cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota adm. jakarta selatan,
Dki jakarta
INDONESIA
Faktor Exacta
ISSN : 1979276X     EISSN : 2502339X     DOI : -
Faktor Exacta is a peer review journal in the field of informatics. This journal was published in March (March, June, September, December) by Institute for Research and Community Service, University of Indraprasta PGRI, Indonesia. All newspapers will be read blind. Accepted papers will be available online (free access) and print version.
Arjuna Subject : -
Articles 531 Documents
Prediksi Churn Pelanggan B2B dengan Segmentasi Menggunakan Bisecting K-Means dan Long Short-Term Memory Wardina, Khairina; Rahmat, Ade; Syafrullah, Mohammad
Faktor Exacta Vol 18, No 3 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i3.27087

Abstract

In the competitive B2B sector, customer churn is a key challenge, particularly for a Fast-Moving Consumer Goods (FMCG) distribution company in North Sulawesi. From 2019 to 2022, the company's churn rate continued to rise despite efforts to reduce it. This study addresses the challenge of identifying churn in a non-contractual context by combining Bisecting K-Means for customer segmentation and Long Short-Term Memory (LSTM) for churn prediction based on monthly revenue. The Bisecting K-Means algorithm produced three clusters with a Davies-Bouldin Index (DBI) of 0.46, indicating effective segmentation. The LSTM model achieved a validation accuracy of 96% and a test accuracy of 95%, with an AUC-ROC of 97%. Results show that cluster 1 has the highest churn rate at 100%, followed by cluster 2 at 16.31%, and cluster 0 with the lowest at 3.21%. Out of 5,163 customers in the test data, 920 were identified as churned.
Application of Extreme Programming in the Design and Development of a Web-Based Inventory Information System at the Kerinci District Communication and Information Office Kesuma, Eastyanda Putra; Khaira, Ulfa; A, Muhammad Razi
Faktor Exacta Vol 18, No 3 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i3.27532

Abstract

The management of inventory at the Department of Communication and Informatics in Kerinci Regency faced challenges due to centralized processes and the limitations of the existing desktop-based application, the Regional Management Information System, which did not meet user needs. To address this, a web-based inventory management system was developed to enhance operational efficiency, data accuracy, and real-time accessibility. The system was built using the Extreme Programming method over two iterations. The first iteration focused on inventory data management, item categorization, and asset history tracking, while the second iteration introduced features for reporting asset conditions, data validation, and recap reports. The development process included planning, design, coding, and testing phases. User acceptance testing and performance testing were conducted to ensure system quality and user satisfaction. The results demonstrated that the system functioned effectively, met user requirements, and supported efficient inventory management. This system is expected to improve transparency, operational efficiency, and public services at the Department of Communication and Informatics in Kerinci Regency.
Penerapan Project Management Pada Proyek Sistem Penjualan Motor Berbasis Geografik Erdiansyah, Dian
Faktor Exacta Vol 18, No 3 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i3.25777

Abstract

PENERAPAN METODE AVERAGE BASED LENGTH FUZZY TIME SERIES LEE UNTUK PREDIKSI KECEPATAN ANGIN DI KABUPATEN NATUNA Nifari, Dela; Nurfalinda, Nurfalinda; Rathomi, Muhamad Radzi
Faktor Exacta Vol 18, No 4 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i4.27726

Abstract

Wind speed is a critical parameter that significantly affects the safety of maritime activities, particularly in Natuna Regency, a strategic region with substantial marine potential. This study aims to predict wind speed in Natuna Regency using the Average Based Length Fuzzy Time Series Lee method. The data utilized in this research consists of the average wind speed data for Natuna Regency obtained from the Meteorological Station of BMKG Ranai, covering the period from January 1, 2023, to December 31, 2023, comprising 365 data points. The interval length in the process significantly influences the prediction results. Based on testing, the model achieved a Mean Absolute Percentage Error (MAPE) of 24.42% with an accuracy rate of 78.05%, indicating that the Average Based Length Fuzzy Time Series Lee method demonstrates a reasonably good level of forecasting accuracy for predicting wind speed in Natuna Regency.
Penerapan Metode Design Thinking dalam Perancangan UIUX Warehouse Management System Hidayat, Manarul; Andrew Sinaga, Frans
Faktor Exacta Vol 18, No 4 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i4.28861

Abstract

Warehouse inventory management that is still done manually at PT. XYZ causes various problems such as stock discrepancies, slow delivery processes, and data loss. To overcome these problems, the company plans to develop a web-based warehouse management system or commonly called the Warehouse Management System. In the system design process, the implementation of User Interface (UI) and User Experience (UX) is an important aspect so that the application can be used effectively and efficiently by users. Figma is used as a tool in designing an interactive and collaborative interface. The Design Thinking approach is applied to explore user needs in depth through the stages of empathize, define, ideate, prototype, and test. System evaluation is carried out using the System Usability Scale (SUS) to ensure user comfort, effectiveness, and satisfaction with the prototype developed. The results of the usability test produced an Excellent score of 80.5. This proves that a well-designed UI/UX can bridge technology and user needs effectively.
IMPLEMENTASI AUTOREGRESSIVE INTEGRATED MOVING AVERAGE (ARIMA) DALAM PREDIKSI JUMLAH PENDUDUK MISKIN KOTA TANJUNGPINANG Musliha, Musliha; Nurfalinda, Nurfalinda; Rathomi, Muhamad Radzi
Faktor Exacta Vol 18, No 4 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i4.27731

Abstract

Poverty is one of the main development issues faced by developing countries, including Indonesia. In Tanjungpinang City, located in the Riau Islands Province, the poverty rate in 2022 reached 27.54 thousand people. Therefore, this study aims to predict the number of poor people in Tanjungpinang City using the Autoregressive Integrated Moving Average (ARIMA) method. The data used is monthly time series data from 2015 to 2022, totaling 96 data points. The analysis process begins with stationarity tests, differencing, and selecting the best ARIMA model. The best model identified is ARIMA (1,2,0). Evaluation results indicate that this model has a Mean Absolute Percentage Error (MAPE) of 10.6%, signifying a good level of prediction accuracy. The predicted number of poor people for January 2023 is 18.302 thousand. This research is expected to serve as a reference for the government in designing strategic policies to address poverty in Tanjungpinang City.
Penerapan Aplikasi E-Perkara di Pengadilan Agama Jakarta Barat dengan Model Agile Development Saputri, Galuh; Siswopranoto, Agung
Faktor Exacta Vol 18, No 4 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i4.27915

Abstract

The West Jakarta Religious Court is part of the Supreme Court of the Republic of Indonesia, which currently still uses conventional methods to recapitulate the percentage of case types. Based on the results of observations, the Chairman of the West Jakarta Religious Court must review the recapitulation of the percentage of cases from the clerk's department. After receiving the recapitulation, the leadership needs to review the report and ask for further information from the Registrar of the West Jakarta Religious Court. The process of processing case data which is still conventional causes slow recapitulation of case settlement percentages and requires a lot of paper for each case, which then requires large archive storage space, and there is a risk of the archives being slipped or lost. To overcome this problem, the proposed solution is to build a Website-based E-Case application for the West Jakarta Religious Court, using an Agile Development approach. With this E-Case application, the overall case data recapitulation process can be carried out online/electronically to make it easier to delegate tasks. This is proven by the results of a questionnaire using the System Usability Scale test, which showed results of 79.50% from Employees and 81.25% from Admin.
Supporting The Company's Investment Decision With The Method Simple Multi Attribute Rating Technique (SMART ) Eriana, Emi Sita
Faktor Exacta Vol 18, No 4 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i4.27692

Abstract

Advancing the company, PT FAC, which is engaged in the processing of snacks, in an effort built to support the performance of the management company, conducting a decision support system (SPK) to expand investment by choosing various alternatives including car purchases, land purchases, expanding warehouses, maintaining systems and information technology facilities and developing new products. This is a consideration for management in making previous decisions that are the reason for investment within 10 years. The SMART method was chosen as a supporting method in selecting alternatives because it allows for effective monitoring of progress by requiring measurable goals. An individual or team can easily determine the extent to which a goal has been achieved. The purpose of this study is to help determine whether corrective action or adjustment to the results of decisions taken based on methodological steps is necessary. The results of the calculation were obtained from the calculation of normalization and weighting that the highest yield of profitable investment in 10 years that PT FAC will take is the maintenance of systems and technological facilities (A3) with a value of 0.85, and the highest value of alternative 4 (A4) is developing new products with 0.670.
Teknologi Penginderaan Jauh untuk Mengidentifikasi Pengaruh Pola Spasio Temporal Penutup Lahan Terhadap Perubahan Temperatur Kawasan Sari, Diah Sekar Arum; Anurogo, Wenang; Seftyarizki, Debby
Faktor Exacta Vol 18, No 4 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i4.28534

Abstract

Evaluasi Keakuratan Produk Satelit (CHRIPS, GPM-IMERG, PERSIANN-CCS, dan GSMaP) Dalam Mengidentifikasi Curah Hujan di Sumatera Barat ZIKRI, MUHAMMAD AULIA; DISERA, TIARA EMANUELLA; SARAGIH, RIO HANSYEN; NUGRAHENI, IMMA REDHA
Faktor Exacta Vol 18, No 4 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i4.27697

Abstract

This study evaluates the accuracy of satellite rainfall products against observational data from three stations in West Sumatra, averaged to represent the region's general conditions. The analysis uses eyeball and statistical methods on daily, ten-day, monthly, and seasonal scales. The satellite products assessed include GPM-IMERG, CHIRPS, GSMaP, and PERSIANN-CCS. On the daily scale, CHIRPS shows the best accuracy with a correlation coefficient of 0.17, RMSE of 27.97 mm, NRMSE of 0.097, and MAE of 14.19 mm. On the ten-day, monthly, and seasonal scales, GPM-IMERG outperforms the other products, achieving the highest correlation coefficient of 0.84. Additional analysis using contingency table metrics (POD, FAR, CSI, FOH, HSS) confirms GPM-IMERG as the most accurate product. These findings indicate that GPM-IMERG is the most reliable satellite product for rainfall estimation in West Sumatra, especially for longer temporal analyses.