I am trying to predict category sales for automotive market. The reason I need this variable is because I have been using it in my scoring data-set for a marketing mix model (time series regression model).
In past I have simply used moving average and simple time series mean and median forecasting. But now I need more concrete methodology for prediction as during actualization (scoring after I have the actual category sales values) I have been noticing a lot of deviation.
I have historical category sales from 2013 monthly and I was thinking of downloading data like gas prices, inflation rate, GDP and median income to build a separate regression model for the category sales. Can anyone direct me or suggest a better way.