Abstract:Abstract: In the current era of very fast technological development, customer churn is a serious challenge, especially in the competitive telecommunications industry. Churn refers to customers who stop using a service or…
move to another provider, and can be categorized into three types: Active Churn, Passive Churn, and Rotational Churn. Rotational Churn, which is difficult to predict be- cause the reasons for stopping are unclear, is the main focus of this research. This research aims to group Rotational Churn customers using a Data-Centric AI approach. This approach emphasizes improving data quality through Confident Learning and Synthetic Data before being applied to the K-Means clustering algorithm. The data used in this research is customer churn data from one telecommunications company during 2023. The research results show that customer grouping using the K-Means algorithm can provide deep insight into the characteristics of customer churn. The application of Data-Centric AI is proven to be able to increase the accuracy of clustering models, which ultimately helps compa- nies optimize programs and services to minimize churn and retain customers.
Keywords: data-centric AI; clustering; K-means
Abstrak: Dalam era perkembangan teknologi yang sangat pesat saat ini, churn pelanggan menjadi tantangan serius, terutama dalam industri telekomunikasi yang sangat kompetitif. Churn mengacu pada pelanggan yang berhenti menggunakan layanan atau beralih ke penyedia lain, dan dapat dikategorikan menjadi tiga jenis: Churn Aktif, Churn Pasif, dan Churn Rotasional. Churn Rotasional, yang sulit diprediksi karena alasan penghentian layanan tidak jelas, menjadi fokus utama penelitian ini. Penelitian ini bertujuan untuk mengelompokkan pelanggan Churn Rotasional menggunakan pendekatan Data-Centric AI. Pendekatan ini menekankan pada peningkatan kualitas data melalui Confident Learning dan Synthetic Data sebelum diterapkan ke algoritma K-Means clustering. Data yang digunakan dalam penelitian ini adalah data churn pelanggan dari satu perusahaan telekomunikasi selama tahun 2023. Hasil penelitian menunjukkan bahwa pengelompokan pelanggan menggunakan algoritma K-Means dapat memberikan wawasan mendalam tentang karakteristik churn pelanggan. Penerapan Data-Centric AI terbukti mampu meningkatkan akurasi model klastering, yang pada akhirnya membantu perusahaan mengoptimalkan program dan layanan untuk meminimalkan churn serta mempertahankan pelanggan.
Kata kunci: data-Centric AI; klasterisasi; K-means
Abstract:Abstract: Medan Aviation Polytechnic is one of the campuses under the ministry of transportation which has a major in telecommunication and air navigation engineering in Indonesia. Based on field surveys, an Analog to Digital…
gital Converter (ADC) practicum kit is needed to improve the ability of cadets. Based on this background, this study aims to design and simulate two ADC circuits, each of which is compiled by the integrated circuit (IC) ADC0804 and IC ADC0809 respectively. Three statistical formulas, namely mean error (ME), standard deviation error (SDE), and root mean square error (RMSE) are used to measure the performance of the two ADC circuits. Both ADC circuits are simulated using a Proteus 8.11 Simulator with 255 analog input voltages. Based on the result of the study, it is known that the ADC circuit compiled by IC ADC0809 is more accurate than the ADC circuit compiled by IC ADC0804. This is evidenced by a smaller error value, which is based on the simulation results of the ME, SDE, and RMSE values were 0.4210, 0.3410, and 0.5110, respectively. And, based on the measurement results, it has ME, SDE, RMSE respectively, namely 0.8510, 0.8110, and 0.9310.
Keywords: ADC; Proteus 8.11 Simulator; IC ADC0804; IC ADC0809; ME; SDE; RMSE
Abstrak: Politeknik Penerbangan Medan adalah salah satu kampus di bawah Kementerian Perhubungan yang memiliki jurusan teknik telekomunikasi dan navigasi udara di Indonesia. Berdasarkan survei di lapangan, kit praktikum konverter analog ke digital diperlukan untuk meningkatkan kemampuat taruna. Berdasarkan latar belakang tersebut, penelitian ini bertujuan merancang dan mensimulasi dua rangkaian ADC yang masing-masing disusun oleh IC ADC0804 dan IC ADC0809. Tiga formula statistik, yaitu mean error (ME), standard deviation error (SDE), and root mean square error (RMSE) digunakan untuk mengukur kinerja kedua rangkaian ADC tersebut. Kedua rangkaian ADC tersebut disimulasi menggunakan Simulator Proteus 8.11 dengan 255 tegangan masukan analog. Berdasarkan hasil penelitian diketahui bahwa rangkaian ADC yang disusun oleh IC ADC0809 lebih akurat dibandingkan dengan rangkaian ADC yang disusun oleh IC ADC0804. Hal tersebut dibuktikan dengan nilai kesalahan yang lebih kecil, yaitu berdasarkan hasil simulasi memiliki ME, SDE, RMSE masing-masing adalah 0,4210, 0,3410 dan 0,5110. Dan berdasarkan hasil pengukuran memiliki ME, SDE, dan RMSE masing-masing adalah 0,8510, 0,8110, dan 0,9310.
Kata kunci: ADC; Simulator Proteus 8.11; IC ADC0804; IC ADC0809; ME; SDE; RMSE
Abstract:Abstract : ODP can be a distribution tools for IT infrastructure development. So that ODP can reach the customer, there must be a telecommunications operator that has the ability to connect production equipment to the area.…
ea. ODP infrastructure development using the network method is CPM method. CPM method has no execution time tolerance. In financing ODP development can be done by two method is normal method and fast method. Normal method means all operation performed normally while the fast financing method means that the cost is more expensive because it requires more labor.
Kata Kunci : CPM; fast cost; normal cost; ODP
Abstrak : ODP dapat menjadi alat pendistribusi pembangunan dalam infrastuktur IT. Agar ODP dapat sampai ke pelanggan harus terdapat operator telekomunikasi yang memiliki kemampuan untuk menghubungkan alat produksi ke daerah tersebut. Pembangunan infrastuktur ODP menggunakan metode jaringan kerja yaitu metode CPM. Metode CPM tidak memiliki toleransi waktu pelaksanaan. Dalam pembiayaan pembangunan ODP dapat dilakukan dengan dua cara yaitu pembiayaan metode normal dan pembiayaan metode dipercepat, pembiayaan metode normal artinya semua operasi yang dilakukan secara normal sedangkan metode pembiayaan dipercepat artinya biaya lebih mahal karena membutuhkan tenaga kerja lebih banyak.
Kata Kunci : biaya normal; biaya dipercepat; CPM; ODP
Abstract:Marriage from an Islamic legal perspective through mobile phone communication is a new issue, as there is no standard fiqh book on this matter. The validity of marriage through telecommunications does not yet have its own…
n legal status because the Marriage Law 1 of 1974 does not regulate the law of prenuptial agreements. Legal analysis of the Islamic legal concept of marriage through telecommunications requires a search for law ( rechtsvinding ) by judges as conservative parties. Even in lawless environments, there are attempts to violate or break well-enforced rules and regulations. Efforts to interpret existing law properly can be applied in all future cases, because the law is sometimes unclear, incomplete, or not up-to-date ( rechtsvinding ). In other words, judges must adapt the law to more serious cases, because existing law cannot cover all social phenomena.
Abstract:The background of this research is that there has not been a habit of using academic information systems by both lecturers and students, there are no educational staff from the field of computer science or informatics, and…
nd the limited budget they have. This research approach is a qualitative research with case study method. The results of this study indicate that academic information system planning refers to the blue print for the development, management and utilization of higher education information systems. The organization assigns a direct assistant to the Head of Academic and Student Affairs who is assisted by two operators, whose operational direction is based on a decree issued by the leadership which is fully managed by the Telecommunications Center. Coordination of academic information systems based on the participation and support of all parties. Control is carried out directly by the Chairman as the leader. The obstacles faced in general are that there is no budget available considering the need for the development of an Academic Information System that requires a large amount of money, the age of most of the lecturers is old so it is quite difficult to adapt to changes towards digital and the ability of lecturers to use information systems is still low. The solution is to encourage students and lecturers to want to get used to adapting and learning in the use of academic information systems