The city search tool we were given seemed fairly rudimentary so we chose to add onto it and improve it to not only have more categories to prioritize, but to customize it further to help a user decide how many potential cities they want to see in front of them. We made it more accessible for users so that they can thoroughly enjoy finding cities that fit their preferences the most.
Let's say the user wants to leave the city they're living in (whether it be for a vacation or permanently). With this city search, the user is able to prioritize what they want to see in a city ranging from purchasing power to atheism all the way to pollution and precipitation rates. After deciding what's the most important to them (rating the prioritization from none to high) and how many cities they want to see, the code outputs the cities that fits the user's preferences the best. From there, not only does the user have a great place to move to, but also fantastic potential vacation destinations for the future.
We, as a team, were given some code to start with from the creators of this challenge. However, it didn't seem to cover enough information the way we visualized and wanted it to. Since the customization through different weights on the prioritization worked well, we decided not to change anything, rather add to it and improve it to be more user friendly and informative.
As novices (we are all freshmen), accessing mass data, importing it into the sheets, and making sure the data was accurate was a huge challenge we ran into. None of us have many experience with skills like data wrangling so much of the time, we were importing manually and entering information into the sheet by hand. On top of that, we had to familiarize ourselves with many data science concepts like normalizing the data to avoid any form of bias towards some categories versus others.
Regardless of what we get out of this project, all of us are extremely excited to present this to the judges and any user who will see this in the future. Not only is this our first datathon, but our first truly marketable project that we can put out into the world. Doing this as freshmen makes us all excited for the potential range we have for the future, making more projects, and learning more about the vast world that is data science and just about every single thing we can do with it. With this project too, we learned so much on how to make data more understandable and user friendly and how to actually use data we have and we found to implement it in a product that truly is useful and can potentially be seen in the future.
We learned so much. Not only did the entire team attend classes that were being offered by the hosts and sponsored, the hands on experience we got with actually handling and coding to make data presentable was also a time to remember for sure. We learned about how to properly normalize, find, and manipulate data to output for something so simple and also learned to understand the algorithm responsible for making our data output according to the user's preferences.
Even now, as we sit and type this devpost out for the judges to see, we're juggling ideas on how to make Global Connect even better. Our eyes are turned to the future, where we plan on using Global Connect much more for the world of tourism. We plan on adding many categories like accessible geography, restaurant availability, and activities to do that range for all ages so that every type of person can use Global Connect and take something away that will truly aide them in their decisions for the future of their vacations whether it be solo, with a special someone, with friends, or with family.