We would like a group of students to utilize our dataset and feature set, apply semi-supervised and supervised machine learning techniques, such as language based transformer models, embedding and clustering techniques, etc., in order to create:

• A series of trained models that can label raw text according to our feature set in order to create a labeled training dataset.
• A series of classification models trained on the labeled dataset created in the previous objective.

This will involve:

• Conducting background research on our existing product, our dataset and our feature set.
• Conducting research into the latest AI and ML techniques and how they could be applied to our data and feature set.
• Developing ML / AI models that can meet the functions stated above with a high degree of accuracy .

By the end of the project, students should submit a final report (along with any source materials such as code, workbooks, etc) that demonstrates:

• Understanding of the available dataset and feature set
• Methodologies and approaches
• Providing trained models that meet the objectives
• Providing the source code and all other relevant documents in a proper software development environment
• Recommended next steps for our organization

Bonus steps in the process would also include:

• Testing the solutions for accuracy with real users

Students will connect directly with us for mentorship throughout the project. We will be able to provide answers to questions such as:

• Current product understanding
• Current dataset, feature set and guidance in navigating it
• Recommended approaches to the AI / ML tasks
• Input on choices, problems or anything else the students might encounter