JUPIK : Jurnal Penelitian Ilmu komputer

PENERAPAN ALGORITMA GENETIKA UNTUK PENJADWALAN MENGAJAR GURU (STUDI KASUS: SD NEGERI KUNCIRAN 7)

2025-07-16T13:44:57+07:00

Teacher scheduling in schools often faces various challenges that can disrupt the learning process. One of the main issues is the occurrence of schedule conflicts, especially when a teacher is assigned to teach multiple classes. At SD Negeri Kunciran 7, scheduling is still done using Microsoft Excel, which is time-consuming and prone to errors. To address this problem, this study implements a web-based scheduling system using the Genetic Algorithm. The Genetic Algorithm is chosen due to its ability to solve optimization problems involving multiple variables and constraints, such as the number of teachers, classes, subjects, and limited time slots. Through stages such as initial population generation, fitness evaluation, selection, crossover, and mutation, the system is able to produce optimal teaching schedules, minimize conflicts, and accelerate scheduling. The testing results show that this algorithm can be effectively used to support efficient and accurate scheduling.

PENGEMBANGAN SISTEM MANAJEMEN SURAT TERINTEGRASI DENGAN WORKFLOW DAN TANDA TANGAN DIGITAL UNTUK MENINGKATKAN EFISIENSI DALAM PROSES ADMINISTRASI DI SMK PERWIRA BANGSA

2025-07-08T17:03:44+07:00

Mail management is an essential part of administrative activities in educational institutions. However, at SMK Perwira Bangsa, the correspondence process is still handled manually, leading to several issues such as delayed distribution, filing errors, and high risks to document security. To address these problems, this research developed a web-based mail management system integrated with workflow automation and digital signatures using OpenSSL. The workflow automates the entire correspondence process, from document creation to distribution, while the digital signature ensures document authenticity and integrity through cryptographic technology. The system was developed using the waterfall methodology, covering stages of requirement analysis, system design, implementation, and testing through black-box testing. Test results showed that the system successfully improved administrative efficiency by accelerating letter distribution, reducing document management errors, and enhancing document security through digital signature validation. Additionally, the system includes a real-time document tracking feature to support transparency and administrative monitoring. The use of OpenSSL provides strong security guarantees for document authentication. This system is expected to serve as an effective digital solution for document management in educational institutions and can be adapted by other schools.

PENGEMBANGAN SISTEM PENDUKUNG KEPUTUSAN UNTUK MENENTUKAN KARYAWAN BERPRESTASI MENGGUNAKAN METODE ADDITIVE RATIO ASSESSMENT (ARAS) STUDI KASUS : PT BINTANG MARAGA LINTAS MEDIA

2025-08-06T16:45:56+07:00

Employees are a vital element in supporting the operations of PT. Bintang Maraga Lintas Media, especially technicians who are directly involved in fieldwork. The company provides monthly bonuses to outstanding employees; however, the evaluation process remains subjective, relying solely on the supervisor's opinion based on attendance and overtime, without considering other aspects such as completed work orders, loyalty, responsibility, and discipline. To address this issue, this study aims to develop a Decision Support System (DSS) based on the Additive Ratio Assessment (ARAS) method to assist in evaluating employees objectively, measurably, and transparently. ARAS is chosen for its ability to perform multi-criteria evaluations logically, taking into account the weight and type of each criterion in a balanced manner. The results of this research show that the developed system can effectively manage employee assessment data and generate accurate rankings of outstanding employees, thereby supporting a fairer evaluation process and encouraging increased motivation and performance among employees.

Prediksi harga mobil bekas menggunakan algoritma K-Nearest neighbor

2025-07-21T14:04:49+07:00

The used car market in Indonesia has shown significant growth, as people's need for more economically priced vehicles increases. However, inconsistent price variations often make it difficult for consumers to determine the fair value of a used car. This research aims to build a used car price prediction model using the K-Nearest neighbor (KNN) algorithm.

The dataset used amounts to 1,079 used car data with selected variables that affect the price of cars such as toyota, honda, mitsubishi brands taken from the oto.com website with data scraping techniques using octoparse, with features such as brand, model, kilometer, location, transmission, type, year, engine size and price.

This research follows the CRISP-DM approach which includes the stages of business understanding, data understanding, data preparation, modeling, and evaluation. Model evaluation is performed using three metrics, namely Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). by finding the best K value based on the division of 80% testing & test datasets. The results show that the KNN algorithm is able. to predict used car prices with a relatively low error rate. This model is expected to help consumers and automotive industry players in estimating used car market prices more accurately and data-based.

IMPLEMENTASI APLIKASI PENILAIAN SISWA EKSTRAKURIKULER PRAMUKA TERBAIK BERBASIS ANDROID MOBILE DENGAN METODE SMART PADA SD RAWABUNTU 3

2025-07-08T15:16:29+07:00

The rapid development of technology has brought major changes in everyday life, including in the assessment process. Manual assessment with a large amount of data has a high risk of calculation errors, while there are still many other determining factors that can be considered in selecting the best scout extracurricular students.

To overcome this, researchers want to develop an android-based system that implements a Decision Support System (DSS) with the SMART (Simple Multi Attribute Rating Technique) method to provide a more structured and objective assessment, so that it can help teachers in conducting transparent assessments. The research methods used include interviews with scout teachers at SD Bawabuntu 3, field observations to understand system needs and literature studies to collect data.

The results of the study indicate that the application created can help facilitate teachers in assessing scout extracurricular students at SD Rawabuntu 3. The results of the analysis show that the system developed received a positive response from users, with the results of the Likert scale calculation of 82% indicating a high level of satisfaction with the assessment application, from 30 respondents.

PREDIKSI HARGA EMAS UNTUK PENGAMBILAN KEPUTUSAN INVESTASI MENGGUNAKAN ALGORITMA CART (CLASSIFICATION AND REGRESSION TREE)

2025-08-08T09:30:35+07:00

The dynamic fluctuations in gold prices, influenced by various global economic factors, make gold price prediction an important topic in finance and investment. This study aims to analyze and predict gold prices using the Classification and Regression Tree (CART) algorithm, which is a decision tree–based machine learning method. Historical gold price data from 2013 to 2023 were used as training data, while data from 2024 to 2025 were used for testing. The research process includes preprocessing, data splitting, CART model construction, and performance evaluation using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The results indicate that the CART model is capable of providing reasonably accurate and effective predictions of gold prices, making it a viable tool for investment decision-making. With its simplicity and interpretability, CART helps uncover patterns in gold price data and offers valuable estimates for investors and market participants.

PREDIKSI HARGA MINYAK KELAPA SAWIT MENTAH (CRUDE PALM OIL) MENGGUNAKAN METODE DECISION TREE

2025-07-22T12:59:52+07:00

Crude palm oil (CPO) is one of Indonesia's main export commodities that has high economic value, but its price is very volatile due to various factors such as global market conditions, climate, and political policies. This research aims to build a CPO price prediction model using the Classification and Regression Tree (CART) algorithm, a form of Decision Tree method known for its ease of interpretation and high accuracy. The data used is historical CPO price data obtained from the Investing.com website within the last 10 years. In the process, the data is divided into training and testing data. The model is evaluated using metrics such as MAE (Mean Absolute Error), RMSE (Root Mean Square Error), and R² (R-Square). The results showed that the Decision Tree method with the CART algorithm was able to provide an accuracy of 93.101%, with an R² value of 0.937, RMSE of 0.062, and MAE of 0.046. This proves that the CART algorithm is suitable for predicting CPO prices and can be a decision-making tool for industry players.