Lilwil’s personalized learning engine teaches teachers how to teach

Every student has a unique learning style, but it’s tough for teachers to figure out whether they learn best through lectures, images, reading, self-directed practice or group projects. By using publicly available education progress data and personality analysis, Lilwil is able to automatically identify the best teaching method for a student and recommend it to their instructor.

Lilwil was one of the hundreds of projects built overnight at the TechCrunch Disrupt NY Hackathon. It could make schools more efficient, keep students engaged and make teaching more rewarding. Personalized learning is becoming a big trend in tech with the Chan Zuckerberg Initiative pledging funding to develop software and strategies in the space.

Lilwil personality over time

First, Lilwil used the HMH API which has data on the grades and assignments of students in a large percentage of public schools. It then applies IBM’s Watson to assess the different personality traits of students based on their work such as openness, conscientiousness, extraversion, agreeableness and emotional range.

Lilwil then presents a personality analysis to teachers, along with suggestions for the best methods for assisting that student. For example, Lilwil could identify higher levels of extraversion and conscientiousness in a student, and determine that they’re best taught through role-playing simulations and roundtable discussions.

Lilwil personality graph

Two of the Lilwil team’s founders, Lishing Chan and Will Ho, originally met in Singapore before coming to the U.S. They’d both had bad experiences in school because they weren’t taught with strategies that matched their disposition.

That can be especially problematic in countries like Malaysia where one of the founders grew up, considering students can be physically punished with caning for poor performance. Their experiences inspired them, along with Luis Bosquez, to build Lilwil so other students have a more adaptive journey through education.

Many teachers stick with the tough job because they love watching children blossom. Lilwil could make it easier to unlock these students’ full potential, making the teaching profession more satisfying and attractive to talent.

Chan tells us “We thought there’s a better way to match learning styles and teaching methods to maximize how students learn. That group of students in primary and secondary school will be our workforce in the future!”

Updated to correct the API used by Lilwil.