We arrange our AI
to work in your company

Develop a web application (a website with a personal office) that acts as a full-fledged loyalty program for the Huggies brand, aimed at retaining existing customers, raising the average check, etc.

A website with a personal office and a mobile version with a built-in CV check recognition module has been developed, allowing you to validate a check within 10 seconds and accrue points (“hagi”) for users with the ability to exchange those points for prizes.

Highly rated the developed service by the Kimberly-Clark team, more than 7,000 registered users on the first day of the loyalty program.

Разработать удобный интерфейс для пользователей, в рамках которого они могут нативно загружать чеки и участвовать в акции от бренда.

Разработаны боты для Телеграм и Вайбер, а также виджет для сайта с проработанным UI/UX, а также со встроенным CV-модулем распознавания чеков, который позволяет валидировать чек в течение 10 секунд.

Высокая оценка разработанного сервиса со стороны команды Kimberly-Clark, для которых проект стал первым опытом разработки чат-ботов, более 3000 зарегистрировавшихся пользователей в первый день работы  акции.

Разработать решение, которое позволит автоматизировать прием заявок на доступные вакансии от кандидатов. Система реализована для устройств, которые расположены в офисе Mareven.

Реализован виджет, который выступает точкой сбора резюме и контактов потенциальных соискателей.

Виджет разработан с учетом особенностей устройств, которые расположены в офисе Mareven, а также реализована адаптивная верстка для планшетных устройств.

Решение автоматизирует процесс за счет предоставления релевантной анкеты на каждый тип вакансии и автоматической проверки соответствия кандидата по основным параметрам, заданным на входе

Высокая оценка дизайна, UX и алгоритма со стороны представителей компании Mareven.

Predict users of Skyeng’s online English courses who will opt out of courses based on their behavior on the site in order to form special offers for such students.

A documented API model has been developed that predicts user outflows based on the features that have been selected as important within the user behavior on the site.

All the signs of such users were also given with their percentage of their impact on the model results.

Results and achievements

In two weeks, a model has been developed that predicts with accuracy more than 86 segments of users who will give up English courses in the next two weeks and in the next month.

Based on the data of this system – Skyeng forms special offers for its customers.

Create chatbots as a widget on the Russian Railways educational portal website.

The widget is supposed to process the main array of user requests, recognizing natural speech and selecting a pre-programmed response from the database.

We prepared a system prototype based on the chatbot in Telegram and Viber, which will allow to test the solution on a sample of 100 users. While creating the system, a machine learning algorithm to work with new data was developed.
In addition, data preparation methodology (preprocessing, cleaning) for new array operational processing was created.
The project is at the testing stage.

A pilot version of the product was developed, allowing even on a limited sample to automate 3 main types of standard user questions.