Background. Breast cancer is a global health concern and a leading cause of morbidity and mortality among women. Early detection of breast cancer contributes to timely linkage to care and reduction of complications associated with breast cancer. In this context, breast self-examination is helpful to detect breast abnormalities particularly in settings with poor access to healthcare for clinical breast examination and mammography. Thus, all women in such settings are highly encouraged to perform breast self-examination regularly, and shreds of evidences are compulsory in this perspective. In the study setting, there was a scarcity of evidence on breast self-examination. Therefore, this study is aimed at assessing knowledge and practice on breast self-examination and its associated factors among summer class female students of social science at Maraki Campus, University of Gondar, Ethiopia. Methods. An institution-based cross-sectional study was conducted from July 01 to September 15/2018. A total of 398 female summer students were included in the study. A simple random sampling technique was utilized to select the study participants, and interviewer-administered structured questionnaires were employed to collect the data. The data were then entered into Epi info version 7.0, and analysis was done by SPSS version 20.0. A bivariable and multivariable logistic regression model was fitted, and the level of significance was declared based on adjusted odds ratio with its 95% CI and a p value ≤ 0.05. Result. The proportion of students having a good knowledge and practice of breast self-examination was found to be 27.6% (95% CI: 22.9, 32) and 17.4% (95% CI: 13.8, 21.6), respectively. In the multivariable logistic regression analysis, urban residency ( AOR = 2.50 ; 95% CI: 1.27, 4.94) and discussion with someone on breast self-examination ( AOR = 4.57 ; 95% CI: 2.42, 8.65) were predictors of good knowledge, whereas family history of breast cancer ( AOR = 7.14 ; 95% CI: 1.75, 25), discussion with someone on breast self-examination ( AOR = 3.85 ; 95% CI: 1.82, 8.33), and good knowledge on breast self -examination ( AOR = 12.02 ; 95% CI: 5.97, 24.20) had been significantly associated with breast self-examination practice. Conclusion. In this study, the proportion of students with good knowledge and practice towards breast self-examination was lower than most of the studies done so far. The predictors of breast self-examination are related to lack of information. Thus, awareness creation on breast self-examination would be helpful in this context.