K-MEANS AND XGBOOST FOR CUSTOMER ELECTRICITY ACCOUNT PAYMENT BEHAVIOR ANALYSIS (CASE STUDY: PLN ULP PANAKKUKANG)

Raditya Hari Nugraha, Diana Purwitasari, Agus Budi Raharjo

Abstract


Revenue Acceleration from electricity account receivables is one of the energy companies' efforts to maintain cash flow so that they can carry out operational activities and carry out investment activities to develop company assets. Factors that influence electricity bill payment behavior include the location of consumers, the amount of the bill, payment point facilities located around consumers' homes, the use of digital technology as a media of payment, as well as consumer awareness and understanding regarding the time limit for paying electricity bills. Therefore, it is necessary to conduct an analysis so that the company can determine a special strategy for customers who have the potential to be in arrears in electricity bills. To get the characteristic of electricity bill payments, several previous studies have used various classification methods of machine learning such as random forest, nave bayes, SVM, CART, etc. to get the best accuracy. In this research, to increase the accuracy of the model, author using the cluster method with the k-means technique and combining it with the eXtreme Gradient Boosting (XGBOOST) classification method based on data on the characteristics of consumer electricity bill payments. In this study also used hyperparameter adjustment with hillclimbing, random search, and bayesian techniques to increase the accuracy of the model. The model simulation carried out in this thesis gives the result that the combination of the k-means cluster with the XGBoost classification and by adjusting the bayesian technique hyperparameters has a much better model accuracy rate with a value of 89.27% and an Area Under Curve (AUC) value of 0.92 when compared to gradient boosting method with an accuracy rate of only 74.76% and an AUC value of 0.75. Based on the simulation results on ULP Panakkukang customer data, it was found that the subsidy category customer group and customers who often experience power outages have a tendency to be in arrears on electricity bills.


Full Text:

PDF

References


A. Darmawan, dan S.P. Bangun. (2016). Electricity Accounts Receivables Billing Procedures. Journal of Applied Accounting and Taxation. 1(1), hal. 15-20.

W. Guo, W. Hong, W. Li, dan K. Guo. (2015). Design and Implementation of Electric Charge Arrears Prediction System. 12th Web Information System and Application Conference (WISA), hal. 309-313.

E. A. Darko, S. Adarkwah, F. Donkor, dan E. Kyei. (2016). Management of accounts receivables in utility companies: A focus on Electricity Company of Ghana (ECG). International Journal of Academic Research in Business and Social Sciences. 6, hal. 486-518.

W. Fu, D. Zhang, Y. Fu, J. Li, dan Y. Xie. (2017). Arrears prediction for electricity customer through Wgan-Gp, IEEE. hal. 1667-1670.

M. Bahrami, B. Bozkaya, dan S. Balcisoy. (2020). Using Behavioral Analytics to Predict Customer Invoice Payment. Big data. 8(1), hal. 25-37.

A. P. Redaputri, dan I. Apriansyah. (2022). Strategi Pengambilan Keputusan Untuk Meminimalkan Tunggakan Tagihan Listrik Pasca Bayar PT. PLN. JBMI (Jurnal Bisnis, Manajemen, dan Informatika). 19(1), hal. 20-33.

S. Zeng, P. Melville, C. Lang, I. Boier, dan C. Murphy. (Agustus 2008). Using predictive analysis to improve invoice-to-cash collection. International Conference on Knowledge Discovery and Data Mining, Las Vegas, Nevada, USA. hal. 1043-1050.

W. Hu. (2016). "Overdue invoice forecasting and data mining,". Massachusetts Institute of Technology. Graduate Thesis.

A. Appel, G. Malfatti, R. Cunha, B. Cardoso and R. de Paula. (Agustus 2020). Predicting Account Receivables with Machine Learning. KDD (Virtual Conference) MLF ’20, San Diego, CA.

I. Indrayani. (2019). Pengaruh Payment Point Online Bank (PPOB) Terhadap Percepatan Aliran Kas (Studi Kasus di PT. PLN (PERSERO) Provinsi Aceh). Jurnal Akuntansi dan Keuangan Universitas Malikussaleh. 7(2), hal. 83-92.

S. Murtaqi. (2011). "Perubahan Sistem Siklis Menjadi Non Siklis,". Peraturan Direksi PT PLN (Persero), Jakarta.

Y. Bambang. (2019). "Pengendalian Piutang," Edaran GM PLN UIW Sulselrabar, Makassar.

R. Nurul dan K. Edi. (2020). Implementasi Metode K-Means Clustering Tunggakan Rekening Listrik pada PT. PLN (Persero) Gardu Induk Kisaran. Jurnal Teknologi Sistem Informasi dan Sistem Komputer TGD. 3(1), hal. 103-117.

D.N Batubara, A.P. Windarto dan E. Irawan. (Februari 2022)Analisis Prediksi Keterlambatan Pembayaran Listrik Menggunakan Komparasi Metode Klasifikasi Decision Tree dan Support Vector Machine. Jurnal Riset Komputer. 9(1), hal. 102-108.

Y. Asri, D. Kuswardani dan E. Yosrita. (2021). Clusterization of customer energy usage to detect power shrinkage in an effort to increase the efficiency of electric energy consumption. Indonesian Journal of Electrical Engineering and Computer Science. 22(1), hal. 10-17.

S. Shah. (Januari 2019). Customer Payment Prediction in Account Receivable. International Journal of Science and Research (IJSR). 8(1), hal. 642-644

P. Tang. (2020). Telecom Customer Churn Prediction Model Combining K-means and XGBoost Algorithm. 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), hal. 1128-1131.

D. Ran, H. Jiaxin dan H. Yuzhe. (2020). Application of a Combined Model based on K-means++ and XGBoost in Traffic Congestion Prediction. 2020 5th International Conference on Smart Grid and Electrical Automation (ICSGEA), hal. 413-418.

J. Henriques, F. Caldeira, T. Cruz dan P. Simoes. (2020). Combining K-Means and XGBoost Models for Anomaly Detection Using Log Datasets. Electronics. 9(7), hal. 1-16.

Z. Mushtaq, S. Ashraf dan N. Sabahat. (2020). Predicting MBTI Personality type with K-means Clustering and Gradient Boosting. 2020 IEEE 23rd International Multitopic Conference (INMIC), hal. 1-5.

F. L. Gewers, G. R. Ferreira, H. F. D. Arruda, F. N. Silva, C. H. Comin, D. R. Amancio dan L. D. F. Costa. (2021). Principal Component Analysis: A Natural Approach to Data Exploration. ACM Comput. Surv. 54(4), hal. 1-34.

L. Ye, C. Qiu-ru, X. Hai-xu, L. Yi-jun dan Y. Zhi-min. (2012). Telecom customer segmentation with K-means clustering. 7th International Conference on Computer Science & Education (ICCSE). hal. 648-651.

T. Chen dan C. Guestrin. (2016). XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 8, hal. 785-794.

C. Wang, C. Deng dan S. Wang. (2020). Imbalance-XGBoost: Leveraging weighted and focal losses for binary label-imbalanced classification with XGBoost. Elsevier. 136, hal. 190-197.

J. Gao, W. Sun dan X. Sui. (2021). Research on Default Prediction for Credit Card Users Based on XGBoost-LSTM Model. A. Farouk, Ed., Discrete Dynamics in Nature and Society. 2021, hal. 5080472.

K. Budholiya, S. K. Shrivastava dan V. Sharma. (2020). An optimized XGBoost based diagnostic system for effective prediction of heart disease. Journal of King Saud University - Computer and Information Sciences. 34, hal. 4514-4523.

K. Nagarajan. (2018). A Predictive Hill Climbing Algorithm for Real Valued multi-Variable Optimization Problem like PID Tuning. International Journal of Machine Learning and Computing. 8(1), hal.14-19.

S.V. Konstantinov, A.I. Diveev, G.I. Balandina dan A.A. Baryshnikov. (2018). Evolutionary Algorithms for the Optimal Control Problem of the Mobile Robot. 13th International Symposium “Intelligent Systems”. 1514, hal. 123-136.

V. H. Nguyen, T. T. Le, H. S. Truong, M. V. Le, V. L. Ngo, A. T. Nguyen dan H. Q. Nguyen. (2021). Applying Bayesian Optimization for Machine Learning Models in Predicting the Surface Roughness in Single-Point Diamond Turning Polycarbonate. Hindawi. 2021, hal. 1-16.




DOI: http://dx.doi.org/10.12962/j24068535.v20i2.a1132

Refbacks

  • There are currently no refbacks.