SNHU
Guide me

Guid me

Empowering New College Students with AI/ML: A Seamless Pathway to Success
Project Description:

We embarked on a journey to apply AI/ML models to support new college students who may lack guidance along their educational pathways. Recognizing the need for timely information and support, we integrated a chatbot and a fluid pathway experience. This system connects students with relevant programs, educational units, or personnel, providing just-in-time assistance to enhance their educational journey.

My Role:

As the Director, I led brainstorming and “how might we” sessions with subject matter experts and a team of designers, researchers, and product managers. Together, we developed comprehensive use cases and proof of concepts. Our goal was to test, iterate, and communicate these concepts to the broader university, enabling them to implement the solutions within their unique programs.

Outcome:

The proof of concept was highly successful. By applying AI/ML models to real-life problems, we created a valuable tool that empowers students to move forward with confidence, knowing that SNHU supports them every step of the way.

Fostering Collaborative Conversations

We are crafting a narrative to engage with SNHU GC and OPPI individuals, aiming to spark “How could we?” and “How would we?” discussions. This story isn’t about problem-solving or reaching conclusions but highlighting areas where sharing specific information can ease learners’ lives when everyday challenges arise. Our goal is to collaborate with SNHU GC as thought partners to find the best ways to enhance this experience.
Success
This information was received with enthusiasm and a strong sense of teamwork.

Explore Your Future with SNHU

Discover Your Pathways
After onboarding, explore different pathways tailored to your interests. Adjust your preferences anytime, and the system will update your results accordingly.

Harnessing AI/ML to Revolutionize Student Support

Natural Language Processing (NLP)

We utilized NLP models to understand and respond to student queries in a conversational manner. These models helped the chatbot interpret the context and intent behind student questions, providing accurate and relevant information.

Recommendation Systems

To personalize the educational pathways, we implemented recommendation algorithms. These models analyzed student data, such as their academic history and preferences, to suggest relevant courses, resources, and programs.

Predictive Analytics

Predictive models were used to identify students who might need additional support. By analyzing patterns in student behavior and performance, these models helped us proactively offer assistance to those at risk of falling behind.

Sentiment Analysis

We incorporated sentiment analysis to gauge student emotions and satisfaction. This allowed the system to adjust its responses and provide a more empathetic and supportive interaction.

Machine Learning Classifiers

Various classifiers were employed to categorize and route student inquiries to the appropriate resources or personnel. This ensured that students received timely and accurate assistance.