Background Bleeding and thrombosis are both major complications of hospitalization in cancer patients. Concern regarding bleeding risk may reduce compliance with thromboprophylaxis. We assessed incidence of major and clinically relevant non-major bleeding (MCRNMB) and identified risk factors associated with in-hospital bleeding risk in hospitalized cancer patients. Methods We conducted a retrospective cohort study of consecutive adults admitted to general oncology floor at Cleveland Clinic from 11/2012–12/2014 (n = 3525). Patients were excluded for bleeding on admission (n = 108), age < 18 (n = 1), non-malignant disease (n = 2) and incomplete data (n = 56). Data collected included demographics, body mass index (BMI), cancer type, length of stay (LOS), use of anticoagulants and baseline laboratory values (+ 48 h). Univariate risk factors were identified with logistic regression analysis. Multivariable risk factors were identified with stepwise logistic regression and confirmed with bootstrap analysis. Results The study population comprised 3358 patients of whom 69 (2.1%) developed MCRNMB. Median age was 62 (range, 19–98) years and 56% male. Median length of stay was 5 (range, 0–152) days. The majority of bleeding events were either gastrointestinal (GI) (N = 23, 33%) or retroperitoneal (N = 10, 14%). In multivariable analysis, anemia as the reason for admission (7.78, 95% CI 4.0–15.1, P < 0.001), GI cancer site (2.96, 95% CI 1.7–5.2 P < 0.001), BMI ≥ 40 (3.08, 95% CI 1.3–2.9, P = 0.008) and thrombocytopenia (1.7, 95% CI 1.0–2.9, P = 0.05) were predictive. Conclusion The incidence of MCRNMB in a population of hospitalized cancer patients was 2.1%. Risk factors at admission included type of cancer and morbid obesity. Improved prediction of bleeding risk can assist physicians in optimizing selection of thromboprophylaxis in this population that is also at increased risk of VTE.