Journal of Applied Business and Technology

Transfer Learning Model Evaluation on CNN Algorithm: Indonesian Sign Language System (SIBI)

Deny Jollyta — 2025-05-31

In Indonesia as much as elsewhere, the deaf can communicate using sign language. The Indonesian Sign Language System (SIBI) is one of the sign language systems used in Indonesia. A model produced by the Convolutional Neural Network (CNN) method can be used in computer science for the recognition of sign language. By using the Transfer Learning paradigm, CNN's performance may be enhanced. However, not many researches have been conducted to assess the effectiveness of transfer learning on sign language models, particularly those that use the TensorFlow library. In fact, the evaluation results can influence the selection of the transfer learning model together with CNN. This study aims to evaluate the efficacy of using the CNN model for SIBI sign language through Transfer Learning. The data used are images of 24 SIBI alphabets and are processed through the TensorFlow library. The images will be recognized through the transfer learning performance of 6 models, namely VGG16, VGG19, Resnet50, Desenet121, Inception-V3 and MobileNet-V2. The results of the study found that through the TensorFlow library, Mobilenetv2 had the highest accuracy of 78% after 20 epochs.

The Influence of Trust on Purchase Decisions of Muslim Fashion Products in Pekanbaru City with Ar-Ridho as a Mediating Variable on Generation-Z in Pekanbaru City

Yusnidar Yusnidar — 2025-05-31

This study aims to analyze the influence of trust on purchasing decisions for Muslim fashion products in Pekanbaru City with ar-ridho as a mediating variable. This study responds to the increasing trend of consumption of Muslim fashion products among religious urban communities. Using a quantitative approach, indicators for each variable were developed based on previous literature and empirical data. The number of samples collected and eligible for analysis in this study was 112 Respondents. The results showed that trust has a significant influence on purchasing decisions, and ar-ridho strengthens the relationship as a mediating variable. Muslim fashion brands need to prioritize honesty, transparency, and adherence to sharia to build consumer trust. It is recommended to continue to consider the sharia and sincerity aspects in every consumption decision so that it not only fulfills worldly needs but also has worship value.

Information Asymmetry Moderates the Impact of Green Intellectual Capital and Real Earnings Management on Future Stock Returns

Etty Murwaningsari — 2025-05-31

The aim of this study is to (1) analyze the impact of green intellectual capital and real earnings management on future stock returns. (2) The role of information asymmetry as a moderating variable for the impact of green intellectual capital and real profit management on future stock returns. This research method uses secondary data from companies in the non-cyclical consumer sector listed on the Indonesian Stock Exchange (BEI). The research sample was selected in the period 2021-2022 based on purposive sampling criteria–, resulting in 158 observations. The data analysis was performed using the moderated regression analysis (MRA) approach to test the relationship between the variables in this study. The results of this investigation show that: (1) Green intellectual capital and real earnings management have a positive impact on future stock returns. (2) Information asymmetry does not weaken the relationship between green intellectual capital and future stock returns, so that it is classified as a moderating predictor. On the other hand, information asymmetry is shown to attenuate the impact of real earnings management on future stock returns, indicating that this variable acts as a full moderator. (3) The control variable leverage has no effect on future stock returns, while firm size has a negative effect on future stock returns.

Design of Sales Information System for Goods at Alpar Wholesale Store in Jambi City Based on Web

Sauti Abrani — 2025-05-31

Alpar Wholesale Store is a store that sells various kinds of products for household needs. In the data processing process using handwriting, so there are still many obstacles in data processing, such as the difficulty of: To record sales data, planning previously planned activities because the data search process is considered slow, data does not appear automatically so it must be written repeatedly, and data cannot be integrated with each other because there is no database. The purpose of this study is to analyze the current system, to overcome the problems faced at the Alpar Wholesale Store, by designing a Web-Based Sales Information System Design at the Alpar Wholesale Store in Jambi City. The Research Framework that will be carried out in solving the problems discussed is, identifying, searching for information based on theoretical foundations, collecting data using observation and interview methods, analyzing to find solutions to the problems faced by the Alpar Wholesale Store. The system development method uses a waterfall model, the implementation of this study uses the PHP Programming Language and DBMS MySQL, to produce data processing applications that are expected to facilitate data processing and report creation.

Designing Startup Application “LaKu” for MSME in Riau Based on Android

Yulvia Nora Marlim — 2025-05-31

Department of Industry, Trade, Cooperatives and SMEs (DITCS) of Riau has an important role in supporting 631,347 groups of Micro, Small and Medium Enterprises (MSMEs) engaged in various fields such as handicrafts, batik, songket, and food and beverages. Many MSME merchants still market their products traditionally through the neighborhood and word of mouth, while online marketing faces a big challenge because they have to compete with well-known brands, making them difficult to develop and grow their business. To overcome these problems, an Android-based application “LaKu” was developed that aims to help MSME merchants in expanding their marketing reach and increasing their competitiveness in Riau. The development of this application uses the Extreme Programming (XP) method which consists of four main steps: Planning, Design, Code, and Testing. The development results show that the “LaKu” application can be an effective digital marketing platform, helping MSMEs in promoting products more widely without having to compete directly with big brands. With this application, MSMEs are able to increase competitiveness and contribute to local economic growth in Riau Province.