What it does
This project analyzes a dataset containing relevant data on sales of a brewery. It cleans and takes the more relevant data and trains a Neural Network to predict the sales of the following months. We have a API where data can be sent and it will return the predicted data and a frontend app to show this process
How I built it
The Neural Network and cleaning of the data is done in Python using Pandas, Tensorflow and Keras. The API is done in Python using Flask and the frontend is done using HTML-CSS-Javascript and Plotly to plot the charts. We used Tableau to see how the data affected the result.
Challenges I ran into
The data was huge and hard to manipulate and take the relevant parts of it. Also the NN was hard to train because of the same problem.
Accomplishments that I'm proud of
Approaching the relation of the sales and the dates using our predictions.
What's next for #73 - jda
If we had more time we could implement a better NN to have a better prediction.
Predictions can be found on output_data.csv
Log in or sign up for Devpost to join the conversation.