Penerapan Algoritma C4.5 Untuk Prediksi Churn Rate Pengguna Jasa Telekomunikasi

Utami, Yohana Tri; Shofiana, Dewi Asiah; Heningtyas, Yunda

doi:10.23960/komputasi.v8i2.2647

Cited by 4 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pada penelitian [5] tentang Prediksi churn rate pada jasa telekomunikasi menggunakan algortima C4.5, untuk langkah awal dalam mengidentifikasi pola persentasi perpindahan pelanggan pada perusahaan telekomunikasi. Penelitian [6] implementasi menggunakan IG-KNN gabungan algoritma seleksi fitur information gain dengan KNN dan Penelitian [7] implementasi menggunakan Algoritma Naïve bayes dalam memprediksi customer churn diantara metode data mining tersebut yang telah digunakan untuk prediksi Customer churn hasilnya belum mencapai nilai yang sangat baik.…”

Section: Pendahuluanunclassified

“…Algoritma C4.5 merupakan suatu metode pembuatan pohon keputusan yang digunakan dalam analisis data dan pemodelan prediktif. Metode ini juga telah digunakan pada penelitian terdahulu [5] dalam memprediksi customer churn didapat hasil prediksi relatif lebih baik dari metode lainnya [6] [7]. PSO adalah algoritma optimisasi terinspirasi dari perilaku kelompok burung atau ikan yang mengarahkan partikel dalam pencarian solusi optimal melalui iterasi.…”

Section: Pendahuluanunclassified

“…Algoritma C4. 5 Algoritma C4.5 merupakan algoritma pembelajaran yang diawasi, algoritma ini memerlukan penggunaan kumpulan data pelatihan. Sebuah sampel diklasifikasikan digunakan dalam set data pelatihan.…”

Section: Customer Churnunclassified

See 2 more Smart Citations

Prediksi Customer Churn Pada Perusahaan Telekomunikasi Menggunakan Algoritma C4.5 Berbasis Particle Swarm Optimization

Rizki Kurniawan,

Nurul Sabrina,

Ilyas

2024

jati

View full text Add to dashboard Cite

Customer churn didefinisikan sebagai kecenderungan customer berhenti dan berpindah dari satu layanan kepada layanan lain pada periode tertentu, Karena ini merupakan masalah terpenting dalam dunia bisnis khususnya dalam industri telekomunikasi yang sangat mempengaruhi keuntungan perusahaan, dalam mendapatkan pelanggan baru biayanya jauh lebih tinggi dari pada mempertahankan pelanggan yang sudah ada. Memprediksi customer churn dapat membantu sektor CRM (Customer Relationship Management) pada perusahaan menentukan strategi mempertahankan pelanggan yang ada. Penelitian ini membahas mengenai prediksi customer churn menggunakan algoritma c4.5 berbasis particle swarm optimization yang digunakan untuk seleksi atribut dan optimasi pengukuran evaluasi confusion metrics. Skenario pembagian data latih 80% dan data uji 20%. Dari hasil penelitian optimasi particle swarm optimization mampu menyeleksi atribut pada algoritma C4.5, sehingga menghasilkan tingkat akurasi dalam prediksi customer churn yang lebih baik dibanding dengan menggunakan metode individual algoritma C4.5 terjadi peningkatan nilai akurasi sebesar 1.91% dengan nilai akurasi sebesar 91.55%, precision sebesar 85.21%, recall sebesar 85.0% dan f1-score sebesar 85.11%.

show abstract

Section: Pendahuluanunclassified

See 1 more Smart Citation

Prediksi Customer Churn Pada Perusahaan Telekomunikasi Menggunakan Algoritma C4.5 Berbasis Particle Swarm Optimization

Rizki Kurniawan,

Nurul Sabrina,

Ilyas

2024

jati

View full text Add to dashboard Cite

show abstract

“…Data mining juga diartikan sebagai suatu proses untuk menemukan sebuah pola pada data. Data Mining adalah sebuah teknologi baru yang ditingkatkan dan sangat begitu cepat berkembang pada saat ini [2]. Algoritma C4.5 pada penelitian terdahulu digunakan untuk menemukan sebuah hasil prediksi tentang kepuasan tenant pada gedung wisma keiai dengan menggunakan algoritma C4.5.…”

Section: Pendahuluanunclassified

Prediksi Tingkat Kepuasan Pelayanan Online Menggunakan Metode Algoritma C.45

Lestari

Defit²,

Yuhandri

2021

INFEB

View full text Add to dashboard Cite

Online service is a service that uses the help of the internet. This service can solve various types of business without having to meet directly with employees. This can be done quickly and on time. Especially when we are currently experiencing the Covid-19 pandemic, all existing services are carried out online and this is increasingly being done by many parties, because they can maximize in helping people's affairs online. This service makes it easier for the public to register which will be done online during this pandemic. The data that will be processed in this online service from 2019 to 2020 is about data about people who do not understand online services, negative community responses, positive community expectations. The method used in this study is the method with the C4.5 algorithm where this is one of the algorithms that will be used to determine a classification or group of data and will be predictive. The advantage of this algorithm is that it can produce a decision tree which will make it easier to implement and will have an acceptable level of accuracy. The results of this study are able to predict a value or determine the level of community satisfaction in 2021 appropriately. Therefore, this study can be used as a reference to determine the level of satisfaction at the Padang City Population and Civil Registration Office. The method used in this study is the prediction method using the C4.5 algorithm by using as many as 14 attributes. The data used in this study is sourced from data from online questionnaires and stored in the Disdukcapil database which has as many as 50 community data which have been presented in a CSV file. The analysis in this study uses the help of tools in the form of rapid miner software version 5.3,000. The results of this study are that there are 3 rules from the data processing process using the C4.5 algorithm where the rule is the final result of the decision tree form.

show abstract

“…Currently, the telecommunications industry is experiencing significant problems regarding customer switching due to intense competition and the existence of new, more attractive offers [4]. The telecommunications industry experiences an average annual churn rate of 30 -35 %, and acquiring new customers is 5 -10 times more expensive than retaining an existing one [5]. Therefore, based on the observations of a telecommunications company, getting new customers is much more complex and more expensive than retaining existing customers [6].…”

Section: Introductionmentioning

confidence: 99%

Customer Decision Prediction Using Deep Neural Network on Telco Customer Churn Data

Nalatissifa

Pardede

2021

J. Elektron. dan Telekomun.

View full text Add to dashboard Cite

Customer churn is the most important problem in the business world, especially in the telecommunications industry, because it greatly influences company profits. Getting new customers for a company is much more difficult and expensive than retaining existing customers. Machine learning, part of data mining, is a sub-field of artificial intelligence widely used to make predictions, including predicting customer churn. Deep neural network (DNN) has been used for churn prediction, but selecting hyperparameters in modeling requires more time and effort, making the process more challenging for the researcher. Therefore, the purpose of this study is to propose a better architecture for the DNN algorithm by using a hard tuner to obtain more optimal hyperparameters. The tuning hyperparameter used is random search in determining the number of nodes in each hidden layer, dropout, and learning rate. In addition, this study also uses three variations of the number of hidden layers, two variations of the activation function, namely rectified linear unit (ReLu) and Sigmoid, then uses five variations of the optimizer (stochastic gradient descent (SGD), adaptive moment estimation (Adam), adaptive gradient algorithm (Adagrad), Adadelta, and root mean square propagation (RMSprop)). Experiments show that the DNN algorithm using hyperparameter tuning random search produces a performance value of 83.09 % accuracy using three hidden layers, the number of nodes in each hidden layer is [20, 35, 15], using the RMSprop optimizer, dropout 0.1, the learning rate is 0.01, with the fastest tuning time of 21 seconds. Better than modeling using k-nearest neighbor (K-NN), random forest (RF), and decision tree (DT) as comparison algorithms.

show abstract

Penerapan Algoritma C4.5 Untuk Prediksi Churn Rate Pengguna Jasa Telekomunikasi

Cited by 4 publications

References 9 publications

Prediksi Customer Churn Pada Perusahaan Telekomunikasi Menggunakan Algoritma C4.5 Berbasis Particle Swarm Optimization

Prediksi Customer Churn Pada Perusahaan Telekomunikasi Menggunakan Algoritma C4.5 Berbasis Particle Swarm Optimization

Prediksi Tingkat Kepuasan Pelayanan Online Menggunakan Metode Algoritma C.45

Customer Decision Prediction Using Deep Neural Network on Telco Customer Churn Data

Contact Info

Product

Resources

About