Fatigue-related crashes are one of the major threats to road safety worldwide. Despite the substantial work in the domain of transportation science by both the industry and academia, there are few studies in applying case-based reasoning (CBR) approach to modelling the risk of driver fatigue. This research explores the potential for fatigued driving using a database of 16,459 traffic crashes reported from 21 cities in Guangdong province, China from 2006 to 2010. The CBR system under development differentiates between fatigued-driving and non-fatigued-driving cases based on various personal and environmental traffic characteristics. The advantage of using CBR in modelling fatigued driving has been demonstrated through empirical evaluation.