Embibe is an online portal that consists of a team of entrepreneurs, who help students to get coaching for various entrance examinations like JEE, AIIMS, AIPMT, CET and much more. Founded by an ex-TCS employee, 33-year-old Aditi Avasthi, wanted to change the way students prepare for competitive exams. Embibe’s vision is simple – to maximize learning outcomes at scale. At present, Embibe boasts of over one million student users. Last year, this EdTech venture raised $4 million from early-stage investors such as Kalaari Capital and Lightbox.
There are 2 step formula that Embibe and its data team use to help solve this problem for millions of students:
- Content Ingestion — Getting enough of the right content for every unique and individual student.
- Content Delivery — Giving each student exactly the content that he needs to see at exactly the right time.
Dozens of syllabus boards, thousands of chapters and concepts, and tens of thousands of institutes and schools result in hundreds of thousands of questions and answers generated and used by instructors every year. Imagine if every student were able to test their knowledge before exams on any subset, or all of these questions, along with getting detailed explanations about the correct answers, and common mistakes made. In order to make this a reality, they are leveraging optical character recognition (OCR) and machine learning to build their own automated ingestion framework that will be highly scalable, truly multilingual, and minimally dependent on human input. And the fun doesn’t stop there. The framework will also be able to ingest handwritten content in a writer-agnostic fashion, thereby rapidly adding to their already fantastic repository of questions, answers, concepts, explanations, and knowledge. Now that they have questions, answers, concepts, and chapters all ingested into a massive data warehouse. It would be painful to manually tag each question or chapter with its relevant concepts, or vice versa. Data Science to the rescue! Using bleeding-edge ideas from text classification, topic modeling, and deep learning, they automatically tag concepts to questions, answers, and chapters.
Prior databases containing seed sets of high quality manually tagged content is instrumental as they extract linguistic, lexical, and context-sensitive features, to train state-of-the-art text-tagging models for all the new data that gets ingested into their systems. For instance, the First Law of Thermodynamics is related to the concept of a thermodynamic system, which in turn is related to the concepts of specific heat capacities of gases, conservation of mechanical energy, and work done by a gas, among others. Their content ingestion framework includes data enrichment components that automatically crawl the web and tag content with such diverse pieces of media as text explanations, video links, definitions, user commentary, and forum discussions, all while respecting copyrights, and properly attributing ownership on sourced content. This wealth of available information also makes it possible to automatically connect related concepts in a tree structure. Using ideas from the fields of graph theory, text mining, and label propagation on sparse structures, they create links and interconnections between concepts that share a source-target relationship.
Embibe track every move that a user makes on the site. The millions of practice and test attempts made by their users over the past three years is calibrated in a data space of many thousands of dimensions. This translates to a space of billions of data points that they can mine to dig deep into the users’ behavioral data and generate insights that correlate with how learning happens. Each additional attempt by a user tweaks their ability to score higher on the concepts tagged to that attempt, along with the connected preceding and succeeding concepts. This super complex problem involves leveraging ideas from sparse matrix processing, computational algorithms in graph theory, and item response theory to build robust and adaptive user profiles that scale with their growing user base.
Certain students may learn and thereafter perform on tests, better with the help of video explanations, compared to other students who prefer extensive textual descriptions, or still others who learn by working step-by-step through solved example problems. They can map users to well studied theoretical models of learning styles like the Dunn and Dunn Model (Dunn & Dunn 1989), or Gregorc’s Mind Styles Model (Gregorc 1982) to automatically tailor remedial courses of practice and help the user towards score improvement. Users are grouped based on their usage patterns with respect to product features as well as their performance patterns with respect to test, practice, and revision sessions. Each user is mapped to a high dimensional feature space of many thousands of attributes, which include static as well as temporal measures.
Embibe’s feedback and recommendation system (on which they have filed patents already) are designed and built for one purpose — to maximize a user’s score improvement. They instrument and interpret thousands of signals about a user’s attempts during practice and test sessions, and transform these signals into a high-dimensional space of thousands of features for each user. Using statistical pattern mining on the massive user-attempt feature space, they have zeroed in on the ranked sets of parameters that positively drive up a user’s score. These parameters are machine-coded as highly targeted just-in-time capsules of score improvement feedback and delivered to the user while they continue with their practice session. The feedback and recommendations expose weaknesses and strategies that they can adopt to maximize their score.
Embibe is a household name among the online education platforms, specially with its ‘feedback and recommendations’ feature which shows the openness of this startup to improve themselves but being such a big name it should also provide a variety of products like considering to provide learning courses in all unconventional streams like Mass Comm, Fine Arts so that more students can be attracted and get the benefit from this wonderful learning platform as today with new courses almost as many new exams make their debut.