ANALISIS PERBANDINGAN ARTIFICIAL NEURAL NETWORK (ANN) DAN RANDOM FOREST DALAM PREDIKSI HARGA RUMAH

Abid Mafahim, - (2024) ANALISIS PERBANDINGAN ARTIFICIAL NEURAL NETWORK (ANN) DAN RANDOM FOREST DALAM PREDIKSI HARGA RUMAH. S1 thesis, Universitas Pendidikan Indonesia.

	Text S_RPL_2000649_Title.pdf Download (3MB)
	Text S_RPL_2000649_Chapter1.pdf Download (1MB)
	Text S_RPL_2000649_Chapter2.pdf Restricted to Staf Perpustakaan Download (5MB)
	Text S_RPL_2000649_Chapter3.pdf Download (3MB)
	Text S_RPL_2000649_Chapter4.pdf Restricted to Staf Perpustakaan Download (7MB)
	Text S_RPL_2000649_Chapter5.pdf Download (665kB)
	Text S_RPL_2000649_Appendix.pdf Restricted to Staf Perpustakaan Download (2MB)

Abstract

Seiring perkembangan teknologi informasi, penerapan machine learning dalam industri properti rumah, khususnya untuk prediksi harga rumah, menjadi semakin penting dan akurasi pada prediksi yang lebih baik semakin dibutuhkan. Peran teknologi dapat membantu mempercepat dan meningkatkan akurasi dalam proses jual-beli properti. Maka dari itu, peran teknologi machine learning dapat dimanfaatkan untuk memenuhi kebutuhan meningkatkan akurasi prediksi harga rumah di kota besar negara berkembang seperti Kota Bandung. Penelitian ini bertujuan untuk menganalisis efektivitas algoritma Artificial Neural Network dan Random Forest dalam memprediksi harga rumah di Kota Bandung. Data yang digunakan adalah data penjualan rumah di Kota Bandung dengan mencakup luas tanah, luas bangunan, jumlah kamar tidur, jumlah kamar mandi, jumlah tempat parkir, dan lokasi kecamatannya. Analisis algoritma dilakukan dengan membandingkan hasil performa pengujian antara kedua algoritma dengan menggunakan metrik-metrik performa untuk model regresi seperti Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), dan R Square (R2). Selain itu, penelitian ini juga menganalisis rasio data antara data Training, data validasi, dan data uji mana yang memiliki hasil terbaik. Hasil penelitian menunjukkan bahwa model dengan rasio data sebesar 60:20:20 menghasilkan performa yang paling baik pada kedua algoritma. Algoritma Random Forest menunjukkan performa yang lebih unggul dengan hasil MAE: 0.0470; MSE: 0.0079; RMSE: 0.0888; dan R2: 0.7085. --------------- With the advancement of information technology, the application of machine learning in the housing industry, particularly for house price prediction, has become increasingly important, and the need for better accuracy in predictions is growing. Technology plays a crucial role in accelerating and enhancing accuracy in property transactions. Therefore, the role of machine learning technology can be leveraged to meet the demand for improving the accuracy of house price predictions in large cities of developing countries, such as Bandung. This research aims to analyze the effectiveness of the Artificial Neural Network (ANN) and Random Forest algorithms in predicting house prices in Bandung. The data used include house sales data in Bandung, covering land area, building area, number of bedrooms, number of bathrooms, number of parking spaces, and the subdistrict location. The analysis of the algorithms was conducted by comparing the testing performance of both algorithms using regression performance metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R Square (R²). Additionally, this study also analyzed which data ratio among the training, validation, and test data provided the best results. The findings show that a data ratio of 60:20:20 yields the best performance for both algorithms, with the Random Forest algorithm outperforming the ANN with results of MAE: 0.0470, MSE: 0.0079, RMSE: 0.0888, and R²: 0.7085.

Item Type:	Thesis (S1)
Additional Information:	https://scholar.google.com/citations?view_op=new_articles&hl=en&imq=Abid+Mafahim ID Sinta Dosen Pembimbing" Indira Syawanodya: 6681751 Yulia Retnowati: 6852573
Uncontrolled Keywords:	machine learning, prediksi harga rumah, Neural Network, Random Forest, machine learning, house price prediction, Neural Network, Random Forest.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General)
Divisions:	UPI Kampus cibiru > S1 Rekayasa Perangkaat Lunak
Depositing User:	Abid Mafahim
Date Deposited:	11 Sep 2024 03:44
Last Modified:	11 Sep 2024 03:44
URI:	http://repository.upi.edu/id/eprint/121506

Actions (login required)

View Item