Female Data Analysts

Inspiration

We were inspired to do this project after seeing that this track would allow a variety computer visualization opportunities when considering the numerous columns included. This also was interesting as there was a real world application to it, the FDA.

What it does

Moving forward, we would want to expand our dataset and incorporate more variables that could refine the predictive capabilities and possibly explore more sophisticated modeling techniques. Our overarching goal is to continue advocating for data-driven decision making and the empowerment of female data analysts in the tech industry.

How we built it

We coded in Google Colab, where employed a range of preprocessing techniques, feature engineering, and linear regression methods to refine our dataset and derive insights for our recommendations to the FDA.

Challenges we ran into

We ran into challenges trying to use different data analysis methods to find meaningful relationships between variables in the dataset and creating an accurate prediction model.

Accomplishments that we're proud of

We are proud that we created a new feature that distinguishes between different medical severities and that we employed a linear regression model to try to understand the causes of medical severity so that we can help enhance care for demographics most susceptible to serious health risks.

What we learned

We learned to work as a team and use a short amount of time and the resources given to us to try different data analysis and modeling methods to draw conclusions from the FDA dataset and how to relate multiple variables' relationships with each other in order to make useful recommendations.