Kurawal - Jurnal Teknologi, Informasi dan Industri

ANALISIS PERAMALAN (FORCASTING) PENJUALAN DENGAN MENGGUNAKAN WEIGHTED MOVING AVERAGE PADA INDOMARET GRAND TAMAN ROYAL TANGERANG

Suwanda Aditya Saputra — Mon, 30 Mar 2026 00:00:00 +0000

Sales forecasting is a crucial aspect of retail management to prevent overstocking or understocking, which can impact customer satisfaction and operational efficiency. This study aims to analyze and measure the accuracy of the Weighted Moving Average (WMA) method in forecasting the sales of five main products at Indomaret Grand Taman Royal Tangerang, namely Chitato, Aqua 600 ml, 5 kg Rice, 5 kg Lifebuoy, and Djarum Super. The WMA method is selected because it gives greater weight to more recent historical data, resulting in predictions that are more responsive to market trend changes. The study uses monthly sales data from the past six periods and a WMA weight ratio of 3:2:1. The forecasting results show high accuracy, with the Mean Absolute Percentage Error (MAPE) values as follows: Chitato 6.28%, Aqua 600 ml 4.51%, 5 kg Rice 7.12%, 5 kg Lifebuoy 5.89%, and Djarum Super 6.03%. The overall average MAPE is 5.97%, indicating very good forecasting accuracy. These findings suggest that the WMA method is effective for sales forecasting and can serve as a decision-making foundation for inventory management and retail sales strategies.

E-Warung Mobile: UI/UX Innovation to Promote Digitalization of Small Businesses

Mon, 30 Mar 2026 00:00:00 +0000

Digital transformation in the small business sector, particularly traditional warung (small retail shops), has become an urgent necessity amid the rapid advancement of information technology. However, low levels of digital literacy and limited access to user-friendly applications remain significant barriers to technology adoption. This study aims to design and evaluate the quality of the User Interface (UI) and User Experience (UX) of the E-Warung Mobile application as an effort to support the digitalization of small businesses. The research method employed is a design thinking approach, which consists of the stages of empathize, define, ideate, prototype, and testing. User experience evaluation was conducted using the User Experience Questionnaire (UEQ), which measures six main aspects: Attractiveness, Perspicuity, Efficiency, Dependability, Stimulation, and Novelty. Data were collected through questionnaires distributed to 25 respondents who are small business owners or prospective users, after they completed a series of task scenarios using the application prototype. The analysis results indicate that the mean scores for each UEQ aspect are as follows: Attractiveness (1.75), Perspicuity (1.68), Efficiency (1.72), Dependability (1.65), Stimulation (1.80), and Novelty (1.60) on a scale ranging from -3 to +3. Based on the UEQ benchmark, all aspects fall within the “above average” to “good” categories, indicating that the application demonstrates high usability, is easy to understand, efficient, and capable of delivering a positive user experience. In conclusion, this study shows that the implementation of user-centered UI/UX design, quantitatively evaluated using UEQ, can enhance the quality of user interaction and has the potential to promote broader adoption of digital technology among small businesses

Analisis Usability Aplikasi E-Dosen UIN Raden Fatah Palembang Menggunakan Metode System Usability Scale (SUS)

Reni Septiyanti, Erni Patmawati, Muhamad Son Muarie — Mon, 30 Mar 2026 00:00:00 +0000

The E-Dosen application is a program developed by the Internal Audit Unit (Satuan Pengawas Internal/SPI) of UIN Raden Fatah Palembang to support lecturers’ performance in providing better services; however, since the application has only recently been implemented, its relatively complex interface has caused confusion for some lecturers, and the large number of features tends to slow down the reporting process. This study aims to evaluate the usability of the E-Dosen application using the System Usability Scale (SUS) method, which includes the variables of effectiveness, efficiency, and satisfaction. Random sampling was employed, involving 240 lecturers as respondents for the SUS assessment and 10 additional lecturers for task scenario testing. The results indicate that the effectiveness level reached 85%, the efficiency value was 0.02877 goals per second showing that tasks could be completed in an average time of 35 seconds per task and user satisfaction, based on a SUS score of 71, fell into the “Good” category, corresponding to Grade C and an acceptable usability scale. Overall, the E-Dosen application is generally usable, although further development is required, particularly in simplifying workflows and the user interface, to enhance speed and user satisfaction.

Optimalisasi SIAKAD Berbasis Mobile melalui Redesign Antarmuka dan Pengalaman Pengguna dengan Pendekatan User-Centered Design

Mon, 30 Mar 2026 00:00:00 +0000

The rapid development of mobile technology encourages educational institutions to provide academic systems that are easily accessible and efficient for users. However, many academic systems still have unintuitive interfaces and suboptimal user experiences, which hinder effective usage. This study aims to optimize the academic system on a mobile platform through a redesign of the User Interface (UI) and User Experience (UX) with a user-centered approach. The method used in this study is the User-Centered Design (UCD) approach, which involves users in every stage of the design process, including requirements analysis, wireframing, prototyping, and usability evaluation. Data were collected through observations, interviews, and questionnaires involving 50 respondents who are active users of the academic system. The results show a significant improvement after the redesign. The System Usability Scale (SUS) score increased from 62.5 (marginal category) to 85.2 (excellent category). The task success rate improved from 70% to 92%, while the average task completion time decreased by 35%. In addition, user satisfaction increased by 40% based on questionnaire results compared to the previous system. These findings indicate that implementing a user-centered UI/UX redesign significantly improves usability, efficiency, and user satisfaction in mobile-based academic systems

ANALISIS SENTIMEN TOKOH PUBLIK TERHADAP RESPONS DEMO MENGGUNAKAN ALGORITMA DECISION TREE

renata ananda sofiarti — Mon, 30 Mar 2026 00:00:00 +0000

This study aims to analyze the responses of public figures to demonstrations in Indonesia using the decision tree algorithm as the main method of sentiment classification. This study was applied to identify patterns of public sentiment towards statements and influential factors in shaping public opinion. Data analysis using the keyword demonstration issue taken from YouTube media resulted in 999 public review datasets, then the reviews were processed using RapidMiner. The analysis process included data cleaning, tokenization, removing unnecessary words, converting words to their basic form, and labeling sentiments into negative and positive. Despite the sentiment, many public reviews were still negative towards the responses of public figures. This study also used the Decision Tree Model to classify data based on the occurrence of dominant keywords. The results of this study indicate that the decision tree algorithm achieved an accuracy of 92.88%. Decision trees are very effective and quite good when used in analyzing public perceptions of demonstration issues and government communication strategies that are more adaptive and able to reveal public sentiment. This study also contributes to the development of political sentiment analysis in Indonesia, especially understanding the dynamics of public opinion on social media. Research from social media, especially YouTube, is a relevant resource for finding reviews in real time. In addition, this research can serve as a reference for the government in developing more responsive strategies to public needs in the current digital era.

Analisis Komparatif Kinerja LSTM, BiLSTM, dan LSTM-AM dalam Prediksi Harga Saham Syariah

Mon, 30 Mar 2026 00:00:00 +0000

The continuously evolving Sharia stock market necessitates more accurate price modeling due to high volatility, regime shifts, and outliers that frequently disrupt investment decision-making processes. This study aims to comparatively evaluate the performance of three deep learning algorithms—LSTM (Long Short-Term Memory), BiLSTM (Bidirectional LSTM), and LSTM-AM (LSTM with Attention Mechanism)—in predicting Sharia stock prices. The research method utilizes daily closing price data from five Indonesian Sharia-compliant issuers (ANTM, ERAA, KLBF, SMGR, and WIKA) spanning the period of December 2016 to December 2021. The data underwent preprocessing using Robust Scaling and was structured into time series with a 60-day window. Model evaluation was conducted via window-based cross-validation with the results show that BiLSTM delivered the best performance with an average MAPE of 9.41% and RMSE of 249.956. This performance was followed by LSTM (MAPE 11.87%) and LSTM-AM as the lowest (MAPE 19.58%). These findings provide a clear understanding of the effectiveness of each architecture in predicting dynamic Sharia stock prices, indicating that increasing model complexity (LSTM-AM) does not always guarantee better accuracy in this domain. Consequently, BiLSTM can be considered the superior model for more stable prediction.