perbandingan algoritma Naive Bayes dan K-Nearest Neighbor (KNN) dalam klasifikasi pemilihan program studi - studi kasus Universitas Pelita Harapan Medan

Kusuma, Eric Stanley (2023) perbandingan algoritma Naive Bayes dan K-Nearest Neighbor (KNN) dalam klasifikasi pemilihan program studi - studi kasus Universitas Pelita Harapan Medan. Bachelor thesis, Universitas Pelita Harapan.

Preview	Text (Title) Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (79kB) | Preview
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (237kB) | Preview
Preview	Text (ToC) ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (471kB) | Preview
Preview	Text (Chapter1) Chapter1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (805kB) | Preview
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (185kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (322kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)

Abstract

Choosing the right study program is an important step towards building a successful career and a bright future. Therefore, a machine learning approach designed to assist in making the appropriate selection is needed. This research compares the use of the K-Nearest Neighbor (KNN) and Naïve Bayes methods with datasets derived from UPH Medan intake in 2019 and 2020, focusing on the study programs of information systems or informatics. The study was managed and conducted in Google Colab using the Python programming language. Based on the results of the training and testing data, Naïve Bayes achieved an accuracy of 56.25% for the information systems class, with a precision of 45%, recall of 83%, and an f1-score of 59%. For the informatics class, Naïve Bayes achieved a precision of 80%, recall of 40%, and an f1-score of 53%. On the other hand, K-Nearest Neighbor (KNN) achieved an accuracy of 81.25% for the information systems class, with a precision of 67%, recall of 100%, and an f1-score of 80%. For the informatics class, K-Nearest Neighbor (KNN) achieved a precision of 100%, recall of 70%, and an f1-score of 82%. Based on the performance results, the K-Nearest Neighbor (KNN) algorithm is more suitable for this case./Pemilihan program studi tepat merupakan langkah yang penting untuk membangun karir untuk mencapai kesuksesan dan masa depan yang cerah. Karena itu diperlukan machine learning yang dirancang untuk membantu pemilihan yang tepat. Penelitian ini membandingkan menggunakan metode K-Nearest Neighbor (KNN) dan Naïve Bayes dengan dataset yang berasal dari UPH Medan intake 2019 dan 2020 yang mengambil program studi sistem informasi atau informatika. Penelitian ini dikelola dan dilakukan di Google Colab dengan bahasa Pemrograman Python. Berdasarkan hasil data training dan data testing didapatkan accuracy Naïve Besar sebesar 56,25% pada class sistem informasi dengan precision 45%, recall 83%, f1-score 59% dan class informatika precision 80%, recall 40%, f1-score 53%. Sedangkan accuracy K-Nearest Neighbor (KNN) sebesar 81,25% pada class sistem informasi dengan precision 67%, recall 100%, dan f1-score 80% dan pada class informatika dengan precision 100%, recall 70%, dan f1-score 82%. Dari hasil performa algoritma K-Nearest Neighbor (KNN) lebih cocok digunakan untuk kasus ini.

Actions (login required)

View Item