From personalized experiences, to expanded access and smart content, AI is transforming Education.

Education

According to research from McKinsey, teachers spent between 20% to 40% on tasks that could be automated. Even though most experts confirm the critical presence of teachers is irreplaceable, there’s plenty of room to help the teacher’s job and improve student success at the same time.

Learn More

Use Cases

How we can leverage ML in Education

Personalized learning

Assessment facilitation

Student and courses matching

Cheating detection

Course recommendation

Smart content

Deepfakes

Deep Fakes and Automatic Translations

About the client

Guide Education is a collective of teachers, governors, technologists, and trainers that support a range of institutions. It provides solutions for school-based teacher training, staff development platform, educational consultancy, and online student support. They have a large dataset of training materials in a text format and would like to transform them into audiovisual materials.

Challenge

They approached us looking to build a tool to create short educational videos that could be easily translated into any language. The purpose was to mitigate the language barriers and foster inclusion in education across the world.

Results

We also developed a solution using speech-to-text to generate text transcriptions based on videos and translate them into any language, all of which could be edited in live mode anytime through a user-friendly interface. Conversely, using text-to-speech, we worked on generating new videos based on previously made text translations. Subtitles were embedded in the video so that users could download the video with the desired transcription.

Alongside the client, we developed an end-to-end product, allowing collaboration between the ML team, backend and frontend developers. As a result, we helped them increase accuracy in the transcribing stage closer to 90-95%, compared to the 70% that was previously achieved.

hrs

Savings in hours per week

Impact

Research suggests that AI applications can save teachers an average of 13 hours per week that could be redirected toward activities that lead to higher student outcomes, more student engagement and increased teacher satisfaction.

Impact

hrs

Savings in hours per week

Technologies

Python, Golang, Tensorflow, Keras, Pytorch, MySQL, GANs.

Detecting Student Attrition

About the client

CAF In this case, our clients were a government agency, in charge of secondary education throughout the country, along with the National Institute of Educational Evaluation.

Challenge

When we want to prevent student dropout, detecting which students are at risk of dropping out in advance is very important. For this reason, the objective of the project was to study the behavior of different student trajectories and identify risk factors based on the socio-economic and academic data of high school students in Uruguay.

We worked with data sets of more than 100,000 students from all over the country.

Results

Data analytics solutions were developed to identify vulnerability factors of students that can later lead to educational dropout. The project also included the identification and clustering of educational trajectories.

As a result, predictions of a student's academic outcome for a given year are also generated.

School dropouts

Impact

School dropouts can be as low as 5% to more than 40% in developing countries. This severely limits the chances of future success for far too many children. Early detection is key to crafting prevention strategies.

Impact

School dropouts

Technologies

Python, data analysis, clustering and visualization techniques.

Clustering

Visualization Techniques

Data Analysis

Get in touch with one of our specialists.

Let's discover how we can help you

Training, developing and delivering machine learning models into production