This paper presents short-term forecasting model for crude oil prices based on three layer feedforward neural network. Careful attention was paid on finding the optimal network structure. Moreover, a number of features were tested as an inputs such as crude oil futures prices, dollar index, gold spot price, heating oil spot price and S&P 500 index. The results show that with adequate network design and appropriate selection of the training inputs, feedforward networks are capable of forecasting noisy time series with high accuracy. © 2008 IEEE.