The research aims to examine the antecedents of Fintech Peer-to-Peer (P2P) lending adoption in Indonesia by extending the UTAUT3 framework with financial risk tolerance and artificial intelligence literacy. It also explores the moderating role of green self-identity and gender differences in P2P lending adoption. Data were collected from 421 respondents in Indonesia using a non-probability voluntary response sampling approach and analyzed using the PLS-SEM method. The results indicate that performance expectancy, effort expectancy, social influence, and AI literacy have a positive and significant influence on behavioral intention toward P2P lending. Facilitating conditions positively and significantly affect use behavior. Green self-identity weakens the relationship between behavioral intention and use behavior. No significant gender differences were found in the correlations between behavioral intention, use behavior, and financial inclusion. This study advances the literature on financial innovation by bridging theory and practice in the context of AI-enabled Fintech P2P lending. By integrating empirical evidence with policy considerations, the findings highlight the importance of collaboration between regulators and Fintech providers in fostering responsible innovation. The results provide actionable implications for designing user-centered lending systems that enhance financial inclusion. In this regard, the study contributes to the advancement of inclusive digital finance and supports Indonesia’s broader strategic objective of expanding sustainable and equitable access to financial services.
Employee data management and daily operational reporting play an important role in supporting efficiency, accuracy, and decision-making processes in warehouse operations. However, many organizations still rely on spreadsheet-based reporting systems and manual data recording processes that are vulnerable to data redundancy, inconsistent updates, limited monitoring capabilities, and delays in report recapitulation, which negatively affect operational efficiency and information accuracy. Previous studies have generally focused only on employee administration systems or inventory management separately, while limited research has discussed the integration of employee databases, daily activity reporting, and operational monitoring within a unified information system. This study aims to design and develop an integrated employee database and daily reporting information system to improve operational efficiency and reporting accuracy in warehouse activities. The system integrates employee data management, daily activity recording, automated reporting, and role-based access control within a centralized platform. The Rapid Application Development (RAD) method was applied to support iterative development and faster adaptation to user requirements. System evaluation was conducted using Black Box Testing to verify functional reliability and system performance. The results show that the proposed system successfully reduces data duplication, accelerates report generation processes, improves information accessibility, and enhances operational transparency and managerial decision-making. The implementation results also demonstrate that the developed system provides a more structured, efficient, and integrated approach to warehouse personnel administration and daily operational reporting.
Road surface damage such as cracks, potholes, and patches can reduce driving comfort and threaten road user safety. Manual road inspection is time-consuming and inefficient, especially for large urban areas. This study proposes an image-based approach to classify road damage types using Gray Level Co-occurrence Matrix (GLCM) feature extraction and a backpropagation artificial neural network. Road images were captured directly in Palembang City using a smartphone camera and converted into grayscale images with five different bit depths: 4-bit, 5-bit, 6-bit, 7-bit, and 8-bit. Texture features including contrast, correlation, energy, and homogeneity were extracted using GLCM and used as inputs to the neural network classifier. Experimental results show that higher grayscale bit depth produces better classification accuracy, with 8-bit grayscale achieving the highest performance compared to lower bit depths. The results confirm that grayscale resolution significantly affects texture representation and classification accuracy. This approach can support automated and efficient road damage detection systems.
Navigation in a canteen environment for an automated service robot requires an approach that ensures both efficiency and safety in path planning. This study implements the A* algorithm within an intelligent navigation system, using the canteen at Indo Global Mandiri University (UIGM) as the experimental setting. The selection of A* is based on its capability to integrate the accumulated movement cost with a heuristic estimation toward the goal, allowing the system to identify an optimal route. The environment is represented using a two-dimensional grid model that distinguishes navigable areas from static obstacles such as tables, service counters, pillars, and walls. Based on this representation, the system autonomously computes the most efficient path from the robot's starting position to the designated customer table. The findings demonstrate that the proposed approach is able to generate effective navigation paths that correspond well with the predefined environmental model. This work can serve as a foundation for further improvements, particularly by introducing dynamic obstacles and benchmarking against alternative pathfinding methods.
The rapid growth of digital tourism platforms has increased the availability of culinary destination information, making it challenging for users to identify destinations that best match their preferences. Recommendation systems have become an effective solution for providing personalized recommendations; however, most conventional approaches only present recommendation results without explaining the underlying reasons, thereby reducing user trust and transparency. This study proposes an Explainable Content-Based Recommendation System for culinary tourism by integrating TF-IDF feature representation with the Cosine Similarity algorithm. Culinary destination data were collected and preprocessed through text normalization and TF-IDF vectorization to represent the characteristics of each culinary destination. Cosine Similarity was then applied to measure the similarity between user preferences and culinary destinations, while an explanation module was developed to provide understandable reasons for each recommendation based on shared culinary attributes, including category, main ingredients, flavor characteristics, and price range. The proposed system was implemented as a web-based application using Python, Flask, and MySQL. Experimental results show that the system achieved a Precision@5 of 0.92, a Recall@5 of 0.88, and an average response time of 0.73 seconds, indicating that the proposed approach is capable of generating relevant recommendations with efficient computational performance. Furthermore, the explanation module enhances recommendation transparency by enabling users to understand the factors contributing to each recommendation. These findings demonstrate that the proposed system provides a practical, lightweight, and explainable solution for culinary tourism recommendation and has the potential to improve user experience in selecting culinary destinations.
