The objective of this study was to construct a predictive model to identify aged care residents at risk of future skin tears. Extensive data about individual characteristics, skin characteristics, and skin properties were gathered from 173 participants at baseline and at 6 months. A predictive model, developed using multivariable logistic regression, identified five variables that significantly predicted the risk of skin tear at 6 months. These included: a history of skin tears in the previous 12 months (OR 3.82 [1.64-8.90], P = 0.002), purpura ≤20 mm in size (OR 3.64 [1.42-9.35], P = 0.007), a history of falls in the previous 3 months (OR 3.37 [1.54-7.41], P = 0.002), clinical manifestations of elastosis (OR 3.19 [1.38-7.38], P = 0.007), and male gender (OR 3.08 [1.22-7.77], P = 0.017). The predictive model yielded an area under the receiver operating characteristic curve of 0.854 with an 81.7% sensitivity and an 81.4% specificity. This predictive model could inform a simple but promising bedside tool for identifying older individuals at risk of skin tears.