Sales Forecast (Shops and Stores Net)

This Shiny Web application is available at https://skipper.shinyapps.io/sales_forecast/). It reads and summaries the history of sales, trains a predictive model, and makes a forecast for the chosen number of days. The source of the data is a net of shops and stores SQLite database. Package ‘prophet’ is used to build the model and forecast. This is a very successful procedure which is based on an additive (or multiplicative) model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus (optional) holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data. Prophet is robust to missing data and shifts in the trend, and typically handles outliers well.