Who has the best proton NMR crystal ball?

The debate about the appropriate program for predicting NMR spectroscopy is going on. One approach which seems to deliver good results is parameterization using functional group identification and information on the 3D structure of the compound to be predicted. The long-standing rule-based approach of Professor Ernö Pretsch of the ETH Zurich, Switzerland, is widely used for 'H NMR and other spectra prediction software packages. This approach draws on analyzing reference chemical shift values from the peer-reviewed literature, assigning a core value and functions by modifying a base proton chemical shift value for a substructure in a particular environment by various amounts depending on the location of neighboring functional groups. The combined approach is capable of producing improved proton NMR predictions for the data set.