The effects of non-native invasive species are costly and environmentally damaging, and resources to slow their spread and reduce their effects are scarce. Models that accurately predict where new invasions will occur could guide the efficient allocation of resources to slow colonization. We assessed the accuracy of a model that predicts the probability of colonization of lakes in Wisconsin by Eurasian watermilfoil (Myriophyllum spicatum). We based this predictive model on 9 years (19901999) of sequence data of milfoil colonization of lakes larger than 25 ha (n =1803). We used milfoil colonization sequence data from 2000 to 2006 to test whether the model accurately predicted the number of lakes that actually were colonized from among the 200 lakes identified as being most likely to be colonized. We found that a lake’s predicted probability of colonization was not correlated with whether a lake actually was colonized. Given the low predictability of colonization of specific lakes, we compared the efficacy of preventing milfoil from leaving occupied sites, which does not require predicting colonization probability, with protecting vacant sites from being colonized, which does require predicting colonization probability. Preventing organisms from leaving colonized sites reduced the likelihood of spread more than protecting vacant sites. Although we focused on the spread of a single species in a particular region, our results show the shortcomings of gravity models in predicting the spread of numerous non-native species to a variety of locations via a wide range of vectors.