NUGROHO, FREDI (2025) PENERAPAN DATA MINING MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR UNTUK MEMPREDIKSI HARGA TELUR AYAM RAS. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (596kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (227kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (304kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (203kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (580kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (191kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (203kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (851kB) |
Abstract
This research aims to analyze the fluctuations in the price of chicken eggs, particularly through the implementation of the K-Nearest Neighbor (KNN) algorithm in data mining to predict the price trends. The primary objectives include determining the effectiveness of KNN in predicting the price of chicken eggs based on data from January 2022 to November 2024, and evaluating the algorithm's accuracy and performance. The study utilizes quantitative methods and statistical analysis to validate the model's prediction accuracy. The data for this study was collected from the National Food Agency (BPN) website, focusing on the egg price data from January 2022 to October 2024. After preprocessing and cleaning the data, the KNN algorithm was applied to predict the price for November 2024. The evaluation of the model's performance involved calculating Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R2). The results showed that the KNN model achieved a high accuracy rate of 94.40%, with an MSE of 3.51 and an MAE of 1.36, indicating low prediction error. However, the R2 score of 0.04 suggests that the model could not fully capture the price variability, highlighting the need for further exploration of additional factors to enhance the prediction model's performance. This study demonstrates the potential of KNN in predicting chicken egg prices while pointing out areas for improvement in the modeling approach. Keywords: Prediction, K-Nearest Neighbor, Chicken Egg, Machine Learning Penelitian ini bertujuan untuk menganalisis fluktuasi harga telur ayam, khususnya melalui penerapan algoritma K-Nearest Neighbor (KNN) dalam data mining untuk memprediksi tren harga. Tujuan utamanya meliputi penentuan efektivitas KNN dalam memprediksi harga telur ayam berdasarkan data dari Januari 2022 hingga November 2024, serta mengevaluasi akurasi dan kinerja algoritma. Studi ini menggunakan metode kuantitatif dan analisis statistik untuk memvalidasi akurasi prediksi model. Data untuk penelitian ini dikumpulkan dari situs Badan Pangan Nasional (BPN), dengan fokus pada data harga telur dari Januari 2022 hingga Oktober 2024. Setelah melakukan pra-pemrosesan dan pembersihan data, algoritma KNN diterapkan untuk memprediksi harga November 2024. Evaluasi kinerja model melibatkan penghitungan Mean Squared Error (MSE), Mean Absolute Error (MAE), dan R-kuadrat (R2). Hasil penelitian menunjukkan bahwa model KNN mencapai tingkat akurasi tinggi sebesar 94,40%, dengan MSE sebesar 3,51 dan MAE sebesar 1,36, menunjukkan kesalahan prediksi yang rendah. Namun, skor R2 0,04 menunjukkan bahwa model tidak dapat sepenuhnya menangkap variabilitas harga, menyoroti perlunya eksplorasi lebih lanjut dari faktor tambahan untuk meningkatkan kinerja model prediksi. Studi ini menunjukkan potensi KNN dalam memprediksi harga telur ayam sambil menunjukkan area untuk perbaikan dalam pendekatan pemodelan. Keywords: Prediksi, K-Nearest Neighbor, Telur ayam ras, Machine Learning
Actions (login required)
 |
View Item |
