Skip to content

srujanreddyj/M5-Forecasting

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 

Repository files navigation

M5-Forecasting


For detailed insights and visualization of the data, my inferences, modelling, Prediction please visit my BLOG.

Project Goal

  • Learning and Applying data wrangling, data exploration and forecasting methods.
  • Applying various forecasting methods and coming up with better predictions for 28-100 days for all the items in the data.
  • Learn to tell a story and practice various data visualization techniques

Data Source

Data Description

  • WALMART data from three states California, Texas, Wisconsin for three product Foods, household and hobbies.

NOTEBOOKS

  • For EDA - see COLAB

  • LightGBM - This notebook contains the implementation for Boosting technique LightGBM to forecast time-series models.

Conclusion

  • 9 different time-series were explore instead of 42000 time series
  • Different forecasting methods have been experimented and explored.
  • RMSE metric returned about 1.5 - 2.5 for 9 time series models.

Future Scope

  • Explore LSTM, Prophet
  • Explore more time series, finding trend and seasonality between items in the products and combine them to explore more time-series

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published