ANALISIS PREDIKTIF KLASIFIKASI PROGRAM MAKAN BERGIZI GRATIS MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBORS (KNN) DAN NAIVE BAYES STUDI KASUS DI SMA KEMALA BHAYANGKARI

PUZA JELITA, NPM 2209100104 (2026) ANALISIS PREDIKTIF KLASIFIKASI PROGRAM MAKAN BERGIZI GRATIS MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBORS (KNN) DAN NAIVE BAYES STUDI KASUS DI SMA KEMALA BHAYANGKARI. Skripsi thesis, Universitas Labuhanbatu.

	Text COVER.pdf Download (777kB)
	Text BAB I.pdf Download (233kB)
	Text BAB II.pdf Download (870kB)
	Text BAB III.pdf Download (718kB)
	Text BAB IV.pdf Download (458kB)
	Text BAB V.pdf Download (147kB)
	Text DAFTAR PUSTAKA.pdf Download (139kB)

Abstract

Program Makan Bergizi Gratis merupakan kebijakan pemerintah yang bertujuan meningkatkan kualitas gizi serta mendukung proses pembelajaran siswa, namun efektivitas pelaksanaannya di tingkat sekolah belum sepenuhnya terukur secara objektif karena adanya variasi hasil dan persepsi siswa. Penelitian ini bertujuan untuk mengklasifikasikan tingkat efektivitas Program Makan Bergizi Gratis menggunakan algoritma K-Nearest Neighbors (KNN) dan Naive Bayes serta membandingkan kinerja kedua metode tersebut. Penelitian ini menggunakan pendekatan kuantitatif dengan metode analisis prediktif berbasis klasifikasi, menggunakan data primer yang diperoleh melalui kuesioner terhadap 57 siswa SMA Kemala Bhayangkari Rantauprapat. Variabel penelitian meliputi kehadiran siswa, semangat belajar, persepsi siswa, dan kualitas pelaksanaan program. Data diolah melalui tahapan preprocessing, transformasi, pembagian data dengan rasio 80% data latih dan 20% data uji, modeling, serta evaluasi menggunakan confusion matrix dengan metrik accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma KNN memiliki kinerja yang lebih baik dibandingkan Naive Bayes dengan nilai akurasi sebesar 81,82%, precision 85,71%, recall 85,71%, dan F1-score 85,71%. Temuan ini menunjukkan bahwa pendekatan klasifikasi mampu memberikan gambaran yang lebih objektif dalam menilai efektivitas program berdasarkan kombinasi variabel yang digunakan. Dengan demikian, algoritma KNN dinilai lebih optimal dalam mengklasifikasikan efektivitas program, serta hasil penelitian ini dapat menjadi dasar evaluasi berbasis data bagi pihak sekolah dan pengambil kebijakan dalam meningkatkan kualitas pelaksanaan program secara berkelanjutan. Kata Kunci: Analisis Prediktif, Klasifikasi Efektivitas, Program Makan Bergizi Gratis, K-Nearest Neighbors (KNN), Naive Bayes ================================================================================================== The Free Nutritious Meal Program is a government initiative aimed at improving students’ nutritional status and supporting the learning process; however, its effectiveness at the school level has not been objectively measured due to variations in outcomes and student perceptions. This study aims to classify the effectiveness of the Free Nutritious Meal Program using K-Nearest Neighbors (KNN) and Naive Bayes algorithms and to compare the performance of both methods. This research employs a quantitative approach with a predictive classification method, using primary data collected through questionnaires from 57 students of SMA Kemala Bhayangkari Rantauprapat. The variables include student attendance, learning motivation, student perception, and program implementation quality. The data were processed through preprocessing, transformation, data splitting with an 80:20 ratio for training and testing sets, modeling, and evaluation using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results indicate that the KNN algorithm outperforms Naive Bayes, achieving an accuracy of 81.82%, precision of 85.71%, recall of 85.71%, and an F1-score of 85.71%. These findings demonstrate that a classification-based approach provides a more objective assessment of program effectiveness based on the combination of variables used. Therefore, the KNN algorithm is considered more optimal for classifying program effectiveness, and the results of this study can serve as a data-driven evaluation basis for schools and policymakers to improve the quality of program implementation sustainably. Keywords: Predictive Analysis, Effectiveness Classification, Free Nutritious Meal Program, K-Nearest Neighbors (KNN), Naive Bayes

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Analisis Prediktif, Klasifikasi Efektivitas, Program Makan Bergizi Gratis, K-Nearest Neighbors (KNN), Naive Bayes==============Predictive Analysis, Effectiveness Classification, Free Nutritious Meal Program, K-Nearest Neighbors (KNN), Naive Bayes
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
Divisions:	Fakultas Sains Dan Teknologi > Sistem Informasi
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	24 Apr 2026 07:43
Last Modified:	24 Apr 2026 07:43
URI:	http://repository.ulb.ac.id/id/eprint/2151

Actions (login required)

View Item