Penerapan Algoritma K-Nearest Neighbour (K-Nn) Untuk Penentuan Mahasiswa Berpotensi Drop Out

Ratniasih, Ni Luh

doi:10.36002/jutik.v5i3.804

Cited by 5 publications

(4 citation statements)

References 2 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Evaluation using confusion matrix [31] concluded that modeling the kNN algorithm using unnormalized data, with values k=5, the system was only able to correctly classify 15 data from 17 data, with an accuracy of 88.24%, an average precision of each class of 89.17% and an average class recall value of 89.17% as seen in Meanwhile, modeling with data that has been normalized using the Z-Score technique, the system was able to classify 16 data from 17 test data with an accuracy of 94.12%, an average precision of each class of 94.44%, and a class recall value of 95.83% as seen in the Table 7. Comparison of modeling performance using normalization and without normalization, as shown in…”

Section: Evaluation Of Modeling Resultsmentioning

confidence: 99%

Determining Eligible Villages for Mobile Services using K-NN Algorithm

2023

View full text Add to dashboard Cite

To maximize and get population document services closer to the community, the Disdukcapil district of Alor provides mobile services by visiting people in remote villages which difficult-to-reach service centres in the city. Due to a large number of villages and limited time and costs, not all villages can be served, so the kNN algorithm is needed to determine which villages are eligible to be served. The criteria used in this determination are village distance, difficulty level, and document ownership (Birth Certificate, KIA, family card, and KTPel). The classes that will be determined are "Very eligible", "Eligible", and "Not eligible". By applying Z-Score normalization with the value of K=5, the classification gets 94.12% accuracy, while non-normalized only gets 88.24% accuracy. Thus, applying normalization to training data can improve the kNN algorithm's accuracy in determining eligible villages for "ball pick-up" or mobile services.

show abstract

Section: Evaluation Of Modeling Resultsmentioning

confidence: 99%

Determining Eligible Villages for Mobile Services using K-NN Algorithm

2023

View full text Add to dashboard Cite

show abstract

“…Terdapat beberapa penelitian terdahulu terkait dengan klasifikasi mahasiswa drop out. Salah satunya pada penelitian [2] yang mengklasifikasikan mahasiswa berpotensi drop out di ITB STIKOM Bali, atribut yang digunakan adalah jenis kelamin, umur, agama, status kelas, kerja praktek dan nilai IPK menggunakan algoritma K-Nearest Neighbour (KNN) dan C4.5 dengan nilai akurasi sebesar 81.50% dan 80.54%. Penelitian [3] melakukan prediksi kelulusan mahasiswa di Universitas Telkom menggunakan metode Naive Bayes menghasilkan accuracy sebesar 73.225%, precision 0.742, recall 0.736 dan F-measure 0.735.…”

Section: Pendahuluanunclassified

Klasifikasi Status Drop Out Mahasiswa Menggunakan Naïve Bayes dengan Seleksi Fitur Information Gain

Ulinnuha,

Fanani

2023

View full text Add to dashboard Cite

Salah satu masalah dalam perguruan tinggi adalah kasus drop out. Banyaknya mahasiswa yang mengalami drop out merupakan salah satu indikator yang mempengaruhi kualitas pembelajaran dan akreditasi yang sangat penting untuk keberlangsungan suatu institusi. Penelitian ini menerapkan algoritma Naive Bayes dan algoritma seleksi fitur Information Gain untuk melakukan klasifikasi mahasiswa drop out. Hasil penelitian menunjukkan bahwa dua fitur yang berpengaruh paling signifikan terhadap klasifikasi mahasiswa drop out adalah jumlah SKS yang ditempuh dan nilai IPS pada semester 4. Temuan ini menunjukkan bahwa aspek akademik yang terkait dengan perkembangan studi mahasiswa berpengaruh dalam klasifikasi drop out. Penerapan seleksi fitur menggunakan metode Information Gain berhasil meningkatkan akurasi dan presisi dari model Naïve Bayes. Model yang dihasilkan mencapai akurasi sebesar 98.36%, presisi sebesar 88.37%, dan recall sebesar 97.44%. Hasil ini menunjukkan bahwa seleksi fitur dengan metode Information Gain membantu dalam mengidentifikasi fitur-fitur penting yang berkontribusi terhadap kualitas model klasifikasi.

show abstract

“…Selain itu, untuk mengetahui atribut/faktor yang paling mempengaruhi terhadap ketepatan masa studi mahasiswa, diperlukan fitur seleksi atribut dengan menggunakan Forward Selection. Fitur ini mampu meningkatkan akurasi dengan membuang beberapa fitur yang kurang relevan terhadap proses klasifikasi [9]. Data yang digunakan yaitu data mahasiswa lulusan tahun 2015-2019 dari 3 program studi yaitu Teknik Informatika, Teknik Sipil dan Teknik Industri ITG.…”

Section: Pendahuluanunclassified

Implementasi Algoritma Naïve Bayes Menggunakan Feature Forward Selection dan SMOTE Untuk Memprediksi Ketepatan Masa Studi Mahasiswa Sarjana

Kurniadi

Nuraeni

Lestari

2022

JSC

View full text Add to dashboard Cite

The punctuality of students in completing their studies is an important aspect of the study program. Because there are still students who have not been able to complete their studies on time. The purpose of this study is to determine the factors that influence students in completing their studies by extracting student academic data to obtain a classification model that can be used to predict the accuracy of the study period. The classification method for predicting the accuracy of the student's study period uses the Naive Bayes algorithm using the Feature Forward Selection and SMOTE. The method for data processing in this study uses CRISP-DM. The results of this study are in the form of a classification model to predict the accuracy of the study period of students who obtain a fairly high accuracy value of 87.13%, a recall value of 83.82%, and a precision value of 89.76%, and an AUC value of 0.92. included in the category of Excellent Classification. The use of SMOTE has succeeded in handling Imbalanced Class on the data, and the application of Feature Forward Selection resulted in 5 factors that most influence the accuracy of the student's study period, namely the attributes of Gender, School Category, Year of Entry, Study Program and Grade Point Average for the third semester. The prediction model generated using the Naïve Bayes algorithm, Feature Forward Selection, and SMOTE is expected to help study programs to find out earlier the possibility of students completing their studies on time or not on time.

show abstract

Penerapan Algoritma K-Nearest Neighbour (K-Nn) Untuk Penentuan Mahasiswa Berpotensi Drop Out

Cited by 5 publications

References 2 publications

Determining Eligible Villages for Mobile Services using K-NN Algorithm

Determining Eligible Villages for Mobile Services using K-NN Algorithm

Klasifikasi Status Drop Out Mahasiswa Menggunakan Naïve Bayes dengan Seleksi Fitur Information Gain

Implementasi Algoritma Naïve Bayes Menggunakan Feature Forward Selection dan SMOTE Untuk Memprediksi Ketepatan Masa Studi Mahasiswa Sarjana

Contact Info

Product

Resources

About