Store Sales Forecasting

Overview

This repository contains my solution for the Kaggle competition Store Sales - Time Series Forecasting. The competition involved predicting sales for the thousands of product families sold at different Favorita stores located in Ecuador.
My solution achieved an RMSLE score of 0.4453 on the test set. You can view my Kaggle notebook solution here.

How to run

Clone the repository

git clone https://github.com/N0-Regrets/Store-Sales-Forecasting.git
cd Store-Sales-Forecasting

Make you sure you have these dependencies installed.

pip install pandas
pip install numpy
pip install scikit-learn
pip install xgboost
pip install plotly
pip install optuna

You should be able to run the notebook using Visual Studio Code or any IDE that supports Jupyter Notebooks, e.g. Spyder.