the causes behind low engagement and implement strategies to encourage more active participation. Improving Student Engagement Using Data Analytics 1️⃣ Analyzing Engagement Data We began by analyzing user interaction data, focusing on metrics such as time spent on the platform, participation in discussions, video completion rates, and quiz scores. Using SQL, we aggregated the data to identify patterns and pinpoint where students were losing interest. SELECT student_id, course_id, AVG(time_spent) AS avg_time_spent, COUNT(discussion_post_id) AS posts_made, AVG(quiz_score) AS avg_quiz_score FROM student_activity GROUP BY student_id, course_id; 🔹 Insight: We identified that students who interacted with course discussions and quizzes had higher completion rates, while others dropped off quickly. 2️⃣ Building a Predictive Model We then created a predictive model to determine which students were at risk of disengaging based on their activity patterns. The model incorporated features such as time spent on the platform, participation in discussions, and progress through the course material. # Pseudocode for Predictive Model def predict_student_engagement(student_data): model = train_engagement_model(student_data) predictions = model.predict(student_data) return predictions 🔹 Insight: This model helped us flag students who were likely to disengage early, allowing for timely interventions. 3️⃣ Implementing Engagement Strategies Based on insights from the model, we implemented strategies such as sending personalized emails with reminders, offering incentives for completing activities, and increasing interaction opportunities through live Q&A sessions. # Pseudocode for Engagement Follow-Up def send_engagement_reminder(student_data): if model.predict(student_data) == 'at_risk': send_email_reminder(student_data) 🔹 Insight: Personalized engagement and incentives led to an increase in student participation. Challenges Faced Identifying meaningful engagement metrics that were predictive of success. Finding the right balance between engaging students without overwhelming them. Business Impact ✔ Student engagement improved, leading to higher completion rates. ✔ Retention rates increased, as more students continued with courses. ✔ Revenue grew, driven by more active and satisfied students. Key Takeaway: By analyzing user activity and leveraging predictive analytics, businesses can identify disengaged customers early and implement strategies to improve engagement and retention.

Everywhere you look, there’s a survey asking students if they’re using AI for learning. The problem is, we don't have real user data on how much are they using it and more importantly, how are they using it? Last month, Anthropic released a paper on CLIO (Claude Insights and Observations) — a tool that analyzes usage patterns of Claude while protecting user privacy. Think of it as Google Trends, but for LLMs. It didn’t get nearly the attention it deserved. (link in the comments) Imagine applying this idea to education: CLIO for learning. Instead of relying on surveys, real anonymized data would help education leaders understand how high school and college students are engaging with AI tools like LLMs in their coursework. 1️⃣ How often are students using AI tools? 2️⃣ Are they using them as “answer engines” or for deeper exploration of topics? 3️⃣ What drives brief, one-and-done interactions versus extended, curiosity-driven engagement in a topic? Right now, we have no real data points for teachers or school leaders to understand how students are interacting with these tools. Banning AI doesn’t work. AI detection tools are ineffective at best. School and district leaders empowered with data on volume of use, types of use, and what contributes to use that furthers learning, sets up the millions of gifted educators across the country with the information they need to evolve learning environments that keep rigor, improve engagement, and help young people thrive in the future. 

What #KhanAcademy’s FY24–25 Data Taught Me About #Scaling With #Proof As someone working in #DataStrategy & #ImpactAnalytics, I find these numbers fascinating — not just for their #scale, but for their clarity of #measurement. Most organizations track #growth. #KhanAcademy proves it. Their latest #EfficacyReport revealed that students who used Khan Academy for just 30+ minutes a week achieved ~20% higher learning gains on the MAP Growth assessment. (link to refer-https://lnkd.in/dQSZgcvb) Even moderate users showed measurable improvement — a clear example of how data validates mission impact. And then came my favorite — #Khanmigo, their AI-powered tutor and teaching assistant built with #OpenAI, which didn’t just grow 100% or 200% — it skyrocketed #731% YoY, reaching 2M users in a single year. But how? Let’s decode it 1. Designed to augment, not replace, teachers — reframing AI from a #threat to a #friend. Khanmigo became a co-teacher, empowering rather than replacing. 2. Transparent dashboards — giving educators real-time visibility into student activity and progress, turning data into decisions. 3. Global access — 2M users across 70+ countries, with nearly half being grassroots teachers using Khanmigo for almost free. For me, this is what great #DataStrategy looks like: 📊 Scale backed by evidence 🤖 AI grounded in governance 🎯 Impact made measurable through design Because growth alone isn’t success — Governed, evidence-based growth is. #AIinEducation #Governance #Leadership #ImpactMeasurement #KhanAcademy #StorytellingWithData

📊 Data in the Classroom: Useful Only When Used Wisely In classrooms, data is not the destination—it is the starting point. Test scores, observations, student reflections, and work samples are collected every day, but data creates impact only when it is interpreted thoughtfully and acted upon intentionally. Consider how data transforms when used wisely in learning spaces 👇 🔹 Raw Data This includes marks, attendance, exit tickets, anecdotal notes, and assessment results. On its own, raw data is fragmented and often overwhelming. It tells us what happened, but not why. 🔹 Sorted Data When teachers group data—by skills, concepts, misconceptions, or learning behaviors—patterns begin to emerge. Sorting helps identify: • Common areas of difficulty • Strengths across the class • Individual learning needs This step brings clarity and focus. 🔹 Arranged Data Organizing data over time allows teachers to track progress and growth. Comparing formative and summative evidence helps answer deeper questions: • Are students improving? • Which strategies supported learning? • Who needs intervention or extension? Here, data begins to inform instructional decisions. 🔹 Presented Visually Charts, rubrics, exemplars, learning progressions, and success criteria make data accessible and transparent. When learning is visible, students can better understand where they are and where they need to go. 🔹 Explained Through a Learning Story Data becomes meaningful when placed in context. Teachers reflect on student experiences, learning strategies, and classroom conditions. This narrative explains the why behind the numbers and supports reflective teaching practice. 🔹 Actionable Data The most important stage. Wise use of data leads to: • Differentiated instruction • Targeted feedback • Reteaching or enrichment • Student goal-setting and ownership of learning ✨ In education, data is not about judgement or comparison—it is about understanding and growth. When data informs teaching, empowers learners, and guides next steps, it becomes a powerful tool for improving learning outcomes. 📌 Data is useful only when it leads to purposeful action that enhances student learning. #DataInEducation #AssessmentForLearning #StudentAgency #ReflectiveTeaching #LearningFocused #EvidenceInPractice #EducationLeadership

📊 How can we use data science to truly improve schools? For over 50 years, education leaders have been urged to leverage data for decision-making. Yet despite massive investments in dashboards and analytics systems, research shows that the link between data use and actual improvements in student outcomes is often weak. In my new paper, “Data Science in Education Administration, Policy, and Practice”, I argue that education data science should be understood as a third core methodology in education research, alongside quantitative and qualitative traditions. Open Access Preprint: https://lnkd.in/eKYTr3i3 Key insights: 🔹 Beyond dashboards: Data science is more than reporting — it involves machine learning, visualization, and exploratory data analysis to support evidence-based improvement cycles. 🔹 Prediction matters: School leaders need accurate predictions, not just statistical model fit. Accuracy should stand alongside theory in informing decisions. 🔹 Algorithms in education must be Accurate, Accessible, Actionable, and Accountable (the “4As”). 🔹 Capacity building: We need to train educational data scientists who can both analyze data and communicate findings to policymakers, teachers, and communities. In effect, we must train people who can talk to people and talk to machines. 👉 The goal is not to replace theory, but to balance explanation with prediction — and to center human judgment, ethics, and collaboration in the process. 🔑 Key Takeaways for the Field For Practice: Schools and districts should embed data science partnerships — not just dashboards — into leadership and improvement cycles. Joint sensemaking between analysts and leaders is essential. For Research: We must expand beyond model fitting to systematically test prediction accuracy and build open, reproducible workflows that connect theory, and application. For Training: Graduate programs in education leadership and policy need roadmaps for education data science capacity building — equipping future leaders to understand, question, and apply advanced analytics responsibly. A key practice for training from Data Science is the Common Task Framework which focuses on: (a) open large-scale real-world deidentified datasets, (b) a shared culture of shared code for shared research, (c) public and open evaluation of algorithms. I’d love to hear from colleagues! Let me know what you think! Open Access Preprint: https://lnkd.in/eKYTr3i3 #EducationResearch #DataScience #EducationPolicy #SchoolLeadership #LearningAnalytics #EdTech

A few months ago, I was trying to learn German via Duolingo. As I struggled with vocabulary, Duo kept giving me vocabulary exercises in many different formats until I got the hang of it. Once I started to grasp the vocabulary, the exercises adjusted in pace, aligning with my learning progress. The adaptive nature of the platform kept me engaged, giving just the right amount of help while making the learning enjoyable. This was a great example of the power of data-driven platforms in personalizing and enhancing the user experience. With millions of users globally, Duolingo has transformed language learning into an engaging, gamified experience. What differentiates Duolingo from others is its use of data to create a personalized learning journey for each user. From the moment a user starts a language course, Duolingo collects data on their interactions with the platform—lessons completed, practice frequency, areas of struggle, and even the time spent on each activity. This data feeds into an algorithm that continuously adapts the learning experience to suit the user’s needs. Duolingo also uses A/B testing to refine its features. By experimenting with different versions of lessons, notifications, and the user interface, Duolingo determines what motivates users and what doesn’t. For example, it has tested various reward systems—such as streaks and gems—to find the most effective ways to encourage daily practice. Beyond personalising individual experiences, Duolingo analyzes broader patterns to shape its overall strategy. If data shows that users in a particular region are more interested in learning certain languages, Duolingo can prioritize developing those courses or change its marketing efforts accordingly. This ability to respond to market demands in real time has been a key factor in Duolingo’s global growth. Duolingo’s success demonstrates the power of data-driven growth strategies. The lesson for businesses is clear: Companies that use data to guide their growth strategies are better positioned to adapt to changing market conditions, respond to customer needs, and optimize operations for long-term success.

How can better access to education data transform literacy outcomes? Nebraska is showing us what’s possible. Project Unicorns latest resource, Transforming Education Data for Literacy and Improved Student Outcomes for All, tells the story of Nebraska’s journey to data interoperability through the Nebraska Education Data Partnership (NEDP). By leveraging the ADVISER system and the Ed-Fi Alliance Data Standard, Nebraska educators are gaining real-time, actionable insights to strengthen instruction and improve literacy outcomes for every student, no matter where they live or learn. This work isn’t just about better technology—it’s about building trust, aligning systems, and providing educators with the tools they need to support students in real-time. Backed by the Michael & Susan Dell Foundation and powered by statewide collaboration, this model provides practical guidance for anyone seeking to enhance the value and impact of education data. One of the co-authors, @terri hettenbough—part of the 2024 Project Unicorn Emerging Leaders Cohort—brings firsthand experience and fresh leadership insights to this important story. Explore the full piece for strategies, lessons, and honest reflections from the field: https://lnkd.in/eMmRpyWi #Interoperability #EdTech #Literacy #EducationData #ProjectUnicorn #EdFi #StudentOutcomes #K12Innovation #LeadershipDevelopment #NebraskaEducation #ISTE2025

Recently Anthropic analyzed conversations from higher education professionals using Claude.ai, revealing how educators are adopting AI across diverse academic functions. Customer Education and Higher Education are very correlated and with the rise of AI tools each industry is looking at how we can leverage the tools to build better learning experiences whether for a student in a University Program or customer. The research shows that educators primarily use AI for curriculum development (57%), academic research (13%), and student assessment (7%), with many going beyond simple chatbot interactions to build custom educational tools. Some takeaways from their research that stood out to me: 🎓 Educators prefer augmentation over automation for high-stakes tasks. While routine administrative work like financial management tends to be fully delegated to AI (65% automation), tasks involving direct student interaction—such as teaching, advising, and grant writing—are predominantly used in collaborative ways where educators maintain control and oversight. 🎓 AI is enabling unprecedented educational creativity. Educators are using AI to build interactive games, assessment tools, data visualizations, and subject-specific learning resources that were previously "prohibitively expensive" in terms of time and technical expertise, transforming AI from a conversational assistant into a creative collaborator. 🎓 AI is fundamentally reshaping educational approaches. Educators report that AI tools are forcing them to completely reconsider what and how they teach, with some abandoning traditional assignments like research papers in favor of more complex, real-world challenges that remain difficult even with AI assistance. What tools are you exploring for your customer or higher education programs? What resonates from this research? #alwaysbelearning #exploringAI #customereducationfuture