This systematic literature review (SLR) explores the application of data mining (DM) and machine learning (ML) in gynecologic oncology (GYN oncology). The review aims to assess the depth and breadth of DM literature in GYN malignancies over the past decade, with a focus on ML-based approaches. The study was conducted in compliance with Kitchenham and Charters' guidelines and PRISMA guidelines, and no ethical approval was required as it involved published articles. The review searched five digital libraries: PubMed, IEEE Xplore, ScienceDirect, SpringerLink, and Google Scholar, for articles published between January 1, 2011, and February 28, 2022. A total of 3499 potential records were identified, and 181 primary studies were eligible for in-depth analysis. The majority of the selected articles (93.92%) were published in journals, with computer science - AI, obstetrics/GYN, and biomedical informatics being the most common disciplines. The most studied GYN site-derived neoplasm was cervical cancer (57.6%), followed by ovarian, tubal, and peritoneal neoplasms (24.9%), and uterine neoplasms (15.1%). The most common empirical schemes were solution proposals (84.2%) and evaluation research (84.2%). The most prevalent data modalities used were medical imaging (58.3%), and neural networks (NNs) were the most commonly implemented DM-ML technique, followed by support vector machines (SVM), random forests (RF), and k-nearest neighbors (k-NN). The review highlights the need for more clinical validation of DM-ML models in GYN oncology, as most studies were solution proposals. The scarcity of validation research (5 articles) and the lack of data sharing and interoperability are significant challenges. The review also discusses the potential of DM-ML in improving diagnostic accuracy, reducing invasiveness, and enabling early detection in GYN oncology.This systematic literature review (SLR) explores the application of data mining (DM) and machine learning (ML) in gynecologic oncology (GYN oncology). The review aims to assess the depth and breadth of DM literature in GYN malignancies over the past decade, with a focus on ML-based approaches. The study was conducted in compliance with Kitchenham and Charters' guidelines and PRISMA guidelines, and no ethical approval was required as it involved published articles. The review searched five digital libraries: PubMed, IEEE Xplore, ScienceDirect, SpringerLink, and Google Scholar, for articles published between January 1, 2011, and February 28, 2022. A total of 3499 potential records were identified, and 181 primary studies were eligible for in-depth analysis. The majority of the selected articles (93.92%) were published in journals, with computer science - AI, obstetrics/GYN, and biomedical informatics being the most common disciplines. The most studied GYN site-derived neoplasm was cervical cancer (57.6%), followed by ovarian, tubal, and peritoneal neoplasms (24.9%), and uterine neoplasms (15.1%). The most common empirical schemes were solution proposals (84.2%) and evaluation research (84.2%). The most prevalent data modalities used were medical imaging (58.3%), and neural networks (NNs) were the most commonly implemented DM-ML technique, followed by support vector machines (SVM), random forests (RF), and k-nearest neighbors (k-NN). The review highlights the need for more clinical validation of DM-ML models in GYN oncology, as most studies were solution proposals. The scarcity of validation research (5 articles) and the lack of data sharing and interoperability are significant challenges. The review also discusses the potential of DM-ML in improving diagnostic accuracy, reducing invasiveness, and enabling early detection in GYN oncology.