Education Technology Services

Learning analytics and data-driven recommendations in education

“When we have all data online, it will be great for humanity. It is a prerequisite to solving many problems that humankind faces.”

-Robert Cailliau, computer scientist and informatics engineer who helped to develop the internet.

Humanity’s critical problem is making education count in a fast-changing world. An effective way is to use data analytics in education to identify learning gaps and build actionable strategies for the desired learning outcomes.

Analytics in education

Fostering a data-driven culture in education is tough, as the education industry is deeply entrenched in legacy. Institutions and educators take a traditional approach to many critical educational processes, including curriculum planning, pedagogy, assessments, learning recommendations, and interventions.

During the pandemic, most institutions digitised, partly or fully, to enable online synchronous learning. The use of ERP portals, online assessments, and Learning Management Systems (LMSs) in education is now common. These tools have provided us with multiple touchpoints and metrics for gathering and evaluating student data.

With learning analytics, it is easy to build descriptive and predictive models for identifying learner issues and offering support through data-driven recommendations.

What are learning analytics and data-driven recommendations?

Learning analytics is extracting, collecting, and analysing data about learners and learning contexts to improve the instructional process and learning environments. Data-driven recommendations refer to using learning analytics insights to enable formative feedback, targeted intervention, and content recommendation for the best learning outcomes.

Traditionally, schools have used descriptive learning analytics - or the evaluation of historical data - to identify student behaviours, preferences, and performance. This helps them to track progress and initiate corrective actions where necessary. The data for descriptive analytics comes mainly from education LMSs and other digital touchpoints.

Institutions now need a progressive approach to foresee likely outcomes based on identifiable historical patterns and initiate interventions and recommendations before problems manifest.*

The way to achieve this goal is through predictive analytics in education.

Predictive analytics in education

Predictive analytics in education combines historical student data with statistical algorithms and machine learning to forecast the likelihood of events in the educational space. With AI and ML backing, predictive models have a 90-95% accuracy.
Predictive analytics with data-driven AI can assist learning institutions in forestalling problems, identifying trends, enhancing feedback methods, and recommending the right services to students.

Researchers in a 2021 study deployed predictive analytics with explainable ML to develop a student dashboard that offered formative feedback for assessments and data-driven course recommendations based on performance. The experiment successfully increased the students’ motivation, assisted them in self-regulation, and improved learning outcomes.

Besides formative feedback, here are some more use cases of predictive analytics in education:

Personalised learning

With predictive analytics, educators can identify their students’ learning gaps and shortcomings in the academic curriculum. With this knowledge, they can customise learning modules to align with individual learning styles and goals for a richer learning experience.

Learner segmentation

Using predictive analytics in education enables institutions to segment students based on subtle characteristics such as learner types, academic choices, and resource usage rather than broader demographics. Learner segmentation is especially useful for content recommendations and targeted recruitment.

Informed recommendations

Through sustained monitoring of student performance, educators can predict success or failure rates in summative assessments. By pre-identifying students or cohorts that need help, they can recommend the relevant content or services to these students to ensure higher success rates.

Trends identification

The use of predictive analytics in education helps uncover trends that can enhance learner responsiveness and overall performance. For instance, educators can identify if weekend online classes, micro-learning videos, or peer reviews are likely to improve student engagement and take the necessary measures.

Targeted intervention

Intervention is necessary for multiple situations in the academic space. With predictive analytics, institutions can identify problems before aggravating them and initiate targeted interventions. For instance, they can identify students most likely to drop out and offer counsel and assistance beforehand.

Targeted enrolments

By predicting which students are more likely to enrol in their courses, institutions can target niche learners and position themselves as the best fit for specific study programmes. This can result in higher ROI on education for all stakeholders.

How can Infosys BPM help?

Infosys BPM learner segmentation and recommendation services support institutions in tapping potential learners, suggesting personalised courses and services,  enabling timely interventions, and ensuring higher success rates.

Our micro-segmentation services include social media marketing, content marketing, and AI/ML-supported campaign strategies to target niche audiences, leading to better conversions.

Know more about learning assessment platform at Infosys BPM Learner Segmentation and Recommendation services.

*For organisations on the digital transformation journey, agility is key in responding to a rapidly changing technology and business landscape. Now more than ever, it is crucial to deliver and exceed organisational expectations with a robust digital mindset backed by innovation. Enabling businesses to sense, learn, respond, and evolve like living organisms will be imperative for business excellence. A comprehensive yet modular suite of services is doing precisely that. Equipping organisations with intuitive decision-making automatically at scale, actionable insights based on real-time solutions, anytime/anywhere experience, and in-depth data visibility across functions leading to hyper-productivity, Live Enterprise is building connected organisations that are innovating collaboratively for the future.