AI Health Insurance Cost Predictor
What it does
This is a web application that provides users with an estimate of their health insurance costs based on specific demographic inputs. Users input key details—such as age, gender, BMI, number of dependents, smoking status, and geographic region—and the AI model predicts their expected health insurance costs. This tool helps users make more informed decisions by giving an estimate that corresponds with general insurance cost trends.
How I built it
I built this application using a ML model (MosiacML in Datastacks) and I trained it based off of a data set that I found online that had the information I needed to start training the AI. I originally wanted it to be for multiple insurance types, yet that proved a little too daunting so I lowered it down to just one. I also originally wanted it to be an interactive chatbot on a website that would only respond to user prompts that contained certain keywords, but I couldn't find a model that was within Technica's prize category, so I used Mosiac since I wanted to make it larger scale. I programmed the whole application in vscode and then used my powershell terminal to create the server IP. Most of my project is backend, but I also integrated some UI using HTML, CSS, and java. Although design is not my specialty, I am proud with my successful implementation of the Bootstrap Framework and Figma prototyping done beforehand.
Challenges I ran into
I encountered so many errors. Since this was maybe my second or third time working on a project like this, it was my first time doing something like this alone. So when I were to run my code it would display errors due to how I would preprocess the data. After a little I figured out some simple syntax errors and moved forward, but I still did struggle with errors in my code here and there even after styling.
Accomplishments that we're proud of
I am really proud that I was even able to bring myself to take on such a large project. It was the best investment of my time I think I have spent thus far and I have learned so many new things and expanded a lot of my previous knowledge, which is great to come out of an event feeling!
What I learned
By building this project, I learned how important patience is and trusting the process. When it got to around 3AM this morning I had felt like I had hit a block, but working on something that genuinely interested me helped me push back that barrier that was holding me back from working.
Log in or sign up for Devpost to join the conversation.