1# RECORD c27bb162a21e02e24af6ca45e7eacffb915471382# TITLE: Application of Multiple Linear Regression Algorithm for House Price Estimation Based on Building Location and Area to Improve Predictive Accuracy in Real Estate Valuation3# YEAR: 2025.0 VENUE: Riau Jurnal Teknik Informatika DOI: 10.30606/rjti.v4i3.39934# AUTHORS: Kecitaan Harefa5# PAGES: 5 CANDIDATE TABLE PAGES (1-based): []6# ABSTRACT: Significant differences in home prices, even on properties with similar building sizes and locations, pose a major challenge in accurately determining property valuations. The discrepancy between the actual market price and the estimated value makes it difficult for potential buyers, sellers, and developers to make the right decision. To overcome these problems, this study applied the Multiple Linear Regression (MLR) algorithm in the Decision Support System (DSS) to estimate house prices based on the location and area of the building. The dataset used consists of 545 housing data points with variables such as house prices, locations, and building areas. The research stages include data collection, pre-processing (data cleaning and normalization), model development using MLR, and model performance evaluation. The evaluation was carried out using the division of trained data and test data with an 80:20 ratio, so that the model was tested using data that was not previously trained. The results showed that the model produced a Mean Absolute Error (MAE) of 1,474,748.13, a Root Mean Squared Error (RMSE) of 1,917,103.70, and a coefficient of determination (R²) of 0.273. A relatively low R² value indicates that the location and area variables of the building are not sufficient to explain the overall variation in house prices, so the addition of other variables—such as the number of rooms, facilities, and environmental conditions—is needed to improve the accuracy of the prediction and produce a more representative price estimate.789===== PAGE 1 (score 9, numeric-paren 0, table-words 1, var-words 7) =====1011Lisensi 12Lisensi Internasional Creative Commons Attribution-ShareAlike 4.0. 13 14436 15 16 17Terbit online pada laman web jurnal: https://journal.upp.ac.id/index.php/rjti/index 18 19 20Vol. 4 No. 3 (2025) 436 – 440 | ISSN: 2829-2529(Media Online) 21Application of Multiple Linear Regression Algorithm for House Price 22Estimation Based on Building Location and Area to Improve Predictive 23Accuracy in Real Estate Valuation 24 25Kecitaan Harefa1 261Teknik Informatika, Fakultas Ilmu Komputer, Universitas Pamulang 271dosen00842@unpam.ac.id 28Abstract 29Significant differences in home prices, even on properties with similar building sizes and locations, pose a major challenge in 30accurately determining property valuations. The discrepancy between the actual market price and the estimated value makes 31it difficult for potential buyers, sellers, and developers to make the right decision. To overcome these problems, this study 32applied the Multiple Linear Regression (MLR) algorithm in the Decision Support System (DSS) to estimate house prices 33based on the location and area of the building. The dataset used consists of 545 housing data points with variables such as 34house prices, locations, and building areas. The research stages include data collection, pre-processing (data cleaning and 35normalization), model development using MLR, and model performance evaluation. The evaluation was carried out using the 36division of trained data and test data with an 80:20 ratio, so that the model was tested using data that was not previously 37trained. The results showed that the model produced a Mean Absolute Error (MAE) of 1,474,748.13, a Root Mean Squared 38Error (RMSE) of 1,917,103.70, and a coefficient of determination (R²) of 0.273. A relatively low R² value indicates that the 39location and area variables of the building are not sufficient to explain the overall variation in house prices, so the addition 40of other variables—such as the number of rooms, facilities, and environmental conditions—is needed to improve the 41accuracy of the prediction and produce a more representative price estimate. 42Keywords: House Price Estimation, Multiple Linear Regression, Location, Building Area. 43Abstrak 44Perbedaan harga rumah yang signifikan, bahkan pada properti dengan luas bangunan dan lokasi yang serupa, 45menimbulkan tantangan besar dalam menentukan penilaian properti secara akurat. Ketidaksesuaian antara harga 46pasar aktual dan nilai estimasi menyebabkan kesulitan bagi calon pembeli, penjual, maupun pengembang dalam 47mengambil keputusan yang tepat. Untuk mengatasi permasalahan tersebut, penelitian ini menerapkan algoritma 48Multiple Linear Regression (MLR) dalam Decision Support System (DSS) untuk memperkirakan harga rumah 49berdasarkan lokasi dan luas bangunan. Dataset yang digunakan terdiri atas 545 data perumahan dengan variabel 50harga rumah, lokasi, dan luas bangunan. Tahapan penelitian meliputi pengumpulan data, pra-pengolahan 51(pembersihan dan normalisasi data), pembangunan model menggunakan MLR, serta evaluasi kinerja model. 52Evaluasi dilakukan menggunakan pembagian data latih dan data uji dengan rasio 80:20, sehingga model diuji 53menggunakan data yang tidak dilatih sebelumnya. Hasil penelitian menunjukkan bahwa model menghasilkan 54Mean Absolute Error (MAE) sebesar 1.474.748,13, Root Mean Squared Error (RMSE) sebesar 1.917.103,70, 55dan koefisien determinasi (R²) sebesar 0,273. Nilai R² yang relatif rendah mengindikasikan bahwa variabel 56lokasi dan luas bangunan belum cukup untuk menjelaskan variasi harga rumah secara keseluruhan, sehingga 57diperlukan penambahan variabel lain—seperti jumlah kamar, fasilitas, dan kondisi lingkungan—untuk 58meningkatkan akurasi prediksi dan menghasilkan estimasi harga yang lebih representatif. 59Kata kunci: Estimasi Harga Rumah, Regresi Linear Berganda, Lokasi, Luas Bangunan. 60 611. Introduction 62The development of the property sector in Indonesia 63has increased rapidly in recent years. The community’s 64need for decent and strategic housing continues to drive 65fluctuations in house prices, especially in urban areas 66such as Greater Jakarta [1]. A major challenge that 67arises is determining the selling or buying price of a 68house that accurately reflects market conditions, as 69prices are influenced by factors such as location, 70building area, land area, and available facilities. These 71