Sex crimes are an issue at Penn State University, University Park. As Penn State students, we receive timely warnings for crimes and students should know that sex crimes are an issue as early as their first semester on campus. We want to raise the community awareness for sex crimes that occur near campus, so that administration can implement the necessary initiatives in place to reduce the likelihood of sex crimes.
What it does
Provides the user with predictive analytics on sex crime data trends. Provides the user with useful information on sex crime and consent.
How we built it
This project was created with figma, webflow and google colab.
Challenges we ran into
We had trouble with the accuracy score while using machine learning models. We also wanted to integrate more models however we agreed that it would be more efficient and to the point to just show the one.
Accomplishments that we're proud of
Having a friendly-user interface is an accomplishment that we are proud of. Another accomplishment is that Vigilant is easy-to-understand because we have provided simple yet effective analytics that provides users with further insights on the trends in their area.
What we learned
We learned about the trends across Pennsylvania and how people are affected by it across the United States. We learned how to use linear regression, support vector regression, and decision tree regression machine learning models for identifying the trends in sex crime data.
What's next for Vigilant
Vigilant needs to have an improved accuracy score for the generated analytics. We understand that there is a limited amount of data available that will assist with the statistical modeling; we want to access more data, so that we are getting the best results.
We want Vigilant to have interactive heat maps for providing the user with further insights on their community's trends. We want to try coding with the R programming language too.