Optimasi Prediksi Harga Rumah dengan Random Forest dan Optuna Hyperparameter Tuning
DOI:
https://doi.org/10.52436/1.jpti.846Keywords:
House Price Prediction, Hyperparameter Tuning, Optuna, Random ForestAbstract
Prediksi harga rumah merupakan aspek penting dalam pengambilan keputusan investasi di sektor properti. Penelitian ini bertujuan untuk membandingkan beberapa algoritma Machine Learning dan Deep Learning dalam memprediksi harga rumah, serta mengoptimalkan Random Forest Regressor menggunakan Optuna dengan implementasi Tree-structured Parzen Estimators (TPE). Dataset yang digunakan adalah House Price 2023 Dataset dari Kaggle, yang mencakup 168.000 entri data properti di Pakistan. Metodologi penelitian ini meliputi tahap preprocessing data, rekayasa fitur, serta penerapan beberapa algoritma prediksi, yaitu Artificial Neural Networks (ANN) dengan model Feedforward Neural Network, KNeighborsRegressor, Linear Regression, dan Random Forest Regressor. Model-model ini dievaluasi menggunakan metrik MAE, MSE, RMSE, R-squared, dan Akurasi. Random Forest Regressor memberikan hasil terbaik dengan R-squared 0.91 dan Akurasi 91.33%. Untuk meningkatkan performa model, diterapkan optimasi hyperparameter menggunakan Optuna dengan pendekatan TPE yang berbasis Bayesian Optimization. Hasil model yang dioptimalkan mencapai peningkatan performa dengan R-squared 0.92 dan akurasi 91.75%. Hasil ini menunjukkan bahwa optimasi hyperparameter menggunakan Optuna berbasis Bayesian Optimization dapat meningkatkan akurasi prediksi harga rumah yang dapat diaplikasikan dalam analisis investasi properti.
Downloads
References
H. Jiang, "House Price Prediction with Optimistic Machine Learning Methods Using Bayesian Optimization," Proceedings of the 1st International Conference on Data Science and Engineering, vol. 1, pp. 488-496, 2024, doi: 10.5220/0012825400004547.
F. M. Basysyar and G. Dwilestari, "House price prediction using exploratory data analysis and machine learning with feature selection," Acadlore Trans. Mach. Learn., vol. 1, no. 1, pp. 11-21, 2022, doi: 10.56578/ataiml010103.
R. N. T. Siregar, V. Sitorus, and W. P. Ananta, "Analisis Prediksi Harga Rumah di Bandung Menggunakan Regresi Linear Berganda," Journal of Creative Student Research (JCSR), vol. 1, no. 6, pp. 395-404, 2023, doi: 10.55606/jcsrpolitama.v1i6.3038.
L. F. Ihzaniah, A. Setiawan, and R. W. N. Wijaya, "Perbandingan Kinerja Metode Regresi K-Nearest Neighbor dan Metode Regresi Linear Berganda Pada Data Boston Housing," Jambura Journal Probability and Statics, vol. 4, no. 1, pp. 17-29, 2023, doi: 10.34312/jjps.v4i1.18948.
R. Naz, B. Jamil, and H. Ijaz, "Real Estate Price Prediction," International Journal of Innovations in Science & Technology, vol. 6, no. 2, pp. 1031-1044, 2024. [Online]. Available: https://journal.50sea.com/index.php/IJIST/article/view/951
E. Fitri, "Analisis Perbandingan Metode Regresi Linier, Random Forest Regression dan Gradient Boosted Trees Regression Method untuk Prediksi Harga Rumah," Journal of Applied Computer Science and Technology (JACOST), vol. 4, no. 1, pp. 58-64, 2023. [Online]. Available: http://journal.isas.or.id/index.php/JACOST
M. A. Hafizh, Subairi, R. D. Libriawan, N. D. Maulana, and A. M. Rizki, "Prediksi Harga Rumah Di Jabodetabek Menggunakan Metode Artificial Neural Network," Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika, vol. 5, no. 2, pp. 48-55, 2024, doi: 10.31284/j.kernel.2024.v5i2.6806.
Y. Wu and J. Feng, "Development and Application of Artificial Neural Network," Springer Nature Link, vol. 102, pp. 1645-1656, 2017, doi: 10.1007/s11277-017-5224-x.
T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, "Optuna: A Next-generation Hyperparameter Optimization Framework," The 25th ACM SIGKDD International Conference, 2019, doi: 10.1145/3292500.3330701.
K. Arai, I. Fujikawa, Y. Nakagawa, T. Momozaki, and S. Ogawa, "Modified Prophet + Optuna Prediction Method for Sales Estimations," International Journal of Advanced Computer Science and Applications (IJACSA), vol. 13, no. 8, pp. 58-63, 2022, doi: 10.14569/IJACSA.2022.0130809.
J. A. Amien, Y. Rizki, and M. A. R. Nasution, "Implementasi ADASYN untuk Imbalance Data pada Dataset UNSW-NB15," Jurnal Computer Science and Information Technology, vol. 3, no. 3, pp. 242-248, 2022, doi: 10.37859/coscitech.v3i3.4339.
A. Tikaningsih, P. Lestari, A. Nurhopipah, I. Tahyudin, E. Winarto, and N. Hassa, "Optuna Based Hyperparameter Tuning for Improving the Performance Prediction Mortality and Hospital Length of Stay for Stroke Patients," Telematika, vol. 17, no. 1, pp. 1-16, 2024, doi: 10.35671/telematika.v17i1.2816.
R. Kausar, F. Iqbal, A. Raziq, N. Sheikh, and A. Rehman, "Enhanced Foreign Exchange Volatility Forecasting using CEEMDAN with Optuna-Optimized Ensemble Deep Learning Model," Sains Malaysiana, vol. 53, no. 9, pp. 3229-3239, 2024. [Online]. Available: https://journalarticle.ukm.my/24507/
U. Ali, "House Prices 2023 Dataset," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/howisusmanali/house-prices-2023-dataset
I. Maulita and A. M. Wahid, "Prediksi Magnitudo Gempa Menggunakan Random Forest, Support Vector Regression, XGBoost, LightGBM, dan Multi-Layer Perceptron Berdasarkan Data Kedalaman dan Geolokasi," Jurnal Pendidikan dan Teknologi Indonesia (JPTI), vol. 4, no. 5, pp. 221-232, 2024, doi: 10.52436/1.jpti.470.
B. Nugroho and A. Denih, "Perbandingan Kinerja Metode Pra-Pemrosesan Dalam Pengklasifikasian Otomatis Dokumen Paten," Jurnal Ilmiah Ilmu Komputer dan Matematika, vol. 17, no. 2, pp. 381-387, 2020, doi: 10.33751/komputasi.v17i2.2148.
Y. Ozaki, Y. Tanigaki, S. Watanabe, M. Nomura, and M. Onishi, "Multiobjective Tree-Structured Parzen Estimator," Journal of Artificial Intelligence Research, vol. 73, pp. 1209-1250, 2022, doi: 10.1613/jair.1.13188.
