Article Per Year (5 Year)
p-Index From 2021 - 2026
0.835
P-Index
This Author published in this journals
All Journal Brilliance: Research of Artificial Intelligence
Rahmat Irsyada
Politeknik Negeri Subang, Indonesia
Decision Sciences, Operations Research & Management Mathematics Other

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Profit Prediction for Skincare Resellers Using the Exponential Smoothing Method Nita Cahyani; Rahmat Irsyada; Azharil Firman; Fatuh Inayaturohmat; Retta Farah Pramesti
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6585

Abstract

This research elucidates the application of the exponential smoothing method in forecasting profit figures for Lutfia MS Glow Skincare. This method was chosen due to its capability to adapt data using the alpha value, along with continual refinement based on exponentially smoothed historical averages. With an explanatory purpose, the study collected profit data from 2020 to 2022 at Lutfia MS Glow Skincare. The single exponential smoothing technique was employed to develop a profit prediction system, enabling the identification of sales trends and evaluation through metrics like Mean Absolute Error (MAE) and Mean Squared Error (MSE). The approach offers simplicity in implementation while providing relatively accurate results, especially for short-term forecasting. This makes it particularly useful in retail and skincare business contexts, where sales figures can be volatile due to seasonal demands or market fluctuations. By utilizing exponential smoothing, the research helps reduce forecasting errors and provides actionable insights for business planning. The result of the analysis showed a reasonably low error margin with a Mean Absolute Percentage Error (MAPE) of 3.65%, indicating high prediction accuracy. The research outcomes furnish skincare resellers and decision-makers with practical guidance in planning inventory, managing supply chains, and executing marketing strategies, ultimately supporting better data-driven decisions in a competitive industry.
Integrated Community-Based Disaster Response Information System: A Case Study of the Subang Regency BPBD Mohammad Iqbal; Erick Febriyanto; Rahmat Irsyada
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6985

Abstract

Subang Regency is an area highly prone to natural disasters such as floods, landslides, and strong winds. In emergency situations, the absence of an efficient and integrated reporting system greatly hinders Badan Penanggulangan Bencana Daerah (BPBD) in carrying out rapid responses, evacuations, and aid distribution. If not addressed promptly, public safety and the effectiveness of disaster management will remain at risk. Therefore, a disaster mitigation application system is needed that allows the community to quickly report disasters through photos, videos, and descriptions directly integrated with the BPBD dashboard. This application is equipped with multi-channel notifications via WhatsApp, SMS Gateway, and alarms, as well as an AI-based heatmap analytics system to predict potential disasters using historical data and weather information from BMKG. In addition, BPBD administrators can verify disaster reports by checking personal biodata linked to the reporter’s account. The system development method applied is Agile Development, which includes observation, planning, design, development, testing, and deployment, enabling intensive collaboration and rapid system iterations based on field feedback. With this system, BPBD Subang is expected to be more responsive and resilient in facing disasters.
Implementation of Least Square Method to Predict Crime in Indonesia Based on the Web Nita Cahyani; Rahmat Irsyada; Diva Anggi
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7424

Abstract

This study was initiated by the need to apply the Least Square method to project the number of crimes in Indonesia using historical data from 2018 to 2022. Crime is a crucial issue in maintaining public security and supporting law enforcement, so accurate prediction results can assist the government in formulating public policies and optimizing resource use. The main problem of this study is how to apply the Least Square method to predict various categories of crimes in Indonesia, such as crimes against life, physical violence, morality, individual freedom, property rights with or without violence, and narcotics crimes. The purpose of this study is to develop a prediction model that can provide an accurate picture of future crime trends. The Least Square method was chosen because it can minimize prediction errors and process data with diverse variations, resulting in more stable and reliable estimates. The data used covers various types of crimes within the study period, with accuracy checked through the Mean Absolute Percentage Error (MAPE) value. The results show that the Least Square method is able to produce highly precise predictions with a MAPE value of 1.21%, thus proving effective in predicting crime rates in Indonesia with a very low error rate.
Family Hope Program Recipient Determination System Using The Naive Bayes Method Rahmat Irsyada; Nita Cahyani; M Rif’an Fawajul Mu’afa; Chepy Perdana; Erick Febriyanto
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.6362

Abstract

Poverty is still a problem that Indonesian people continue to face. To achieve prosperity and social justice for all Indonesian citizens, poverty can be considered a situation where a person does not have the ability to fulfill their basic needs, such as food, shelter, clothing, has a low income, has limited access to education, and has work skills. which is inadequate. The government, as a policy maker, has made various efforts to reduce poverty, one of which is through the Family Hope Program (PKH). However, in its implementation, the distribution of PKH assistance still faces problems in terms of targeting accuracy. To overcome this problem, a system is needed that can provide recommendations about who is worthy of receiving PKH assistance. One approach that can be used is a decision support system (DSS) using the Naïve Bayes method. Naïve Bayes is an algorithm used for text classification and is a Machine Learning method that focuses on calculating probability and statistics to predict future probabilities based on past experience. With the help of SPK, this system is able to provide recommendations about who should receive assistance. PKH is based on criteria such as school children, toddlers, pregnant women, the elderly and people with disabilities. Test results using the Naïve Bayes method with Confusion Matrix calculations show an accuracy level of 75%. Next, a comparison was carried out with testing using Cross Validation, which showed an increase in accuracy compared to previous testing without using 10-fold Cross Validation.
Performance Comparison of SelectKBest and Permutation Importance in Feature Selection for Diabetes Prediction Nita Cahyani; Rahmat Irsyada
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.6507

Abstract

This study evaluates the effectiveness of two feature selection methods, namely the statistics-based SelectKBest and the model-based Permutation Importance, in improving the performance of classification algorithms for diabetes prediction. A dataset consisting of 17 clinical and demographic features was used to train 11 machine learning algorithms with two subsets of selected features. Performance evaluation used accuracy, precision, recall, F1-Score, ROC AUC, and training time. Based on the results, the SelectKBest method was able to improve the performance of Random Forest with an accuracy of 82.7%, a precision of 0.8, a recall of 0.5, and an F1-Score of 0.615. Meanwhile, the Permutation Importance method showed more consistent performance, with six models including Random Forest, K-Nearest Neighbors, and Quadratic Discriminant Analysis (QDA) achieving an accuracy of up to 86.2%. QDA stood out with the highest ROC AUC of 0.887, indicating better class detection capabilities. These findings underscore the superiority of Permutation Importance in selecting relevant and varied features, including demographic factors, thereby improving overall prediction accuracy. In practice, Random Forest with SelectKBest is recommended for applications requiring fast and interpretable models, while QDA and Gradient Boosting with Permutation Importance are recommended for those requiring high accuracy and sensitivity. This study strengthens the foundation for developing more accurate and applicable diabetes prediction models across various contexts.
Co-Authors Azharil Firman Chepy Perdana Diva Anggi Erick Febriyanto Fatuh Inayaturohmat M Rif’an Fawajul Mu’afa Mohammad Iqbal Nita Cahyani Retta Farah Pramesti