{ "article_id": 1467, "public_id": "77da6800-d831-485c-afa5-9ab6b3a9caa6", "internal_identifier": null, "source_identifier": "90:16", "status": "published", "type": "research_article", "title": "Yurtta Barınan Öğrencilerin Ayrılma Sebeplerinin Veri Madenciliği Yöntemleriyle Analiz Edilmesi", "title_secondary": null, "abstract": "Ülkemizde Üniversite öğrencilerinin büyük bir bölümü öğrenim hayatlarının bir döneminde devlet yurtlarında kalmaktadır. Bu çalışmanın amacı, Kredi ve Yurtlar Genel Müdürlüğü (KYGM)’nde barınan öğrencilerin; yurttan ayrılma sebeplerinin veri madenciliği yöntemleriyle analiz edilmesidir. Yapılan analizler sonucunda yurt şartlarının iyileştirilmesi veya sosyal ortamın düzenlenmesi için öneriler sunulması, ayrılma nedenleri ve barınan öğrencilerin çeşitli özellikleri analiz edilerek; ayrılması baştan öngörülen öğrencilerin yurt başvuru ve yerleştirme kriterlerinin yeniden gözden geçirilmesinin sağlanmasıdır. İlk olarak veri ön işleme ve öznitelik analizi gerçekleştirilmiştir. Öznitelik seçimi, bilgi kazancı ve korelasyon öznitelik sıralama filtresi kullanılarak yapılmıştır. Modellerin aşırı uyumunu önlemek için eğitim seti üzerinde k-katlı çapraz doğrulama kullanılarak, veri setine popüler tahmin modelleri olan; lojistik regresyon, naive bayes, destek vektör makinesi, karar ağaçları, KNN, ANN vb. uygulanmıştır. Önerilen kayıp tahmin modeli; doğruluk, kesinlik, hatırlama, f-ölçüsü ve karar verici etkinliği (ROC) alanı gibi metrikler kullanılarak değerlendirilmiştir. En başarılı sonuçları; Karar Tablosu (DecisionTable) algoritması %86,95 doğruluk ve %89 ROC alanı, Adaboost algoritması  %86,93 doğruluk ve %89 ROC alanı ve Karar Kütüğü (Decision Stump) algoritmasın %86,93 doğruluk ve %85 ROC alanı ile göstermiştir.", "language": "tr", "english_title": "Analysis of Reasons for Student Departure from State Dormitories Using Data Mining Methods", "english_abstract": "In our country, a large number of university students stay in state dormitories for a period of their education. The aim of this study is to analyze the reasons for students leaving the dormitories of the General Directorate of Student Loans and Dormitories (KYGM) using data mining methods. The results of the analyses aim to provide suggestions for improving dormitory conditions or organizing the social environment, and to ensure a revision of dormitory application and placement criteria for students whose departure is predicted from the outset, by analyzing the reasons for departure and various characteristics of the students residing there. First, data preprocessing and feature analysis were performed. Feature selection was done using information gain and correlation feature ranking filters. To prevent overfitting of the models, k-fold cross-validation was used on the training set, and popular prediction models such as logistic regression, naive Bayes, support vector machine, decision trees, KNN, ANN, etc., were applied to the dataset. The proposed loss prediction model; The algorithms were evaluated using metrics such as accuracy, precision, recall, f-measure, and decision-maker efficiency (ROC). The most successful results were shown by the DecisionTable algorithm with 86.95% accuracy and 89% ROC, the Adaboost algorithm with 86.93% accuracy and 89% ROC, and the Decision Stump algorithm with 86.93% accuracy and 85% ROC.", "doi": "10.36287/setsci.6.1.027", "doi_url": "https://doi.org/10.36287/setsci.6.1.027", "resource_url": "https://www.set-science.com/a/77da6800-d831-485c-afa5-9ab6b3a9caa6", "pdf_url": "https://www.set-science.com/a/77da6800-d831-485c-afa5-9ab6b3a9caa6/pdf", "og_image": "https://www.set-science.com/assets/img/og-card-v2.png", "authors": [ { "public_id": "54d97492-2419-4809-b59d-d0bff451d241", "given": "Berrin", "family": "Değirmenci", "full": "Berrin Değirmenci", "literal": null, "orcid": null, "orcid_url": null, "email": "berrin.degirmenci@gazi.edu.tr", "corresponding": true, "sequence": "first", "affiliations": [ { "name": "Gazi Üniversitesi", "department": null, "country": null, "country_code": null, "ror": null, "ror_url": null } ] }, { "public_id": "6e40a9e5-459f-43f2-a29b-106fec51c1b8", "given": "Oktay", "family": "Yıldız", "full": "Oktay Yıldız", "literal": null, "orcid": null, "orcid_url": null, "email": "oktyildiz@gmail.com", "corresponding": false, "sequence": "additional", "affiliations": [ { "name": "Gazi Üniversitesi", "department": null, "country": null, "country_code": null, "ror": null, "ror_url": null } ] } ], "keywords": [ "Yurt Memnuniyeti", "Sınıflandırma", "Kümeleme", "Makine Öğrenmesi", "Veri Madenciliği" ], "translations": [ { "language": "en", "title": "Analysis of Reasons for Student Departure from State Dormitories Using Data Mining Methods", "abstract": "In our country, a large number of university students stay in state dormitories for a period of their education. The aim of this study is to analyze the reasons for students leaving the dormitories of the General Directorate of Student Loans and Dormitories (KYGM) using data mining methods. The results of the analyses aim to provide suggestions for improving dormitory conditions or organizing the social environment, and to ensure a revision of dormitory application and placement criteria for students whose departure is predicted from the outset, by analyzing the reasons for departure and various characteristics of the students residing there. First, data preprocessing and feature analysis were performed. Feature selection was done using information gain and correlation feature ranking filters. To prevent overfitting of the models, k-fold cross-validation was used on the training set, and popular prediction models such as logistic regression, naive Bayes, support vector machine, decision trees, KNN, ANN, etc., were applied to the dataset. The proposed loss prediction model; The algorithms were evaluated using metrics such as accuracy, precision, recall, f-measure, and decision-maker efficiency (ROC). The most successful results were shown by the DecisionTable algorithm with 86.95% accuracy and 89% ROC, the Adaboost algorithm with 86.93% accuracy and 89% ROC, and the Decision Stump algorithm with 86.93% accuracy and 85% ROC.", "keywords": [ "Student Satisfaction", "Classification", "Clustering", "Machine Learning", "Data Mining" ] } ], "subjects": [], "subject_names": [], "published_date": "2023-12-29", "published_year": "2023", "received_date": null, "accepted_date": null, "volume": "15", "issue": null, "page_first": "76", "page_last": "80", "article_number": null, "conference": { "short_name": "BMYZ2023", "full_title": "Cognitive Models and Artificial Intelligence Conference", "name": "Cognitive Models and Artificial Intelligence Conference", "acronym": "BMYZ2023", "location": "Ankara, Türkiye", "start_date": "2023-10-26", "end_date": null, "public_id": "dc3a47c3-f4b3-4059-b610-f99aca33d7a0" }, "proceedings": { "title": "Cognitive Models and Artificial Intelligence Conference", "series_title": "SETSCI Conference Proceedings", "publisher": "SET Technology", "isbn": "978-605-69925-7-5", "eisbn": null, "issn": null, "eissn": "2687-5527", "doi": null, "doi_prefix": "10.36287", "slug": "setsci-volume-15-2023-legacy-90", "public_id": "33fc699d-0ab3-4057-b2e0-644dc89f900d", "url": "https://www.set-science.com/p/setsci-volume-15-2023-legacy-90" }, "license": { "name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "code": "CC-BY-4.0", "open_access": true }, "copyright": { "holder": "SET Technology", "year": "2023" }, "funding_statement": null, "funders": [], "references": [ { "order": 1, "raw": "E. Kavuncu, “Türkiye’de Üniversitelerde Öğrenci-Yurt Hizmetleri ve Barınma Sorunu”, Eğitim-Öğretim ve Bilim Araştırma Dergisi, sayı:30,pp. 48-50, 2014.\r\n\r\nP. Frijters et al., “Heterogeneity in peer effects in random dormitory assignment in a developing country”, Journal of Economic Behavior and Organization, 163, pp.117-134,2019.\r\n\r\nN. Perach et al. “Stable matching of student-groups to dormitories”, European Journal of Operational Research, 302 (1) , pp.50-61, 2022.\r\n\r\nÖ. Kökalan et al., “Measurement of Service Quality in Public and Private/Foundation University Dormitories: Comparison of Turkish and Foreign Students”, Yüksek Öğretim Dergisi, 9(3), pp.263-278, 2019\r\n\r\nI. Ullah et al., “A Churn Prediction Model Using Random Forest: Analysis of Machine Learning Techniques for Churn Prediction and Factor Identification in Telecom Sector”, IEEE Access, vol:7, pp: 60134 – 60149, 2019.\r\n\r\nA. De Caigny et al., “A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees”, European Journal of operational research, vol:269 (2), pp.760-772,2018.\r\n\r\nTianpei Xu. et al., “Telecom Churn Prediction System Based on Ensemble Learning Using Feature Grouping”, Applied Sciences-Basel, 11(11), doi: 10.3390/app11114742, 2021.\r\n\r\nA. Amin et al., “Customer churn prediction in the telecommunication sector using a rough set approach”, Neurocomputing, vol:237, pp.242-254, 2017.\r\n\r\nS. Wu et al., “Integrated Churn Prediction and Customer Segmentation Framework for Telco Business”, IEEE ACCESS, Vol. 9, 62118-62136, 2021.\r\n\r\nF. Usman-Hamza et al., “Intelligent Decision Forest Models for Customer Churn Prediction”, Applied Sciences, Vol. 12,8270, 2022.\r\n\r\nP. Lalwani et al. “Customer churn prediction system: a machine learning approach”, Computing, Vol. 104, No:2, pp.271-294,2021.\r\n\r\nD. Al-Najjar et al., “Machine Learning to Develop Credit Card Customer Churn Prediction”, Journal of Theoretical and applied electronic commerce research, Vol. 17, Issue:4,pp:1529-1542,2022\r\n\r\nP. Mishra et al., “A Detailed Investigation and Analysis of Using Machine Learning Techniques for Intrusion Detection”, IEEE Communications Surveys & Tutorials, vol.21(1), pp. 686-728,2019\r\n\r\nH. Uğuz, “A two-stage feature selection method for text categorization by using information gain, principal component analysis and genetic algorithm”, Knowledge-Based Systems, Vol:24, pp:1024-1032,2011\r\n\r\nK. Niu et al., “A Developed Feature Selection Method for Classification Based on United Information Gain”, 2017 IEEE Smartworld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet Of People And Smart City Innovation (Smartworld/Scalcom/Uic/Atc/Cbdcom/Iop/Sci),2017\r\n\r\nAM. Kowshalya et al., “Correlation Based Feature Selection Algorithms for Varying Datasets of Different Dimensionality”, Wireless Personan Communications, Vol.108, pp:1977-1993, 2019\r\n\r\nA. Çınar, “Performance Evaluation Of Classification Algorithms In Data Mining And An Application With The R Language”, Marmara Üniversitesi Öneri Dergisi, vol. 14(51), pp. 90-111,2019\r\n\r\nS. Uddin et al. (2019), “Comparing different supervised machine learning algorithms for disease prediction”, BMC Medical Informatics and Decision Making, 19(1), 2019\r\n\r\nTM. Rausch et al., “Predicting online shopping cart abandonment with machine learning approaches”, International Journal of Market Research, Vol:64, pp:89-112, 2022.\r\n\r\nC. Cortes and V. Vapnik, Support-Vector Networks. Machine Learning, 20, 273-297. http://dx.doi.org/10.1007/BF00994018,1995", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null } ], "statements": { "acknowledgements": null, "conflict_of_interest": null, "data_availability": null, "ai_disclosure": null }, "credit": [], "history": { "published": "2023-12-29" } }