Claim Missing Document
Check
Articles

Found 3 Documents
Search

Heart Attack Risk Prediction Using Machine Learning: A Comparative Study of Decision Tree and K-Nearest Neighbors Hizbullah, Fauzi; Noorachmad Muttaqin, Alif; Andiharsa Sih Setiarto, Rahardian; Aulia Hakim, Rizki; Abdulmana, Sahidan
Electronic Integrated Computer Algorithm Journal Vol. 3 No. 1 (2025): VOLUME 3, NO 1: OCTOBER 2025
Publisher : Yayasan Asmin Intelektual Berkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62123/enigma.v3i1.98

Abstract

Heart disease, particularly heart attacks, is a leading cause of death worldwide, highlighting the importance of early detection and risk prediction. This study develops and evaluates machine learning models to predict heart attack risk using seven health-related attributes: age, marital status, gender, body weight category, cholesterol level, participation in stress management training, and stress level. The dataset, processed with the Orange Data Mining platform, was divided into training (66%) and testing (34%) sets. Two supervised algorithms, Decision Tree and K-Nearest Neighbors (K-NN), were implemented without extensive hyperparameter tuning. Model performance was evaluated using accuracy, precision, recall, and F1 score. The Decision Tree achieved the best results with 84.78% accuracy, 88.52% precision, 79.41% recall, and 83.72% F1 score, indicating its effectiveness in identifying at-risk individuals. Key predictors included age, stress level, and cholesterol, aligning with established medical findings. While the results are promising, limitations include a small dataset and limited algorithm scope. Future research should expand the dataset, include additional clinical features, and explore advanced algorithms to improve accuracy and reduce false negatives, enhancing applicability in preventive healthcare.
The Evaluating Customer Relationship Marketing Strategy on Customer Retention at DMKR Fashion Company Husaini, Galih Rashif; Lubis, Muharman; Andiharsa Sih Setiarto, Rahardian; Fauzan, Ratandi
Electronic Integrated Computer Algorithm Journal Vol. 3 No. 2 (2026): VOLUME 3, NO 2: APRIL 2026
Publisher : Yayasan Asmin Intelektual Berkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62123/enigma.v3i2.164

Abstract

Building and maintaining strong relationships with customers is essential for business sustainability, especially in an increasingly competitive market where customer loyalty can shift easily. Customer Relationship Management (CRM) has become an important strategic approach that allows companies to manage customer data, strengthen communication, and improve customer experiences. CRM also supports public relations activities by enhancing trust and long-term engagement. During the COVID-19 pandemic, business owners at Dakar, a local MSME in the batik fashion industry, faced significant uncertainty and were required to adapt quickly to changing customer needs and digital consumption patterns. Despite this challenge, the company continued to identify opportunities to strengthen customer loyalty and retention through various CRM-based strategies. This study examines how Dakar implements CRM and evaluates its impact on customer retention using qualitative methods supported by sales and customer behavior data. The results show that CRM contributes to better understanding customer preferences, improving service quality, and encouraging repeat purchases. Furthermore, CRM helps Dakar build emotional bonds with customers through product personalization, social engagement, and the integration of digital platforms. Overall, CRM plays a crucial role in supporting business resilience and customer loyalty in the post-pandemic era.
Brain Tumor Detection and Classification from MRI Images Using a Convolutional Neural Network Approach Andiharsa Sih Setiarto, Rahardian; Ahmad Zainul Fanani
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9610

Abstract

Brain tumors are a serious neurological disease that require rapid and accurate diagnosis to improve treatment success. However, conventional interpretation of brain MRI images is often time-consuming and highly dependent on radiologists’ expertise, which may lead to diagnostic inconsistency. This study aims to develop a brain tumor detection and classification model from MRI images using a Convolutional Neural Network (CNN) approach. The dataset consists of four classes, namely glioma, meningioma, pituitary, and no tumor. The research stages include data collection, image preprocessing, model training, and evaluation using accuracy, loss, precision, recall, and F1-score. The results show that the CNN model achieved a training accuracy of 1.0000 at the final epoch, while the testing phase produced an accuracy of 58.75% with a loss value of 1.9600. These findings indicate that the model was able to learn important patterns from MRI images, although the gap between training and testing performance suggests overfitting. This study contributes to the development of AI-based medical image classification for brain tumor identification and shows that CNN has potential as a supportive tool for assisting medical personnel in brain tumor diagnosis. Further improvements can be achieved through data augmentation, hyperparameter tuning, and optimization of model architecture.