italki is an online learning platform that connects language learners with teachers worldwide for personalized, one-on-one lessons. What sets italki apart is its focus on immersive, interactive language learning, where students can engage in real-time conversations, pick up cultural nuances, and improve their pronunciation with native speakers.
To provide a rich and personalized experience, italki adopted a multi-level personalization strategy further enhanced by Blueshift’s Intelligent Customer Engagement (ICE) Platform. This strategy improved italki’s customer personalization, making matching students with the right teachers possible. The result? Higher student-teacher interactions, happier learners, and a meaningful revenue boost.
The Power of Multi-Level Personalization
In online learning, personalization often starts with basic filters like age or language preference. However, to truly resonate with learners, italki adopted a deeper, multi-layered approach that considered multiple dimensions of each user’s profile and behavior. italki turned to Blueshift to utilize the full richness of student and teacher preferences to deliver campaigns relevant to each student’s unique needs.
How the Multi-Layered Personalized Recommendation System Works
italki’s personalized recommendation process includes four key steps that turn student preferences into more accurate teacher matches. Here’s a closer look at how it works:
- Capturing Language Preferences and Proficiency Levels
italki personalizes learning by creating a unique profile for each student, capturing their target languages, proficiency levels (A1-C2), and native language. This ensures ideal teacher-student matches. - Curating a Candidate Set of Teachers
Blueshift’s recommendation engine selects teachers based on each student’s language and proficiency criteria, leveraging Collaborative Filtering and Large Language Models (LLMs) to enhance relevance to each learner’s needs. - Generating Filters for Targeted Matches
Filters refine the teacher pool based on learning goals. For instance, beginner Spanish learners are matched with teachers skilled in foundational grammar and conversation. - Prioritizing Teachers with a Personal Touch
The final step ranks teachers based on engagement, learning style compatibility, and pace, ensuring students connect with the most suitable instructors.
The results: Engagement and Revenue increase through targeted recommendations
italki enhanced its ability to provide effective, multi-level personalization. As a result, it experienced a 17.31% increase in new users’ post-registration engagement. This means increasing the number of users who registered and then booked a lesson within three days.
It saw a 25% improvement in dormant users’ re-engagement rates. Dormant users were defined as those who had been inactive for over a month and have now begun to engage with the platform again.
The number of one-time learners returning for another lesson within a month rose by 12.8%.
Conclusion: Empowering Students with Tailored Learning Journeys
italki continues to evolve its personalization strategies and relies on Blueshifit’s ICE Platform to meet the needs of modern language learners. The success of multi-level personalization at italki highlights the power of data-driven strategies in online learning. With Blueshift’s integrated CDP and AI-powered cross-channel marketing automation capabilities, italki is well-equipped to scale engagements with its user base and continue to expand to multiple countries and regions.