PREDIKSI TINGKAT PELANGGAN CHURN PADA PERUSAHAAN TELEKOMUNIKASI DENGAN ALGORITMA ADABOOST

Iqbal Muhammad Latief, Agus Subekti, Windu Gata

Abstract


With the rapid advancement of the telecommunications industry, and competition between telecommunications companies is increasing, companies need to predict their customers to determine the level of customer loyalty. One of them is by analyzing customer data by doing a Customer Churn Prediction. Predicting Customer Churn is an important business strategy for the company. To acquire new customers is much higher cost than retaining existing customers. The ease of operator switching is one of the serious challenges that the telecommunications industry must face. By predicting customer churn, companies can take immediate action to retain customers. To retain existing customers, the company must improve customer service, improve product quality, and must know in advance which customers have the possibility to leave the company. Prediction can be done by analyzing customer data using data mining techniques. In line with this, gathering information from the telecommunications business can help predict whether customer relationships will leave the company. The data used in this study are secondary data and amount to 7.403 data customers. The data has 21 variables. This study proposes to use the ensemble method namely adaboost, xgboost and random forest and compare them. Algorithm is validated through training data and testing data with a ratio of 80:20. From the results we got using python tools, it was found that the adaboost algorithm has an accuracy of 80%.

Keywordsaccuracy, adaboost, churn prediction, compare model, data mining.


Full Text:

PDF


DOI: https://doi.org/10.30873/ji.v21i1.2867

 

 

 

LP4M IBI DARMAJAYA

Jl. Zainal Abidin Pagar Alam No. 93 Labuhan Ratu, Bandar Lampung.Kampus IBI Darmajaya,  Gedung A Lantai 2.Telp. 0721-787214, 781310 Fax. 0721-700261 ext.126

Index by:
      

 

Flag Counter


Creative Commons License

Jurnal Informatika is licensed under a Creative Commons Attribution 4.0 International LicenseMy Stats jurnal

www.reliablecounter.com