top of page



ScoutSync


Football player in black jersey runs with the ball, tackled by player in white and orange. Action on grassy field, intense competition.



This is a server side project. This is a recruitment dashboard where NFL recruiters can search for college football players. The application uses AI methods to provide statistical data about the players.


User dashboard with search bar functoinality and complex filters with double slider, complex units, foot transofmations




Technologies used







What are their services?

WSO provides data science services to athletes and recruiters for the NFL.


For recruiters: they offer web-based software that is connected to a large database with over 30,000 qualified and classified players with Ai methods and growing constantly.


Athletes: Athletes can singup to create a profile, the profile would be approved using AI methods to determine if this is the right candidate.




Video presentation








What did we do?

We developed a web-based software with Django, Ai methods, and a PostgreSQL database


We built a Django backend that classifies players given their statistical stats, the backend runs on machine learning algorithms and defines alike players so recruiters can build a basic set of expectations and the program takes this data to search players with similar stats or potential capabilities based on millions of statistical data computed by the machine learning algorithms.


Subscription system, this allows recruiters to choose a subscription plan that is being paid monthly, or annually.


Ai methods from scratch, no framework was used we built a bespoke solution for our client with their specific needs.


We collaborated with their IT team, to develop the software in a docket container that later on was deployed using GitHub actions directly to the AWS server.


We working in collaboration using Git, GitHub, and GitHub Actions, to build a robust infrastructure to deploy to AWS.



UI/UX slide show


We worked with their UX team to bring to reality the exact interface designed by their team.

Their team shared with us this design using Figma.









Athlete profile


Athlete profile rendered by Django backend on a Velo interface






How does it work?

Recruiters log in to the web-based software via a browser, and recruiters set desired parameters and ranges. Then the recruiter clicks the apply button which sends all the requested data to the Django backend, the backend receives the data processes it, and starts running the machine learning classifier algorithms given the desired parameters and ranges, the system defines alike players, players that don't present certain skills but given millions of computed data have a high probability to develop very specific skills, once everything is computed is sent back to the recruitment user interface where the recruiter can then take further decisions such as analyze more stats or add to their contact list the player







The analytics section in the profile

Analytics are automatically computed by the web-based software that we created.


Athlete profile analytics data has been computed on the Django backend that we built







Website landing page


WSO website screenshot shows athlete-coach connection tools. Features include data analytics, profiles, and a call to action to "Recruit Now."










Athletes application form


WSO Athlete Recruiting Form step 5 of 7, asks about test scores, NCAA/NAIA registration, and future pursuits. Blue accents, Next Step button.


bottom of page