Objective: To investigate the prevalence of depressive symptoms and their associated factors among students in Zhejiang Province, so as to provide evidence for targeted prevention strategies. Methods: A stratified cluster random sampling method was used to select 23 829 college students and primary and secondary school students aged 11-22 years in Zhejiang Province from December 2019 to February 2020. Depressive symptoms were assessed using the Center for Epidemiologic Studies Depression Scale (CES-D). Three machine learning algorithms, including Logistic regression, random forest, and eXtreme Gradient Boosting (XGBoost), were applied to construct predictive models, and key associated factors were identified by comparing model performance. Results: The detection rate of depressive symptoms among students in Zhejiang Province was 19.92%; the rates were 17.20% in boys and 22.87% in girls( χ 2=164.89, P <0.05). The CES-D total score was 9.00(4.00,13.00). Multiple Logistic regression analysis revealed that loneliness had the strongest association with depressive symptoms ( AOR =9.58, 95% CI =8.90-10.30), while bullying exposure ( AOR =4.39, 95% CI =4.02-4.80), female students( AOR =1.81, 95% CI =1.68-1.94)，never eating breakfast ( AOR = 2.34，95% CI =2.00-2.67) and overweight/obesity( AOR =1.10，95% CI =1.08-1.12) were significant associated factors of depressive symptoms among students (all P <0.05). Analysis based on the XGBoost model produced highly consistent results, identifying the above 5 factors as the core features with the highest correlation strength (all P <0.05). Conclusions Female, loneliness, bullying exposure, frequency of weekly breakfast and BMI are strongly associated with depressive symptoms among students. Mental health education for high risk groups should be strengthened, and coordinated prevention efforts between families and schools are recommended.