Inspiration
We were curious to see how we could use the quantitative data available to create an index that could accurately rank countries by the level of poverty they face.
What it does
The program organises the data and produces a cleaned data set, where Principal Component Analysis is performed on it to create a list of indicators that have a fixed weight to them.
How we built it
Utilising different libraries such as Sci-Kit Learn, Pandas, Numpy, and Seaborn, we were able to manipulate the data and rearrange the dataset to fit the specifications we needed to plot and visualise the information.
Challenges we ran into
One of the main challenges, as a group with no experience with Hackathons, was time management and identifying where to begin with the project. Also, because we did not have any prior experience in these technical skills, we had to constantly learn how to use the python libraries as we went along the project, this lead to us needing to use more time to process data, leaving us with less time to analyse the data properly.
Accomplishments that we're proud of
As challenging as it was to get through the processing and analysis, we are proud to have come up with an index that had weightage that was intuitively accurate.
What we learned
We have learned how to utilise the various data manipulation and visualisation libraries in Python, and we have also learnt different statistical analysis skills that will be useful for future data analysis projects.
What's next for CXC 2025 Submission
We intend to further explore the project, with a particular focus on the machine learning aspect of the challenge, we have ideas on how we could utilise machine learning to help predict how a country might develop in the future.
Log in or sign up for Devpost to join the conversation.