4 Forecasting Time Series Data Using ARIMA and Facebook Prophet Models

Forecasting a parameter of interest in the time series data, based on the past values helps resource optimization in case of sensor networks, or to meet the demand of the society in case of analyzing essential commodity time series data or it helps in better analysis of a company value in near feature based on the revenue generated in the past. Auto Regression Integrated Moving Average (ARIMA) model is used to predict the future value of energy dissipation in case of sensor network, product, sales, share market fluctuation, essential commodity, etc. Facebook Prophet model is launched by Facebook which is an open-source library which can be used to analyze data which shows the variation in trend and seasonality. In this article, the number of passengers using aircraft is predicted using the ARIMA model and the Facebook Prophet model. Both the model performs well for the data considered and in ARIMA model, choosing the fundamental parameter for analysis of the data is challenging as compared to Facebook Prophet model as the latter uses in-built library function to ease the task.