AWS DeepAR is a supervised machine learning algorithm for forecasting time series using recurrent neural networks (RNN). The benefits of DeepAR over traditional ARIMA or ETS models are that of its ability to train a single model using multiple time series data sets. The intention is to use this algorithm to train a model using multiple time series data containing the garbage level readings from multiple garbage bins. The trained model will be able to forecast garbage levels into the future and combined with the Smartcity Wastemanagement application, an inovating and more optimized approach to wastemanagment can be implemented.
-
Notifications
You must be signed in to change notification settings - Fork 0
hhamid35/garbage-bin-level-time-series-forecast
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
A time series forecasting ML model to predict garbage bin levels using AWS Sagemaker DeepAR Forcasting Algorithm
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published