BACtoBAC

Inspiration

We've often seen people have a lack of understanding when it comes to how much they can drink. People sometimes drink a lot thinking they are fine because the alcohol hasn't been absorbed yet, and when the effect eventually kick in, they are overwhelmed by a lack of coordination and will sometimes vomit. Even though many of these people understand BAC and what effects different ranges have, they seem to have a misunderstanding of how BAC changed depending on drinks and time passed.

What it does

BACtoBAC is a visualization tool to help people, particularly inexperience drinkers, understand how their blood alcohol content will change over time. Additionally, it is more accurate than other currently available tools because it accounts for people consuming alcohol while their body is already metabolizing alcohol from prior drinks. BACtoBAC also accounts for different absorption rates based on the situation.

How we built it

We created a model based off of multiple scientific studies that mapped the absorptions of alcohol into the bloodstream over time and the reduction of alcohol in the bloodstream. These were created to take several factors into account, such as weight, height, sex, volume of the drink, and alcohol content. We then built a live website around this model to display the data in an easily digestible manner. Finally, we created a simple app using the website for a more convenient way of accessing this tool.

Challenges we ran into

The biggest challenge by far was determining how to model BAC over time. There were a variety of factors, some significant, some not, which we had to judge and potentially add to our model. We overcame this challenge by examining data from multiple research papers and using tools like TensorFlow to determine the importance of certain factors.

Accomplishments that we're proud of

We're very proud of the model that we've created, especially since no tools like it currently exist. We feel that this is something many people would want to use, so we were very happy that we successfully accomplished the goal we had in mind when we started this project. The scientific and data-driven side of this project was by far the most difficult aspect of this project, but we managed to come up with a solution we're proud of.

What we learned

We learned how we could use TensorFlow to help do data analysis for us, instead of combing over datasets and equations ourselves. This alleviated much of the pressure off of us, so that we could focus on other aspects of this project. Additionally, we've learned how to create a effective and interactive data visualization tool for people to use.

What's next for BACtoBAC

In the future, we would like to include a pop up that will display how you might be feeling based on the effects of the alcohol, as well as warning if the model predicts your BAC will reach dangerous levels soon.