Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Journal of Software Engineering, Information and Communication Technology
Syawanodna, Indira
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comparative Analysis of Artificial Neural Network (ANN) and Random Forest in House Price Prediction Retnowati, Yulia; Mafahim, Abid; Syawanodna, Indira
Journal of Software Engineering, Information and Communication Technology (SEICT) Vol 5, No 2: December 2024
Publisher : Universitas Pendidikan Indonesia (UPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/seict.v5i2.75945

Abstract

With the advancement of information technology, the application of machine learning in the property industry, particularly for house price prediction, has become increasingly important. Technology plays a crucial role in speeding up and enhancing the accuracy of property buying and selling processes. Therefore, the role of machine learning technology can be utilized to meet the need for improving the accuracy of house price predictions in major cities of developing countries, such as Bandung. This research aims to analyze the effectiveness of the Artificial Neural Network and Random Forest algorithms in predicting house prices in Bandung. The data used includes 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 is conducted by comparing the performance testing results of both algorithms using performance metrics for regression models such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-Square (R2). Additionally, this research analyzes which data ratio among the training, validation, and test data yields the best results. The research findings indicate that the model with a data ratio of 60:20:20 produces the best performance for both algorithms. The Random Forest algorithm demonstrates superior performance with results of MAE: 0.0470; MSE: 0.0079; RMSE: 0.0888; and R2: 0.7085.
Co-Authors Mafahim, Abid Retnowati, Yulia