Online Regression

An efficient web resource for measuring a foreign language proficiency level

Hours total

1640

Technical Stack

Linear models, DTW, Deep learning, Probabilistic programming, VGG, PCA

Services Involved

Dedicated Team

Have similar project?

OVERVIEW

An efficient web resource for measuring a foreign language proficiency level. Foreign language learners aim to find a simple for understanding and complex for skill sharpening tests covering all aspects of language.

CHALLENGE

To measure a person’s language proficiency level with a number, where the number is the highest item score the person is capable of answering correctly. This number should correlate with TOEFL or CEFR scores. The product should be deployed to a website capable of accepting large number of concurrent.

Solution

Development of a Maximum Likelihood Estimation (MLE) as an algorithm for computing the proficiency level, creation of mode estimation models for solving the online regression task.

Results

A fast and reliable web service with clean and simple UI test which allows users to determine their language proficiency level within a few dozens of two-option questions. The results show a strong alignment between the test numbers and TOEFL scores.

Recent cases

Our latest challenges where technology meets creativity

image
image

Colourbox

Discover your favorite place

image
image

Middleware

Tool for keeping data

image
image

Large Scale Analytics

The process of applying data analysis techniques to a large amount of data

Contact us

If you have a question, request or just want to meet up for coffee, call, email us or fill out the form and we will contact you asap.

Full Name
Email
Short message