IMPLEMENTASI NEURAL NETWORK PADA PREDIKSI PENDAPATAN RUMAH TANGGA
Abstract
Pendapatan rumah tangga sangat penting dalam kehidupan sehari-hari, oleh karena itu, untuk memprediksi bagaimana pendapatan rumah tangga dapat ditingkatkan di sini, penulis menggunakan algoritma jaringan syaraf tiruan untuk memprediksi faktor-faktor yang dapat mempengaruhi pendapatan rumah tangga. Algoritma jaringan syaraf tiruan merupakan teknik peramalan yang paling umum digunakan, karena algoritma Neural Network dapat cepat dan akurat, banyak peneliti menggunakan jaringan syaraf tiruan untuk memecahkan masalah peramalan. Jaringan Syaraf Tiruan memiliki keunggulan bahwa jaringan syaraf tiruan dapat mengatasi masalah nonlinier, memiliki toleransi yang tinggi terhadap data yang mengandung noise dan mampu menangkap hubungan yang sangat kompleks antara variabel prediktor dan keluaran. Pada data pendapatan rumah tangga ini algoritma jaringan syaraf tiruan dapat memprediksi jumlah pendapatan dengan akurasi sebesar 83,62%. Nilai akurasi yang didapat sangat tinggi dan dapat membantu dalam menata keuangan di setiap rumah tangga, sehingga jaringan syaraf tiruan dapat memecahkan masalah dalam memprediksi pendapatan rumah tangga di berbagai negara di dunia sesuai dengan data dari UCI dataset dibandingkan menggunakan algoritma KNN yang nilai akurasinya sebesar 79.18%.
Kata Kunci : Data Mining, Neural Network, Rumah Tangga
ABSTRACT
Household income is very important in everyday life, therefore, to predict how household incomes can be improved here, the authors use artificial neural network algorithms to predict factors that may affect household incomes. Artificial neural network algorithms are the most commonly used forecasting techniques, because the Neural Network algorithm can be fast and accurate, many researchers using artificial neural networks to solve forecasting problems. Artificial Neural Networks have the advantage that artificial neural networks can overcome nonlinear problems, have high tolerance to noise-containing data and be able to capture the very complex relationship between predictor and output variables. In this household income data artificial neural network algorithm can predict the amount of income with an accuracy of 83.62%. The accuracy of the value obtained is very high and can help in managing the finances in every household, so that neural networks can solve the problem in predicting household income in various countries in the world according to data from UCI dataset than using KNN algorithm whose accuracy value is 79.18%.
Keyword : Data Mining, Household, Neural Network
Full Text:
PDF (Bahasa Indonesia)References
Gorunescu, Florin. (2011). Data Mining: Concepts, Models and Techniques. Verlag Berlin Heidelberg, Springer. Jerman.
Guillet, Fabrice. Hamilton, Howard J. (2007). Quality Measures in Data Mining. Verlag Berlin Heidelberg, Springer. Jerman.
Han,J& Kamber, Micheline. (2007). Data Mining Concepts, Models and Techniques. Second Edition, Morgan Kaufmann Publisher. Elsevier.
Heaton, Jeff. (2010). Programming Neural Networks With Encog 2 In Java. Heaton Research.Inc, USA.
Larose, D. (2005). Discovering Knowledge in Data. New Jersey, John Willey & Sons.Inc.
Liao, Warren. T. & Triantaphyllou.Evangelos. (2007). Recent Advances in Data Mining of Enterprise Data: Algorithms and Applications. Series: Computer and Operation Research. 6. 190.
Lim TS, Loh WY, Shih YS.(1999). A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms. Kluwer Academic Publishers: Boston.
Maimon, Oded& Rokach, Lior. (2010). Data Mining and Knowledge Discovery Handbook, Springer, New York.
Mihov, Valentin. (2015). Adult Income Data Set Analysis with IPython. Sofia University, Bulgaria.
Min, Hui Tsai, et al.(2010). Profiling U.S. Household Income. https://faculty.biu.ac.il/~yahavi1/Projects/CP2010T1_rep.pdf.
Myatt, Glenn J. (2007). Making sense of data : A Practical Guide to Exploratory data analysis and Data Mining. John Wiley & Sons Inc, New Jersey.
Shukla, Anupam. Tiwari, Ritu. & Kala, Rahul. (2010). Real Life Application of Soft Computing.New York: Taylor and Francis Groups, LLC.
Siang, Jong Jek (2009). Jaringan Syaraf Tiruan dan Pemrogramannya menggunakan MATLAB. Penerbit Andi. Yogjakarta.
Topiwalla, Mohammed. (2013). Machine Learning on UCI Adult data set using various classifier algoritms and scaling up the accuracy using extreme gradient boosting. University of SP Jain School of Global Management.
Vercellis,C. (2009). Business Intelligence: Data Mining and Optimization for Decision Making. Wiley.
Witten,I. Frank, E., & Hall. (2011). Data Mining: Practical Machine Learning and tools. Morgan Kaufmann Publisher, Burlington.
DOI: https://doi.org/10.31294/swabumi.v6i1.3312
INDEXING
P-ISSN : 2355-990X E-ISSN: 2549-5178
