This repository provides the code for the paper "Improved Sales Time Series Predictions Using Deep Neural Networks with a Dynamic Spatiotemporal Adjustment Mechanism"
We provide processed Cainiao dataset that you can use to slice data as needed. We give the examples to run Cainiao CW1 in python main.py.
Python 3.6.7 and Pytorch 1.8.0
This multivariate time series forecasting framework was implemented based on the following two repositories:
Some codes and design patterns are borrowed from these two excellent frameworks.