cover
Contact Name
Galih Hermawan
Contact Email
galih.hermawan@yahoo.co.id
Phone
-
Journal Mail Official
komputa@email.unikom.ac.id
Editorial Address
-
Location
Kota bandung,
Jawa barat
INDONESIA
KOMPUTA : Jurnal Ilmiah Komputer dan Informatika
ISSN : 20899033     EISSN : 27157849     DOI : 10.34010
Core Subject : Science,
Jurnal Ilmiah KOMPUTA (Komputer dan Informatika), adalah wadah informasi berupa hasil penelitian, studi kepustakaan, gagasan, aplikasi teori dan kajian analisis kritis di bidang kelimuan Komputer dan Informatika. Terbit dua kali dalam setahun pada bulan Maret dan Oktober.
Arjuna Subject : -
Articles 216 Documents
Implementasi Algoritma Neural Collaborative Filtering Menggunakan TensorFlow Sebagai Rekomendasi Buku Pada Aplikasi Praktikum Program Studi Sistem Informasi Fariz Aisyar Dafin, Ahmad; Irsyad, Akhmad; Rivani Ibrahim, Muhammad
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v14i2.16724

Abstract

Low literacy levels among students pose a significant challenge in supporting academic activities, especially in practical courses in the Information Systems Study Program. This study aims to develop a personalized and relevant book recommendation system using the Neural Collaborative Filtering (NCF) algorithm implemented in TensorFlow and deployed through FastAPI. The dataset used is Book-Crossing, containing over one million user-book interactions. The development follows the CRISP-DM methodology, covering business understanding, data preparation, modeling, and deployment. The NCF model utilizes embedding and dense layers to learn complex user-item interactions. Evaluation shows that the model achieves MAE of 0.3133 and MSE of 0.1531 on training data. The system was successfully deployed and validated through unit testing, capable of providing the top five book recommendations based on user input. The result demonstrates the effectiveness of deep learning approaches in enhancing student literacy through adaptive and integrated recommendation systems.
Prediksi Kelayakan Pemberian Kredit dengan Algoritma Backpropagation Agustin, Dhea Ayu; Febri; Arianto, Dede Brahma
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v14i2.17660

Abstract

One of problems in lending activities is credit risk due to errors in selecting debtors. In this study, the backpropagation algorithm will be used to develop a prediction calculation system that uses features such as age, gender, marital status, occupation, income, number of dependents, loan amount, time period, collateral, home ownership, and loan purpose to predict creditworthiness. To determine the accuracy level of built, a model evaluation was conducted. The model evaluation was carried out using a confusion matrix, but before that, the data used was separated by ratio of 80 : 20, namely 80% for training and 20% for testing. With the best hyperparameters from several hyperparameter tuning scenarios, the scenario used for implementation in the system is screnario model 5 with 2 hidden layers (50 and 25 neurons), ReLU activation function, learning rate 0.001, 500 epochs, batch size 64, adam optimizer, and early stopping, resulting in an accuracy of 98.18% and a f1 Score of 98.33%. These values are excelent amd show that system created can be used as a reference in predicting creditworthiness. In addition, these values show that the backpropagation model is free from overfitting.
Pengaruh Fitur Tambahan untuk Klasifikasi KepribadianMyers-Briggs Type Indicator (MBTI) Menggunakan SVM Widiastuti, Nelly Indriani; Dewi, Kania Evita; Sidik, Muhammad Abdul Rohman
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v14i2.17796

Abstract

This study examines the effect of adding metadata feature on the effectiveness of the Support Vector Machine (SVM) algorithm in classifying personality types based on the Myers–Briggs Type Indicator (MBTI) indicators, using data from Indonesian-language X (Twitter) posts as a representation of users' digital expressions. The developed model integrates two main feature categories: textual features extracted using the Term Frequency-Inverse Document Frequency (TF-IDF) method, and metadata features that reflect users' social interaction patterns, such as the number of retweets, likes, followers, and publication time. These features are considered capable of representing user behaviour dynamics more comprehensively. After the dataset is cleaned, pre-processing, feature extraction, and encoding are performed. Classification is then performed using SVM. This study employed four systematically designed testing scenarios: two scenarios utilised pure text data, while the other two combined social metadata features. Each scenario was tested both before and after the hyperparameter tuning process to optimise model performance. The evaluation was conducted using accuracy and F1-score metrics to measure the accuracy and balance of the classification model. The results of the experiment showed that the combination of social media metadata features consistently improves classification performance, with accuracy increasing by 2–6% and F1-score by 2–8% compared to text-based models alone. These findings confirm that social media metadata contributes significantly to enriching feature representation, thereby improving the precision, generalisation, and stability of models in identifying the personality types of social media users.
Pengelompokan Mahasiswa Berdasarkan Capaian Pembelajaran Lulusan Menggunakan K-Means Clustering di Program Studi Teknik Informatika UNIKOM Agustia, Richi Dwi; Finandhita, Alif
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v14i2.17932

Abstract

The Outcome-Based Education (OBE) curriculum emphasizes learning outcomes as benchmarks of graduate competence. This study in the Informatics Engineering Program at UNIKOM aims to cluster students based on the fulfillment of Learning Outcomes (CPL) to more accurately identify graduate professional tendencies. The dataset consists of 336 OBE cohort students, 58 core courses, and 312,793 academic records. The K-Means clustering method was applied with preprocessing steps including removal of missing values, duplicates, and non-relevant general courses (MKDU). Cluster validity was evaluated using the Davies–Bouldin Index (DBI) and Silhouette Score. The results yielded four clusters: (1) hardware integration and technology consultancy, (2) basic programming and data management, (3) systemic and managerial competence in information systems, and (4) data analytics, business intelligence, and predictive modeling. Evaluation metrics (DBI = 1.18; Silhouette Score = 0.27) indicate reasonably valid clustering despite intra-cluster variation. This study provides a strategic contribution to curriculum development in the Informatics Engineering Study Program at UNIKOM, particularly in aligning graduate profiles with the demands of the digital technology-driven workforce.
Prediksi Curah Hujan Berbasis Regreasi PolinomialMenggunakan Data Historis Cuaca Diyani, Dela Putri; Sriwijayanti, Erlis Rahayu; Gustrianysah, Rendra
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v14i2.16331

Abstract

Rainfall is one of the most variable and difficult-to-predict climate factors, especially in tropical regions like Indonesia. This uncertainty can significantly impact various sectors such as agriculture, forestry, and disaster mitigation. This study aims to develop a rainfall prediction model based on polynomial regression using historical weather data from Southeast Sulawesi. The dataset includes average temperature, average humidity, and sunlight duration, obtained from BMKG and processed using linear interpolation to handle missing values. Polynomial regression was chosen due to its ability to capture non-linear relationships between weather variables and rainfall. Model evaluation using Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) resulted in values of 41.84, 4.67 and 4.85, respectively, indicating relatively low prediction error. Therefore, polynomial regression proves to be an effective, accurate, and computationally efficient method for short-term rainfall forecasting.
Analisis Stres Akademik pada Mahasiswa yang Bekerja dengan Menggunakan Metode Fuzzy Logic(Studi Kasus: Mahasiswa Prodi Sistem Informasi Unpam Kampus Serang) Stevanes, Stevanes; Septiani, Selly
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v14i2.17730

Abstract

Students who work are at risk of experiencing higher academic stress due to the dual burden of work and study. This study aims to analyze the level of academic stress among students in the Information Systems Program for working adults (Regular C Saturday) at UNPAM Serang using a fuzzy logic approach. The method used is the Mamdani Fuzzy Inference System through five main stages: fuzzification, rule base formation, inference process, defuzzification, and result interpretation. The testing was conducted through MATLAB application calculations and manual calculations, with accuracy evaluated using the Mean Absolute Percentage Error (MAPE). The test results showed that the difference in results between the manual method and MATLAB was very small, with a MAPE value of 0.843%, indicating that MATLAB has a very high accuracy rate in classifying academic stress into the categories of no stress, low stress, moderate stress, and high stress. These findings prove that fuzzy logic is effective for measuring psychological variables that are difficult to capture conventionally. Additionally, this approach has the potential to be developed as a tool for early detection of psychological conditions among students in higher education settings.

Filter by Year

2012 2025


Filter By Issues
All Issue Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 1 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 13 No 2 (2024): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 13 No 1 (2024): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 12 No 2 (2023): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 12 No 1 (2023): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 11 No 2 (2022): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 11 No 1 (2022): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 10 No 2 (2021): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 10 No 1 (2021): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 9 No 2 (2020): SettingsVol 9 No 2 (2020): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 9 No 1 (2020): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 8 No 2 (2019): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 8 No 1 (2019): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 7 No 2 (2018): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 7 No 1 (2018): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 6 No 2 (2017): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 6 No 1 (2017): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 5 No 2 (2016): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 5 No 1 (2016): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 4 No 2 (2015): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 4 No 1 (2015): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 3 No 2 (2014): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 3 No 1 (2014): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 2 No 2 (2013): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 2 No 1 (2013): Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 1 No 2 (2012): Komputa : Jurnal Ilmiah Komputer dan Informatika More Issue