This study presents a geographic information system (GIS)-based predictive habitat suitability model for the Kentucky arrow darter (Etheostoma spilotum), a fish species of the upper Kentucky River system that is a candidate for federal listing by the U.S. Fish and Wildlife Service. Five habitat factors were identified by experts for modeling the habitat: gradient, canopy coverage, land cover, riparian zone width, and stream order. Using a GIS, values for the five habitat factors were calculated and then combined for all stream segments of the upper Kentucky River system at 100-m intervals. Habitat factor combinations were assigned an overall habitat suitability rating using a weighted calculation system derived through input from aquatic biologists. The resulting model was tested against presence data using locational modeling statistics. A total of 97.33 percent of occurrences were located in the two higher rated categories of habitat suitability. Only two occurrences were located on stream segments of the two lower rated categories of habitat suitability, and neither of these were in the lowest rated category. Whereas model accuracy was high, model precision was moderate, as 61 percent of stream segments were categorized by the model as suitable habitat.