Digital educational platform

A platform that connects mentors and coachees using machine learning and data analytics.

Customer

Industry

Education

Region

Client since

2020

Our customer is a European e-learning platform that provides customers with mentors on the subjects of their choice.

Detailed information about the client cannot be disclosed under the provisions of the NDA.

Challenge

A client came up with the idea that the platform should be enhanced with data engineering and machine learning tools so that it could suggest mentors to users more rapidly and accurately. Data should be properly gathered and refined before being used by recommender systems, time-logging tools, and other software.

To solve the problem, Innowise’s software engineers needed to

study the client’s existing data flow design;
rebuild the data flow;
automate an array of manual processes;
design architecture that ensures both functionality and security.

Solution

Innowise has built from scratch a platform that provides mentors and coachees a toolset for interacting with each other in an effective and convenient way. The solution has been developed to replace the previous version of the platform due to its lack of response speed and functionality.

Our software engineers have designed the solution in a way that allows data to be rapidly gathered and updated from various sources. The data is automatically refined according to the preset templates and sent to the tools that operate it.

Amazon Web Services

The solution is based on Amazon Web Services due to its security, flexibility, scalability, and cost-effectiveness.

Coaches and regular customers can submit their data in various forms to the platform, including text, pictures, videos, document scans, etc. This data is uploaded to AWS and stored in a data lake.

ETL pipelines

Our data engineers have developed and introduced ETL pipelines to automatically gather data chunks from the users into the cloud storage.

Data lake and data warehouse

Data gathered through ETL pipelines is refined in data lakes. This process is operated by Airbyte and dbt. After the data is refined, Apache Airflow transfers it to the data warehouse where it can be used for various purposes, such as

recommending and notifying mentors of suitable coachees more precisely;
estimating user activity and productivity;
predicting user behavior in different fields;
providing secure automated payments to the mentors;
detecting frauds;
performing KYC, AML, ATF actions, etc.

Technologies & tools

Back-end

Python 3.x, Flask, Celery, WebSockets, Django REST framework, Pytest

Front-end

TypeScript

Databases

PostgreSQL, Redshift, S3, SalesForce, Elasticsearch

DevOps

Kubernetes, Apache Airflow, Terraform, plural, astronomer

Cloud

Google Cloud Platform, AWS

VCS

GitLab, GitHub

Process

Taking into consideration all the project requirements and specifics, we have selected Scrum as a software development methodology, conducting bi-weekly sprints and Sprint overviews to demonstrate the progress. We used Jira and Confluence and held the meetings and overall communication with the client in Microsoft Teams.

Our team developed the requirements according to the client’s vision of the solution and documented them. During the development process, we were constantly analyzing, refining, and decomposing the requirements into tasks and subtasks for easier progress tracking. After several tasks were completed, Innowise’s quality assurance engineers checked whether the solution was compliant with the outlined requirements, was bug-free, and our team was on the same page with the client’s vision and expected outcomes.

Team

Data engineers

Back-end developers

Front-end developers

ML engineer

Data scientists

BI developers

Business analyst

Project manager

QA engineers

Results

Innowise has built a secure platform that allows the client’s employees to collect, store, and manage data from students and tutors on the platform. Due to the security of the solution and strict access and operation control, this information can be used for a variety of purposes without fear of being leaked.

Our software engineers have automated a number of processes that were previously manual and designed the data flow to make the solution as efficient as possible.

Project duration

Since 2020
The project is still ongoing; at this stage, we support the platform and implement new features

Related cases

Contact us!

Book a call or fill out the form below and we’ll get back to you once we’ve processed your request.

What happens next?

Having received and processed your request, we will get back to you shortly to detail your project needs and sign an NDA to ensure the confidentiality of information.

After examining requirements, our analysts and developers devise a project proposal with the scope of works, team size, time, and cost estimates.

We arrange a meeting with you to discuss the offer and come to an agreement.

We sign a contract and start working on your project as quickly as possible.