Prediksi minat studi lanjut menggunakan Algoritma K-Nearest Neighbor

Mubarok, Rizki Akbar (2022) Prediksi minat studi lanjut menggunakan Algoritma K-Nearest Neighbor. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text (COVER)
1_cover.pdf

Download (119kB) | Preview
[img]
Preview
Text (ABSTRAK)
2_abstrak.pdf

Download (47kB) | Preview
[img]
Preview
Text (DAFTAR ISI)
3_daftarisi.pdf

Download (108kB) | Preview
[img]
Preview
Text (BAB I)
4_bab1.pdf

Download (170kB) | Preview
[img] Text (BAB II)
5_bab2.pdf
Restricted to Registered users only

Download (344kB) | Request a copy
[img] Text (BAB III)
6_bab3.pdf
Restricted to Registered users only

Download (307kB) | Request a copy
[img] Text (BAB IV)
7_bab4.pdf
Restricted to Registered users only

Download (1MB) | Request a copy
[img] Text (BAB V)
8_bab5.pdf
Restricted to Registered users only

Download (44kB) | Request a copy
[img] Text (DAFTAR PUSTAKA)
9_daftarpustaka.pdf
Restricted to Registered users only

Download (169kB) | Request a copy

Abstract

INDONESIA : Sistem prediksi memainkan peran penting pada zaman sekarang. Sistem prediksi banyak digunakan saat ini untuk memberikan rekomendasi kepada pengguna berdasarkan preferensi pengguna. Salah satunya ialah untuk melakukan prediksi terkait dengan minat studi lanjut. Masih banyak yang melanjutkan studi tidak sesuai minat belajarnya, karena paksaan atau bahkan masih tidak mengetahui secara pasti minat studinya. Oleh karena itu, tujuan dari penelitian ini adalah untuk memberi rekomendasi minat studi berdasarkan preferensi pengguna. Penelitian ini menggunakan metodologi pengembangan CRISP-DM dan juga Algoritma K-Nearest Neighbor dengan k-value 24 maka dihasilkan akurasi model sebesar 73% dengan distance metric Manhattan menggunakan data training sebanyak 250 sampel data training dengan masing-masing data testing sebanyak 300 sampel data label (Academics), 100 sampel data label (Arts), 155 sampel data label (Sports). Model dibungkus dengan pickle untuk diintegrasikan dengan bagian interface sistem melalui Flask API, Sehingga user dapat menggunakan aplikasi dengan menjawab pertanyaan yang disediakan sistem secara mudah. ENGLISH : Prediction systems play an important role in this day and age. Prediction systems are widely used today to provide recommendations to users based on user preferences. One of them is to make predictions related to interest in further studies. There are still many who continue their studies not according to their learning interests, because of coercion or even they still do not know for sure their study interests. Therefore, the purpose of this study is to provide recommendations for study interest based on user preferences. This study uses the CRISP-DM development methodology as well as the K-Nearest Neighbor Algorithm with a k-value of 24, resulting in a model accuracy of 73% with the Manhattan distance metric using training data of 250 training data samples with each testing data of 300 samples of label data. (Academics), 100 label data samples (Arts), 155 label data samples (Sports). The model is wrapped in a pickle to be integrated with the system interface via the Flask API, so that users can use the application easily.

Item Type: Thesis (Sarjana)
Uncontrolled Keywords: Sistem Prediksi; Confusion matrix; Data Training; Data Testing Algoritma K-Nearest Neighbor; k- value;
Subjects: Data Processing, Computer Science
Mining and Related Operations
Business > Data Processing and Analysis of Business
Computer Arts, Digital Arts
Divisions: Fakultas Sains dan Teknologi > Program Studi Teknik Informatika
Depositing User: Rizki Akbar Mubarok
Date Deposited: 01 Nov 2022 06:12
Last Modified: 01 Nov 2022 06:12
URI: https://digilib.uinsgd.ac.id/id/eprint/60326

Actions (login required)

View Item View Item