CD Skripsi

Perbandingan Algoritma K-Nearest Neighbor Dan Random Forest Dalam Memprediksi Laju Pertumbuhan Ekonomi Kabupaten/Kota Pulau Sumatera

---

Sumatra Island is the third largest island in Indonesia. The potential for economic growth in various regencies/cities on this island is enormous, driven by leading sectors such as mining, agriculture, plantations, and tourism. However, from 2019 to 2023, the economic growth rate of regencies/cities in Sumatra experienced fluctuations, indicating that the community and government were not yet ready to increase the economic growth rate. This study aims to obtain the best method for predicting the economic growth rate of regencies/cities in Sumatra by comparing the K-Nearest Neighbor (KNN) and Random Forest algorithms. The data used in this study is data that affects the economic growth rate of regencies/cities in Sumatra from 2019 to 2023, taken from the Central Statistics Agency (BPS) of regencies/cities in Sumatra. The results obtained from this study are that Random Forest is the best algorithm for predicting the economic growth rate of regencies/cities in Sumatra. This is based on the Random Forest's ability to capture patterns in data quite well, namely relatively stable fluctuations around the average value, while KNN produces predicted values that are far from the actual values. This is supported by the value of the Mean Absolute Percentage Error (MAPE) prediction accuracy in the best Random Forest model, which is included in the category of fairly good forecasting with a MAPE value of 25.56%, so the accuracy is 74.44%.
Keywords: Economic growth rate, Prediction, K-Nearest Neighbor, Random forest, Mean Absolute Percentage Error.

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2003113645

Penerbit

Pekanbaru : Universitas Riau FMIPA Statistika., 2024

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2003113645

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

STATISTIKA

Info Detail Spesifik

-

Pernyataan Tanggungjawab

mardiah

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar