3 Ways for Multiple Time Series Forecasting Using Prophet in Python
Train and predict multiple time series using for-loop, multi-processing, and PySpark
Multiple time series forecasting refers to training many time series models and making predictions. For example, if we would like to predict the sales quantity of 10 products in 5 stores, there will be 50 store-product combinations, and each combination is a time series. Using the multiple time series model, we can train and predict the 50 time series model at the same time. Another example is to predict multiple stock prices at the same time.
In this tutorial, we will predict the stock prices of five tech companies using Prophet. Three ways of running multiple time series forecasting will be demonstrated. You will learn:
- How to run multiple time series forecasting using for loop?
- How to set up multi-processing and utilize all the cores on a computer to run multiple time series models?
- How to set up PySpark to run multiple time series forecasting in parallel?
If you are not familiar with Prophet, please check out my previous tutorial Time Series Forecasting Of Bitcoin Prices Using Prophet and Multivariate Time Series Forecasting with Seasonality and Holiday Effect Using Prophet in Python.
