Christopher Barkachi: using data science to build an e-learning marketplace

Thursday, Aug 26, 2021
by Sharon Adarlo

Christopher Barkachi, 21, Class of 2022

Studies:

Barkachi is a computer science major who recently completed the undergraduate certificate program at the Center for Statistics and Machine Learning (CSML).

Research:

Barkachi is interested in using data science techniques for practical applications and having it potentially spun off into a start-up business. His independent project for the CSML certificate was developed along those lines: an e-learning market place called LiveShare.

“My project is a marketplace to connect people who want to learn and teach a skill by allowing people to offer their skills live,” he said. “Currently, with sites like Skillshare, instructors can record hours of content to upload. But for the learner, this entails their very first hours of learning, which psychologists say are the most crucial, to be unguided and lacking any sort of feedback loop. LiveShare obviates that need by giving learners the kind of one-on-one support that’s crucial when they’re first learning a skill.”

For the data science component of the project, Barkachi used machine learning to create a recommender system.

“A recommender system is basically a way of looking at a whole database of user reviews on movies, shopping items, games, or in this case, purchasable time with experts. And using that database of users, we are able to understand through machine learning which types of users like which types of items,” he said.

In LiveShare, the program not only recommends items to users based on what similar users enjoyed and rated the highest, but the program also clusters users for market segmentation analysis, he said.

“We are trying to understand the different user ‘archetypes’ that are using our service. Are you the type of customer that really enjoys more productivity or job-oriented skills like time management or a laid-back user who wants to try and get into pottery? We can discover or at least try to guess latent variables like these with recommender systems.”

After he completed his CSML project this past semester, Barkachi has continued to work on LiveShare.

“I am currently in the process of production. I am making sure that it's actually ready for a large number of users,” said Barkachi, who see this project potentially becoming publicly available.

After he graduates, Barkachi is interested in joining a start-up company working on natural language processing. Specifically, he’s interested in working on and studying racial and gender biases in natural language processing, especially when it comes to translation.

I made a Google Chrome extension that helps you understand the roots of words in Arabic, which I am learning. And that small project made me think about racial and gender biases that may come up when you perform translation tasks,” he said.

For now, Barkachi is spending his summer at Amazon as a software development engineer intern.

Extracurricular Activities:

Barkachi is part of the Princeton Tiger Tones, an acapella group, and is vice president of the Computational Linguistics Society on campus.

For Fun:

Barkachi enjoys exploring neighborhoods in New York City with friends.