I'm creating a predictive model for closing price of stocks (using neural network and support vector machines.). Is it appropriate to use adjusted prices or unadjusted prices for this prediction purpose? my inputs are technical indicators (+ lags of price) and my output is trend deterministic (1 if we have increase in price and down if we have decrease in price).
Whenever you are looking to estimate total return, you would use adjusted closing prices. If you are strictly looking for the future stock price, you would use unadjusted closing price. I assume, though, that you are looking to predict the value of holding a stock during a given period, so you would want to use adjusted prices. The only time I've used actual closing prices in a model was when a security's value is strictly based on the closing price as of a certain day and ignorant of any dividend payments made. Historical correlation/volatility and estimates of return use adjusted prices.