We saw the Prudential challenge and wanted to test our data science skills.
What it does
Determines a binary value that determines the highest or lowest risk to the insurance company based on various factors included in the dataset.
How we built it
We visualized various features against the Approved and Lowest Risk columns. Since the neural net would determine the weight each column would have, we just added the appropriate columns that we felt would give the best result.
Challenges we ran into
We tried to optimize it and remove selective columns in an early build, but the neural net didn't converge. We added features back slowly, but because of the time it takes to run a neural net, it took a lot of time.
Accomplishments that we're proud of
We successfully implemented neural networks in a practical use case.
What we learned
We learned about various kinds of neural networks and the basics of R.
What's next for Prudential Data Analysis
Make the algorithm more optimized and speed up the process.