Inspiration
Every year thousands of hot dogs are toss into the garbage by Fuel Station Managers due to sanitary restrictions on how much time they are kept warm.
What it does
We developed a machine learning model that helps the store managers to know with time in advance how many hot dogs are they going to sell during that month which would prevent the wastage.
How we built it
We first did EDA of the data, observed the trends, then set out for feature engineering, then we selected the best model which suited our purpose and at last did hyperparameter tuning to get the lowest possible RSME.
Challenges we ran into
We never solved Time Series Forecasting problems in our past, this was our first time doing this. So, we tried using ARIMA model but could not make it work hence we settled with XGBoost.
Accomplishments that we're proud of
We solved a Time Series Forecasting using traditional ML methods.
What we learned
ARIMA model, Time series Forecasting
Log in or sign up for Devpost to join the conversation.