PURPOSE: Few studies have explored whether accelerometer-measured sedentary behavior increases cancer risk. We examined the associations of accelerometer-measured daily sitting time and mean sitting bout duration classified by the Convolutional Neural Network Hip Accelerometer Posture (CHAP) machine-learned algorithm with incidence of any cancer, incidence of 13 physical activity-related cancers, and cancer mortality among postmenopausal women. METHODS: We used data from 22,097 women (mean age = 73.3 years, standard deviation [SD] = 6.7) in the Women's Health Accelerometry Collaboration, a consortium of two US-based cohort studies of postmenopausal women: the Women's Health Study and the Women's Health Initiative Objective Physical Activity and Cardiovascular Health Study. Women who completed hip-worn triaxial accelerometry for ≥ 4 of 7 consecutive days were included. Associations between sedentary behaviors and physician-adjudicated invasive cancer incidence and mortality were tested using Cox regression. RESULTS: Women were followed on average 8.0 years to identify cancer cases (n = 1,861) and deaths (n = 601). Overall, mean sitting time was 567 (SD = 113) min/day and mean sitting bout duration was 12.8 (SD = 4) min/bout. In covariate-adjusted models, one-SD increment higher in sitting time was associated with a 6% increased risk of incident cancer (hazard ratio [HR] = 1.06, 95% CI: 1.01-1.11); associations were similar for bout duration (HR = 1.05, 95% CI: 1.00-1.10). Estimates were similar for the 13 physical activity-related cancers (sitting time: HR = 1.10, 95% CI: 1.04-1.17; bout duration: HR = 1.08, 95% CI: 1.02-1.14) and for cancer mortality (sitting time: 1.06, 95% CI: 0.98-1.16; bout duration: HR = 1.05, 95% CI: 0.97-1.13). CONCLUSION: Among postmenopausal women, sedentary behavior was associated with increased cancer risk, particularly for physical activity-related cancers and cancer mortality.