ARTÍCULO
TITULO

Prediction of Smooth Rusunawa Rental Payments Using the Backpropagation Algorithm and Decision Tree DOI : 10.24114/cess.v8i2.46862 | Abstract views : 0 times

Mangapul Siahaan    

Resumen

Permasalahan pemukiman yang sering terjadi diperkotaan adalah keterbatasan lahan untuk tempat tinggal sedangkan pertumbuhan penduduk semakin berkembang sehingga diperlukan prasarana tempat tinggal untuk masyarakat yang golongan ekonomi kurang mampu. Kelancaran pembayaran uang sewa rumah susun masih menjadi kendala sehingga diperlukan suatu sistem untuk mengklasifikasi dan prediksi kemampuan bayar oleh masyarakat. Tujuan penelitian ini adalah untuk menganalisa algoritma yang bagus dengan nilai akurasi yang tinggi agar bisa diimpelementasikan pada sistem. Sumber dataset yang digunakan dari database aplikasi sewa rumahsusun dengan variabel yang digunakan adalah nobriva, pekerjaan, statuspekerjaan, gaji, hargasewa dan keterangan. Algoritma yang digunakan dalam penelitian ini adalah Decision Tree dan Backpropagation dengan arsitektur 5-5-2. Berdasarkan hasil uji maka didapat nilai akurasi Decision Tree sebesar 90%, sedangkan nilai akurasi dengan algoritma Backpropagation dan arsitektur jumlah 5 node layer, 5 node hiden layer dan 2 node output layer dengan menggunakan activation sigmoid maka menghasilkan nilai akurasi sebesar 88.39%.Settlement problems that often occur in urban areas are limited land for residence while population growth is growing, so residential infrastructure is needed for economically disadvantaged people. The smooth payment of rent for flats is still an obstacle, so a system is needed to classify and predict the ability to pay by the public. This study aims to analyze a good algorithm with a high accuracy value so that it can be implemented in the system. The dataset source used is the flat rental application database, with the variables used are nobriva, occupation, employment status, salary, rental price, and description. The algorithm used in this research is Decision Tree and Backpropagation with 5-5-2 architecture. Based on the test results, the accuracy value of the Decision Tree is 90%. In contrast, the accuracy value with the Backpropagation algorithm and architecture consists of 5 node layers, 5 hidden layer nodes, and 2 output layer nodes using sigmoid activation, resulting in an accuracy value of 88.39%.  

 Artículos similares

       
 
Kadria Ezzine, Joseph Di Martino and Mondher Frikha    
We present an any-to-one voice conversion (VC) system, using an autoregressive model and LPCNet vocoder, aimed at enhancing the converted speech in terms of naturalness, intelligibility, and speaker similarity. As the name implies, non-parallel any-to-on... ver más
Revista: Applied Sciences

 
Yuliang Zhao, Xinyue Zhang, Mingliang Yang, Qingchao Zhang, Jian Li, Chao Lian, Changbo Bi, Zhiping Wang and Guanglie Zhang    
Basketball has become one of the most popular sports and is generally popular in international sports events. However, how to effectively achieve shooting prediction and then guide shooting has become a major challenge. Different from the classical manua... ver más
Revista: Applied Sciences

 
Kasumi Morita, Masashi Mouri, Riccardo Fincato and Seiichiro Tsutsumi    
This paper investigates the fatigue cyclic deformation behavior of mid-carbon steel. Uniaxial tensile loading tests and fatigue tests under constant and multi-step amplitude loading steps are performed to characterize the influence of loading history. Th... ver más

 
Said M. Easa, Ahmed A. Lamri and Dejan Brkic    
Numerous explicit approximations of the Colebrook equation have been developed and evaluated based on two criteria: prediction accuracy and computational efficiency. This paper introduces a new evaluation criterion based on the reliability of each equati... ver más

 
José Jiménez-Varona and Gabriel Liaño    
The flow at high angles of attack over axisymmetric configurations is not symmetric. The mechanism that triggers the asymmetry may be a combination of a global or hydrodynamic instability (temporal instability) combined with a convective instability (spa... ver más
Revista: Computation