đź‘‹ Hello, friends! We recently sat down with Swaraj Banerjee and Larry Zhang from Sempre Health, a startup that brings behavior-based, dynamic pricing to Healthcare. They are doing some exciting work with machine learning and are leveraging our Expert Acceleration Program to accelerate their ML roadmap.
An example of our collaboration is their new NLP pipeline to automatically classify and respond inbound messages. Since deploying it to production, they have seen more than 20% of incoming messages get automatically handled by this new system 🤯 having a massive impact on their business scalability and team workflow.
In this short video, Swaraj and Larry walk us through some of their machine learning work and share their experience collaborating with our team via the Expert Acceleration Program. Check it out:
If you’d like to accelerate your machine learning roadmap with the help of our experts, as Swaraj and Larry did, visit hf.co/support to learn more about our Expert Acceleration Program and request a quote.
Transcription:
Introduction
My name is Swaraj. I’m the CTO and co-founder at Sempre Health. I’m Larry, I’m a machine learning engineer at Sempre Health. We’re working on medication adherence and affordability by combining SMS engagement and discounts for filling prescriptions.
How do you apply Machine Learning at Sempre Health?
Here at Sempre Health, we receive thousands of text messages from the patients on our platform every single day. A huge portion of these messages are messages that we can actually automatically respond to. So, for example, if a patient messages us a simple “Thank you”, we can automatically reply with “You’re welcome”. Or if a patient says “Can you refill my prescription?”, we have systems in place to automatically call their pharmacy and submit a refill request on their behalf.
We’re using machine learning, specifically natural language processing (NLP), to help identify which of these thousands of text messages that we see daily are ones that we can automatically handle.
What challenges were you facing before the Expert Acceleration Program?
Our rule-based system caught about 80% of our inbound text messages, but we wanted to do much better. We knew that a statistical machine learning approach would be the only way to improve our parsing. When we looked around for what tools we could leverage, we found the language models on Hugging Face would be a great place to start. Even though Larry and I have backgrounds in machine learning and NLP, we were worried that we weren’t formulating our problem perfectly, using the best model or neural network architecture for our particular use case and training data.
How did you leverage the Expert Acceleration Program?
The Hugging Face team really helped us in all aspects of implementing our NLP solution for this particular problem. They give us really good advice on how to get both representative as well as accurate labels for our text messages. They also saved us countless hours of research time by pointing us immediately to the right models and the right methods. I can definitely say with a lot of confidence that it would’ve taken us a lot longer to see the results that we see today without the Expert Acceleration Program.
What surprised you about the Expert Acceleration Program?
We knew what we wanted to get out of the program; we had this very concrete problem and we knew that if we used the Hugging Face libraries correctly, we could make a tremendous impact on our product. We were pleasantly surprised that we got the help that we wanted. The people that we worked with were really sharp, met us where we were, didn’t require us to do a bunch of extra work, and so it was pleasantly surprising to get exactly what we wanted out of the program.
What was the impact of collaborating with the Hugging Face team?
The most important thing about this collaboration was making a tremendous impact on our business’s scalability and our operations team’s workflow. We launched our production NLP pipeline several weeks ago. Since then, we’ve consistently seen almost 20% of incoming messages get automatically handled by our new system. These are messages that would’ve created a ticket for our patient operations team before. So we’ve reduced a lot of low-value work from our team.
For what type of AI problems should ML teams consider the Expert Acceleration Program?
Here at Sempre Health, we’re a pretty small team and we’re just starting to explore how we can leverage ML to better our overall patient experience. The expertise of the Hugging Face team definitely expedited our development process for this project. So we’d recommend this program to any teams that are really looking to quickly add AI pipelines to their products without a lot of the hassle and development time that normally comes with machine learning development.
With the Expert Acceleration Program, we’ve put together a world-class team to help customers build better ML solutions, faster. Our experts answer questions and find solutions as needed in your machine learning journey from research to production. Visit hf.co/support to learn more and request a quote.
