Objectives: Because of rapid population aging, cognitive decline and dementia in the older population are recognized as major public health problems. The purpose of this study was to identify demographic, behavioral, medical, and genetic factors associated with cognitive decline, and to develop a model that can predict cognitive decline. Methods: Data for community-dwelling people aged 65 years and older were obtained from the Gyeonggi Dementia and Mild Cognitive Impairment Study (GDEMCIS). Cognitive decline was defined using the random slope and intercept linear mixed model. Those demonstrating a change in the slope of less than 0 were defined as decliners. Data mining such as decision tree and bagging methods were used to develop the prediction model for cognitive decline. Results: Among the subjects, 7.4% showed cognitive decline. Based on the area under the curve the prediction model based on decision tree analysis was selected. In the modeling dataset, 59 (7.4%) showed cognitive decline. The prediction model identified 49 cognitive decliners (6.2%). The correct classification rate of the prediction model was 93.4%. Conclusions: In this study, a prediction model for cognitive decline in community-dwelling older people was developed. The prediction model may provide useful information to healthcare professionals in identifying and monitoring older adults vulnerable to cognitive decline.