Objective: Current prediction models for advanced age-related macular degeneration (AMD) are based on a restrictive set of risk factors. The objective of this study was to develop a comprehensive prediction model, applying a machine learning algorithm allowing selection of the most predictive risk factors automatically. Design: Two population-based cohort studies. Participants: The Rotterdam Study I (RS-I, training set) included 3838 participants aged 55 years or more, with a median follow-up period of 10.8 years and 108 incident cases of advanced AMD. The ALIENOR study (test set) included 362 participants aged 73 years or more, with a median follow-up period of 6.5 years and 33 incident cases of advanced AMD. Methods: The prediction model used the bootstrap lasso for survival analysis to select the best predictors of incident advanced AMD in the training set. Predictive performance of the model was assessed using the area under the receiver operating characteristic curve (AUC). Main outcome measures: incident advanced AMD (atrophic and/or neovascular), based on standardized interpretation of retinal photographs. Results: The prediction model retained i) age, ii) a combination of phenotypic predictors (based on the presence of intermediate drusen, hyper-pigmentation in one or both eyes and age-related eye disease study (AREDS) simplified score), iii) a summary genetic risk score based on 49 single nucleotide polymorphisms, iv) smoking, v) diet quality, vi) education, and vii) pulse pressure. The cross-validated AUC estimation in RS-I was 0.92 [0.88-0.97] at 5 years, 0.92 [0.90-0.95] at 10 years and 0.91 [0.88-0.94] at 15 years. In ALIENOR, the AUC reached 0.92 at 5 years [0.87-0.98]. In terms of calibration, the model tended to underestimate the cumulative incidence of advanced AMD for the high-risk groups, especially in ALIENOR. Conclusions: This prediction model reached high discrimination abilities, paving the way towards making precision medicine for AMD patients a reality in the near future.