Claim Missing Document
Check
Articles

Found 6 Documents
Search

ANALISIS DALAM MENENTUKAN PRODUK BRI SYARIAH TERBAIK BERDASARKAN DANA PIHAK KETIGA MENGGUNAKAN AHP Putrama Alkhairi; Agus Perdana Windarto
CESS (Journal of Computer Engineering, System and Science) Vol 3, No 1 (2018): Januari 2018
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (593.568 KB)

Abstract

Salah satu tujuan Bank BRI Syariah membuat layanan produk-produk dan jasa unggulan  adalah untuk menghasilkan kegiatan perbankan yang berkualitas dan menunjang pelaksanan ekonomi dab stabilitas nasional ke arah peningkatan kesejahteraan masyrakat banyak. Banyak asumsi dan pendapat dari sejumlah kalangan tentang produk mana yang terbaik yang di keluarkan oleh BRI Syariah. Banyak kriteria dari produk - produk yang dapat dijadikan parameter sebagai kunci menjadi produk unggulan. Penelitian ini membahas tentang metode pengambilan keputusan di antara sekian banyak pilihan dengan menggunakan metode AHP (analytic hierarchy process). Model kasus yang digunakan adalah menentukan produk mana yang terbaik dri produk BRI Syariah berdasarkan Dana Pihak Ketiga. Penelitian menggunakan dua komponen komparasi yakni data riil BRI Syariah dan Observasi langsung, serta tiga kriteria yakni masalah Setoran awal, Biaya penutupan, dan Prospek fasilitas. Hasil dari penelitian ini menenujukan bahawa perhitungan yang dilakukan secara manual mampu memberikan perangkingan alternatif dari hasil perhitungan bobot nilai produk sesuai dengan metode (AHP). Dari hasil pengujian Tabungan Faedah BRI Syariah menunjukan yang menjadi produk BRI Syariah terbaik berdasarkan Dana Pihak Ketiga dengan nilai angka konsistensi eigen vektor 0,32201 yang lebih besar dari pada 0,19889 sebagai tempat kedua terbaik.
Enhancing Premier League Match Outcome Prediction Using Support Vector Machine with Ensemble Techniques: A Comparative Study on Bagging and Boosting Agus Perdana Windarto; Putrama Alkhairi; Johan Muslim
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 1 (2025): February 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i1.6173

Abstract

Predicting football match outcomes is a significant challenge in sports analytics, requiring models that are both accurate and resilient. This study evaluates the effectiveness of ensemble techniques, specifically Bagging and Boosting, in enhancing the performance of Support Vector Machine (SVM) models for predicting match outcomes in the English Premier League. The dataset comprises detailed match statistics from 1,520 matches across multiple seasons, including features such as team performance, player statistics, and match outcomes. Four models were examined: baseline SVM, SVM with Bagging, SVM with Boosting, and a combined SVM + Bagging + Boosting approach. Evaluation metrics include accuracy, recall, precision, F1 score, and ROC-AUC, providing a comprehensive assessment of each model's performance. Experimental results indicate that ensemble methods substantially improve model accuracy and stability, with the SVM + Bagging + Boosting combination achieving perfect scores in accuracy, recall, precision, and F1 score, alongside an ROC-AUC value of 0.88. However, this model's slightly reduced ROC-AUC compared to others and its high computational cost highlight potential risks of overfitting and the need for significant resources. These findings underscore the practical potential of combining Bagging and Boosting with SVM for robust and accurate predictions. Limitations include the dataset's focus on a single league and the high resource requirements for ensemble methods. Future research could expand this approach to other sports and leagues, improve computational efficiency, and explore real-time predictive applications
Peningkatan Literasi Digital Bagi Masyarakat Desa Melalui Pelatihan Keamanan Siber Dasar Berbasis Komunitas Putrama Alkhairi; Agus Perdana Windarto; Solikhun; Anjar Wanto
JPM: Jurnal Pengabdian Masyarakat Vol. 6 No. 1 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jpm.v6i1.2529

Abstract

Low digital literacy in rural communities is a big gap for increasing cases of digital crime such as online fraud, phishing, and the spread of hoaxes. This community service activity aims to increase the understanding and awareness of the community of LK.I Sukamulia Village, Sinaksak Village, Tapian Dolok District, Simalungun Regency regarding the importance of cybersecurity through community-based basic training. The activity was carried out for five days, attended by 50 participants with various professional backgrounds such as farmers, traders, laborers, motorcycle taxi drivers, teachers, and online entrepreneurs. The method of implementing the activity consisted of the initial survey stage, module preparation, interactive training, direct practice, and evaluation of results. The material presented included an introduction to digital threats, how to create a secure password, the use of two-factor authentication, and the practice of using security applications. Evaluation was carried out through pre-tests and post-tests as well as observations during the activity. The results showed an average increase in participant understanding of 83% after participating in the training. In addition, the Village Digital Community was also formed as a sustainable step for local digital security education. This activity proves that a practical and contextual educational approach can increase community resilience to digital risks and can be replicated in other villages to expand the impact of community service.
Analysis of the Impact of Backpropagation Hyperparameter Optimization on Heart Disease Prediction Models Nita Syahputri; Putrama Alkhairi; Enok Tuti Alawiah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 4 (2025): August 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i4.6473

Abstract

Heart disease is a major global health issue, highlighting the need for early and accurate prediction to reduce complications and improve patient outcomes. The Backpropagation Neural Network (BPNN) is a widely used method for heart disease prediction, but its performance relies heavily on proper hyperparameter selection, including neuron count, activation function, optimizer, and batch size. This study analyzed the impact of hyperparameter optimization on BPNN performance. A standard BPNN model was compared with an optimized version, where key hyperparameters were fine-tuned to enhance predictive accuracy and stability. Both models were trained and tested on the same dataset, and their performance was evaluated using Accuracy, Precision, Recall, Mean Squared Error (MSE), and Mean Absolute Error (MAE). The results show that the optimized model achieves a slightly better accuracy (99.11% vs. 99.09%) and lower error rates (MSE and MAE of 0.0089 vs. 0.0091). It also demonstrates higher precision, reflecting an improved capability in correctly identifying heart disease cases. Although the performance gap was small, the optimized model showed a more balanced and consistent outcome. These findings highlight the importance of hyperparameter tuning for improving neural network models for medical prediction. This study contributes to the development of more accurate and reliable AI tools for the early diagnosis of heart disease. Future studies may apply advanced optimization techniques, such as Bayesian Optimization or Genetic Algorithms, and use larger and more diverse datasets to enhance model generalization.
Penerapan Metode Jaringan Saraf Tiruan Dalam Memprediksi Produksi Daging Domba Menurut Provinsi Listy Oktaviani; Sandy Erlangga; Bintang Aufa Sultan; Agus Perdana Windarto; Putrama Alkhairi
Journal of Computing and Informatics Research Vol 3 No 2 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/comforch.v3i2.992

Abstract

Prediction is the process of estimating future needs. This research aims to predict the amount of sheep meat production by province. Lamb is a source of protein which is also a high value commodity. However, along with the increase in lamb production in Indonesia, the level of lamb meat consumption in Indonesia has tended to fluctuate in recent years. Imports are the step most often taken by the government to meet domestic sheep meat needs. By using Artificial Neural Networks and the backpropagation algorithm, the amount of sheep meat production will be predicted based on provinces in order to determine steps to fulfill domestic sheep meat needs based on the amount of sheep meat consumption in the community. This research uses data from 2001 to 2022 with 1 target, namely data for 2023.
Analisa Metode Backpropagation Dalam Memprediksi Jumlah Perusahaan Konstruksi Berdasarkan Provinsi di Indonesia Muhammad Kurniawansyah; Rafiqotul Husna; Raichan Septiono; Agus Perdana Windarto; Putrama Alkhairi
Journal of Computing and Informatics Research Vol 3 No 1 (2023): November 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/comforch.v3i1.993

Abstract

This research aims to analyze the number of construction companies in Indonesia and gain an understanding of the trends and characteristics of the construction industry in that country. In this research, data related to the number of construction companies is analyzed using available sources such as government statistical reports, industry publications, and other secondary data sources. The data we use in this research is data on the number of construction companies by province in Indonesia from 2016-2021 which was taken from the website of the Central Statistics Agency (BPS) using the backprogation artificial neural network (JST) method. The analysis results show that the number of construction companies in Indonesia has increased significantly in recent years. It is hoped that this research will encourage strong economic growth and increasing investment in the infrastructure and property sectors has driven demand for construction services. In addition, government policies that support the construction sector, such as infrastructure development programs and regulations that facilitate foreign investment, also contribute to the growth in the number of construction companies. Apart from growth trends, this research also identifies several characteristics of the construction industry in Indonesia. The industry is dominated by small and medium-sized companies operating locally, although there are also large companies involved in large-scale projects. Competition in this industry is fierce, with companies vying to win construction contracts and develop a competitive advantage. The architectural models that we use in this research are 6 architectural models, of which the best architectural model will be obtained. The architectural models include 5-11-1-1 with an accuracy percentage of 61.8%, 5-12-1- 1 with an accuracy percentage of 70.6%, 5-14-1-1 with an accuracy percentage of 82.4%, 5-18-1-1 with an accuracy percentage of 64.7%, 5-20-1-1 with an accuracy percentage of 70.6%, 5-22- 1-1 with an accuracy percentage of 73.5%. So the best architectural model is obtained, namely the 5-12-1-1 model which produces an accuracy rate of 82.4%. with a Mean Square Error (MSE) of 0.00099997 with an error prone of between 0.001-0.05. These results are quite good in predicting the number of construction companies based on provinces in Indonesia