1
$\begingroup$

My task is 'unemployment forecasting'. I have data with monthly ammount of unemployed. First as I do was : simple exp smoothing, holt's method, Holt-Winters method, ARMA model. All this models take only 1 series and build prediction based only on historical data.

Now I need to forecast unemployment using such data as unemployment benefits, gross domestic product, Consumer price index, etc.

example of dataset: enter image description here

My scientific adviser suggest to use neural network. But I dont think that it will do good forecasts (because of small amount of features).

What methods (which based not only on 1 column, but on all predictors) can I use for forecasting?

$\endgroup$
1
$\begingroup$

I'd review the chapter here: https://www.otexts.org/fpp/9/1

Neural networks require extreme amounts of data and many more features than you have for them to typically outperform other time series methods.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.