Inspiration
Getting hands-on experience working with a real dataset and solving a common problem.
What it does
It gives the likelihood of intense purchasing seasons through the year, and predicts costs for the year 2023. It also optimises shipments by grouping demanded products by available packaging options and hospitals.
How we built it
We developed an algorithm on python that estimates high-demand regions throughout the year. Then, we used R and Shiny App to employ the ETS, Auto.Arima and Prophet models to predict the 2023 time series.
Challenges we ran into
Creating a Shiny App application from scratch, working with such a big and varied dataset.
Accomplishments that we're proud of
An overall sound and informative model. We are able to give firm results.
What we learned
We learned how to implement code with python, R, the models we learned, and especially managing time.
What's next for Agenda 2023
Perfecting the models with bigger datasets and greater precision.
Log in or sign up for Devpost to join the conversation.