JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP)

Implementasi Data Mining Untuk Mengklasifikasi Hasil Belajar Siswa/i Dengan Metode Naïve Bayes

2024-07-19T07:43:33+00:00

This study aims to classify student learning outcomes and determine the accuracy of the research methods. The research was conducted at MAS Amaliyah Sunggal in 2024. This research applies data mining using the Naïve Bayes algorithm method and testing the accuracy of the Naïve Bayes method with RapidMiner. The data used consists of secondary data obtained directly from the school and data from distributing questionnaires. The population is all third-grade high school students T.A. 2023/2024, which amounted to 151 people. The sampling technique used is simple random sampling with a sample size of 60 people, which will be used as a dataset. The attributes used amounted to 10 and 1 class attribute for classification. Data analysis is done with the Bayes theorem equation with 60 training data and 1 testing data. The analysis results show that the highest probability value is in the P (H = Very Good) class of 0.4061516, which can be concluded by the classification of learning outcomes on report cards T.A. 2023/2024, categorized as very good. Based on the results of testing the level of accuracy of the Naïve Bayes method with RapidMiner using the provisions of 70% training data and 30% testing data, it shows an accuracy value of 94.44%, which means that the Naïve Bayes method is good enough to be used to classify student learning outcomes.

Analisis Interaksi Pengguna Sosial Media Sekolah di Palembang Berdasarkan Topik dengan hLDA dan SVM

2024-09-21T03:45:49+00:00

Instagram is a social media that can be used to promote schools by sharing various documentation of school activities, but schools still have difficulty analyzing engagement to find out the audience's interests. This software development aims to identify topics from captions and analyze the like engagement of each topic. 3,900 caption data were collected from five school Instagram accounts in Palembang with Instaloader. The hLDA algorithm is implemented to identify topics from the caption data, and generate a new dataset that gives the topic information of each caption. This dataset was then classified using SVM and SVM-SMOTE. SMOTE is used to overcome class imbalance in order to improve classification results. In the classification process, the dataset is divided into 70% for training and 30% for testing, with evaluation based on F1-Score. The best results were obtained by SVM-SMOTE, with the best F1-Score value from hLDA 3 Level Dataset (13 labels), reaching 95.68% and the lowest value from hLDA 5 Level Dataset (8 labels), reaching 79.43%. Datasets that have more topics give better classification results. Based on the number of likes for each topic in the hLDA 3 Level Dataset, the most popular topic is topic 11, which includes school facilities, student uniforms, and entertainment events. This information can help schools further develop the most liked topics and improve the less liked topics.

Analysis of Credit Card Usage Against Business Segmentation Using Agglomerative Hierarchical Clustering

2024-10-25T03:01:56+00:00

This study analyzes credit card usage patterns and their impact on business segmentation using the Agglomerative Hierarchical Clustering (AHC) method. AHC was chosen because of its ability to group data in detail, especially for datasets with hierarchical relationships. The dataset includes balances, credit limits, monthly payments, and late history. The study aimed to identify high-risk credit card users in payments so that financial institutions can develop more effective risk management strategies. This study successfully identified customer groups with varying payment risks and offered solutions like debt consolidation and flexible payment programs. These findings contribute to the credit card industry in customer segmentation and credit risk management in the credit card industry.

ANALISIS KOMPARASI ALGORITMA C4.5, NAIVE BAYES DAN K-NEAREST NEIGHBOR UNTUK MEMPREDIKSI KETEPATAN WAKTU LULUS MAHASISWA

2024-09-21T04:38:38+00:00

The problem of student graduation in higher education is one of the most essential things in showing the quality of learning in higher education, especially on the Sumbawa University of Technology (UTS) campus. The purpose of this research is to compare three algorithm methods, namely C4.5, Naive Bayes, and K-Nearest Neighbor (KNN), which is better at predicting the timeliness of student graduation using RapidMiner tools with the Knowledge Discovery in Database (KDD) method. The dataset used by the three classifications is 330 Informatics student data. Based on the comparison of the three algorithms with data splitting techniques, it is found that the C4.5 algorithm produces an accuracy of 73.49% with a precision of 64.62% and a recall of 41.89%. The Naive Bayes algorithm produces an accuracy of 72.79% with a precision of 64.06% and a recall of 38.11%. Meanwhile, the K-Nearest Neighbor (KNN) algorithm produces an accuracy of 76.08% with a precision of 73.11% and a recall of 41.92%. From the comparison of the three algorithms, the most appropriate for predicting the timeliness of student graduation is the K-nearest neighbor (KNN) algorithm.

Klasifikasi Tingkat Kematangan Buah Kersen Dengan Menggunakan Support Vector Machine

2024-11-11T04:30:41+00:00

Kersen fruit, native to Southern Mexico and often found in Indonesia, has health benefits that attract people. It is round with a diameter of 1-1.5 cm, yellowish green in color when young, and turns red when ripe. Determining the maturity level of kersen, which has been done manually, is essential for people to consume good quality fruit. This study aims to simplify the identification of Kersen fruit maturity through image processing using the Support Vector Machine (SVM) method with a parameter value of C-25. The test results show that this method achieves the best accuracy level of 72% in identifying the ripeness of kersen fruit, so it can be an effective solution in making it easier for people to determine the level of fruit ripeness.

Implementasi Algoritma K-Means Menggunakan RapidMiner untuk Klasterisasi Data Obat Pada Rumah Sakit Royal Prima

2024-11-12T03:59:58+00:00

Efficient management of drug data is a crucial element in hospital operations to ensure the availability and proper use of medications. This research aims to implement the K-Means clustering algorithm using RapidMiner software to cluster drug data at RS Royal Prima. The dataset includes information such as drug type, category, price, and intake frequency. The clustering process begins with data preprocessing stages, such as cleaning and normalization. The optimal number of clusters is determined using the elbow method and silhouette analysis. The clustering results show that drug data can be grouped into several large clusters based on specific characteristics. This analysis helps identify patterns of drug use that can support clinical decision-making and improve inventory management. This implementation demonstrates that using RapidMiner to cluster pharmaceutical data is effective and provides valuable insights to enhance hospital operations.

Analisis Sentimen Kepuasan Pengguna Media Sosial Dengan Menggunakan Data Mining Dan Matlab

2024-11-12T04:37:56+00:00

In today's digital era, social media has become an integral part of many people's daily lives, with platforms such as Twitter, Facebook, Instagram, and TikTok being used to share opinions, experiences, and satisfaction or dissatisfaction with various products and services. This research aims to analyze social media user satisfaction sentiment using data mining techniques and Matlab. With data collected from several social media platforms, this research identifies and categorizes user sentiment as positive, negative, or neutral. The methods used include data collection, pre-processing, feature extraction, model building, and model evaluation. The results show that data mining techniques and Matlab effectively classify user sentiment, providing valuable insights for companies to improve their quality and performance based on social media user feedback.