Python framework for a good neural network for the Makidrakis 5 (M5) competition hosted on Kaggle.

Time series forecasting of retail items

M5 Competition Data

Forest the unit sales of Walmart retail goods for the next 28 days.

The goal of this project is to provide 28-days ahead point forecasts for 30490 various items sold by Walmart.

This repo contains the R language code used for m5 forecasting accuracy. The models used for forecasting are Xgboost, Catboost, Lightgbm and facebook prophet

Data for M5 Walmart Kaggle Competition

Meta-learnng solution using FFORMA for the M5 Uncertainty Forecasting Competition in Kaggle: https://www.kaggle.com/c/m5-forecasting-uncertainty