International Journal of artificial intelligence research (IJAIR)
Not a member yet
271 research outputs found
Sort by
Personalized Product Recommendations Using Restricted Boltzmann Machines To Overcome Cold-Start Challenges On A Niche Coffee E-Commerce Platform
No full textThis paper examines the use of a Restricted Boltzmann Machine (RBM) to provide personalized product recommendations on a niche coffee e-commerce platform facing cold-start conditions. We train RBM variants on a binary transaction matrix derived from 100 simulated user transactions and evaluate four hidden-unit configurations (3, 5, 10, 15) using 5-fold cross-validation. Models were trained with Contrastive Divergence (CD-1) and assessed primarily by Mean Squared Error (MSE) for reconstruction fidelity, complemented by ranking metrics (Precision@3, NDCG@3). The 10-hidden-unit configuration achieved the best balance of reconstruction and ranking performance, with an average test MSE ? 0.0454, outperforming popular-item (MSE: 0.0802) and random (MSE: 0.0760) baselines. While the RBM demonstrates strong capability in modeling latent user preferences under sparse data, ranking metrics expose limitations when predicting exact top-N items in extremely sparse cases. The study highlights practical implications for early-stage niche marketplaces and suggests integrating content signals or hybridization to further improve top-N recommendation quality
OVERVIEW OF THE PLANNING DOCUMENT STRUCTURE AS A TOOL FOR LOCAL GOVERNMENT PERFORMANCE MEASUREMENT AND RISK MANAGEMENT
No full textLocal governments have a noble role in providing direct services felt by the community regarding basic needs such as civil registration services for primary and secondary education, health care, etc. by paying attention to the synchronization of policies at the central and provincial government levels. To ensure the effectiveness of the execution of these functions, local governments should adopt a performance management and risk management approach as formulated in applicable laws and regulations to improve the quality of strategic management in line with the principles of good governance. Based on these matters, by taking into account the applicable laws and regulations and taking into account the span of control of local government organizations, it is very necessary to identify detailed activities and/or end products documented in the annual planning document, especially at the Regional Apparatus Organization (OPD) level, detailed activities and/or end products describe in detail the sub-activities and sub-activity indicators, the identification and documentation can improve the quality of the OPD annual planning document as a living document, because it is not only used as a basis for measuring performance, but also as an input in identifying and analyzing risks at the operational level in achieving performance objectives at the sub-activity level, and can be used as an input in ensuring the cascade preparation of performance agreements from both the strategic level and the operational level. The methodology of this research uses a descriptive qualitative approach focusing on the Statute Approach and the Conceptual Approac
IOT AND MACHINE LEARNING INTEGRATION TO PERSONALIZE SHOPPING EXPERIENCES IN SMART MALLS
Full text linkThe development of digital technology is driving significant transformation in the retail industry, one of which is through the application of the Internet of Things (IoT) and Machine Learning (ML) in smart mall management. This research aims to analyze how the integration of IoT and ML can create a more optimal personalized shopping experience for visitors. The method used is qualitative research with a literature review approach, namely reviewing various scientific studies, research reports, and academic publications related to IoT implementation, ML analytics, and personalization concepts in the context of smart retail. The study results show that IoT enables real-time customer data collection through sensors, beacons, mobile devices, and smart camera systems. The data is then processed using ML algorithms to produce personal recommendations, predictions of consumer preferences, visitor movement patterns, and automatic service adjustments. The integration of these two technologies is proven to improve the quality of the shopping experience through relevant offers, navigation efficiency, optimization of tenant management, and increased customer interaction with the mall environment. In addition, the literature shows that the success of smart malls depends on the quality of system integration, data security, privacy transparency, and the readiness of human resources in managing technology. This research concludes that the use of IoT and ML has great potential in forming a smart retail ecosystem that is responsive and customer-centered. However, implementation needs to pay attention to ethical, technical and operational challenges so that personalization can be achieved without reducing consumer comfort and trust. It is hoped that this study can become a conceptual basis for the development of further research and digital transformation strategies in the modern retail sector
Exploring Indicators and Developing the Initial DigiGOVQUAL Model: An Exploratory Factor Analysis in Banjar City
Full text linkThe digital transformation of government through the Electronic-Based Government System (Sistem Pemerintahan Berbasis Elektronik—SPBE) has become a foundational element of bureaucratic reform in Indonesia. However, the absence of a standardized instrument for assessing SPBE service quality—particularly within the Government-to-Government (G2G) domain—has hindered systematic evaluation and continuous improvement efforts. This study aims to develop a preliminary model called DigiGOVQUAL, designed to measure the quality of SPBE services from the perspective of internal users within government institutions. The model adapts and refines relevant indicators from the E-Government Service Quality (EGSQUAL) framework to better reflect the specific characteristics of digital public services in the Indonesian bureaucratic context. Employing a quantitative research approach, the study utilizes Exploratory Factor Analysis (EFA) to validate the construct dimensions. Data were collected via an online survey distributed to over 200 active civil servants in the Banjar City government who have experience using G2G SPBE services. The findings are expected to contribute to the development of a valid and contextually appropriate evaluation tool for digital government service quality. Ultimately, the DigiGOVQUAL model is intended to support more accountable and user-centered public service delivery policies in the digital er
AI-Driven Personalized Design: Adapting Building Interior Design Based on User Preferences
Full text linkThe adoption of Artificial Intelligence (AI) increases efficiency in the design industry. However, the implementation of AI is not entirely received positively by designers. This study aims to explore the application of AI technology in personalizing building interior design based on user preferences. A qualitative approach was employed using the design thinking method. Data were collected through in-depth interviews with product and graphic designers and subsequently validated by experts in the field of AI. The results of this study indicate that the integration of AI in interior design based on user preferences can assist designers in generating more personalized, efficient, and client-specific design recommendations. AI has proven capable of processing both explicit and implicit preference data to predict optimal layouts, color selections, materials, and lighting. However, this study also found several significant challenges, such as inconsistent data quality, limitations of algorithms in understanding subjective and emotional aspects, and concerns regarding user data privacy. Nonetheless, the use of AI in interior design still offers great opportunities to create spaces that are more functional, innovative, and adaptive to the evolving lifestyles of their occupants
Evaluation of IoT Regulatory Readiness in Indonesia and Policy Recommendations to Support Safe and Effective Implementation
No full textThe rapid development of Internet of Things (IoT) technology in Indonesia presents significant opportunities as well as regulatory challenges. Although IoT adoption continues to increase across various sectors, national policies remain fragmented and lack an integrated framework to support safe and effective implementation. This study assesses Indonesia's readiness for IoT regulation and formulates policy recommendations using a mixed-methods approach. The dataset used in this study comprises both secondary and primary data. Secondary data includes Indonesia's Cybersecurity data, Digital Infrastructure Status, IoT Regulations and Laws, Bappenas Studies, Data from Bappenas, and several policies in other countries, such as America, China, Japan, Korea, and Europe. Meanwhile, primary data was collected through questionnaires distributed to several elements, including 61.5% respondents from IoT users, 19.3% respondents from IoT business actors/IoT Startups, 15.8% academics, and 3.7% Government as regulators. The results of this data were then processed to determine government policy readiness by implementing DDPG, where the state space consists of 6 dimensions of leading regulatory readiness indicators (infrastructure, security, data protection, interoperability, institutional maturity, and economy). The action space is a 6-dimensional vector with continuous values in the range of [-1, 1], representing policy interventions in each dimension. The implementation applies reward functions, actor networks, and critic networks. Training data was applied for several episodes at 400 and 1000 episodes. The comparison results show that IoT regulations and policies in Indonesia should be designed with an adaptive approach based on Reinforcement learning, where the balance between data security, technology readiness, and market penetration can be dynamically adjusted to national and global condition
Influence Of Innovation Strategy Model To Improving Organizational Performance Regional Government In Indonesia
Full text linkThis research is aimed at testing the innovation strategy model to improving organizational performance regional government in Indonesia The performance of the Regional Government organization is the overall achievement of the results that have been achieved and achieved in handling all activities carried out by the Regional Government in a certain period (Muhamad F., 2009) as well as a description of the achievement of the government's goals and objectives as an elaboration of the vision, mission and strategy The following agencies indicate the level of success or failure in implementing activities determined by the Regional Government in accordance with established programs and policies. And this research uses the Partial Least Squares Structural Equation Modeling analysis technique (PLS-SEM), to model many variables in research
The Influence Of Operational Strategy And Operational Competence On Quality Culture And Quality Of Hospital Services And Implications On Patient Satisfaction (Survey At Rapha Theresia Hospital, Baiturrahim Hospital, Arafah Islamic Hospital And Mitra Hospital In Jambi Province)
Full text linkThis research aims to identify the influence of operational strategy on operational competence on quality culture, quality of hospital services, and patient satisfaction. According to the Health Law (UU No. 17 of 2023), improving the quality of hospital services in Indonesia is very important to reduce wastage of foreign exchange due to people taking care abroad. This examination was carried out at hospitals in Jambi Province (Rapha Theresia Hospital, Baiturrahim Hospital, Arafah Islam Hospital, Mitra Hospital) using a quantitative approach. Data was collected through interviews, questionnaires, and observations from 300 employees and distributed to each hospital. The results of the analysis show that operational strategies and operational competencies in food have a significant influence on quality culture, service has a 69.30% influence. This, operational strategy and operational competency and food have a significant influence on the quality of hospital services (74.48%). Good quality culture and the quality of hospital services simultaneously have a significant influence on patient satisfaction and a total influence of 81.52%. There are still practical suggestions for hospitals to improve operational strategies, develop operational competence, strengthen quality culture, and improve service quality to improve patient satisfaction. The authors also asked about the panalungtikan salajengna kalayan ngalibetkeun additional variables jeung negligent the scope of the panalungtikan to the city/district séjén pikeun add to the results of the panalungtikan
The Impact of Entrepreneurial Networks, Orientation, and Competence on Online Trading SMEs Performance in Makassar City
Full text linkResearch Aims: This study aims to examine the effect of entrepreneurial networks, entrepreneurial orientation, and entrepreneurial competence on the performance of online trading SMEs in Makassar City. It seeks to understand how these entrepreneurial factors contribute to SMEs’ success in the digital business environment.Design/Methodology/Approach: A quantitative approach was adopted using Partial Least Squares Structural Equation Modeling (PLS-SEM). Data were collected through online questionnaires distributed to 150 SME owners operating in online trading in Makassar. The measurement model and structural model were assessed for validity, reliability, and hypothesis testing.Research Findings: The study found that all three variables — entrepreneurial networks, entrepreneurial orientation, and entrepreneurial competence — have a significant and positive influence on SME performance. Entrepreneurial orientation was the most dominant factor, followed by entrepreneurial competence and entrepreneurial networks. The model explained 83.4% of the variance in SME performance with high predictive relevance (Q² = 0.732).Theoretical Contribution/Originality: This research enriches the literature on entrepreneurial dynamics by empirically validating the interplay between entrepreneurial orientation, networks, and competence in the context of digital SMEs in emerging economies. It confirms the Resource-Based View (RBV) theory by showing how internal capabilities and external linkages enhance performance.Practitioners/Policy Implications: The findings provide practical guidance for SME owners to focus on building robust networks, enhancing managerial competencies, and fostering a proactive and innovative business mindset. For policymakers, the study highlights the need for support programs focusing on digital literacy, entrepreneurial training, and access to networking platforms.Research Limitations/Implications: This study is limited to online trading SMEs in Makassar City, which may affect the generalizability of findings to other regions or industries. Future research could explore longitudinal designs, incorporate moderating variables such as digital transformation or government support, and compare SMEs across multiple regions or sectors
Website Based (We-Retag) as Chemical Foam Quality Tests Record on Foam Tender Vehicles
Full text linkThis study aims to design a We-ReTag website (we enter record tag) which digitally able to record the outcomes of foam quality testing on foam tender vehicles more efficiently than logbooks or spreadsheets. In addition, this study also ensures that the website is designed to be easy to use (user-friendly) for inputting data on foam quality test results. A material expert and an IT expert who serves as a We-ReTag website validator are the study's subjects. The entire 36 (thirty-six) ARFF personnel at Sultan Mahmud Badaruddin II Airport Palembang are the subject of this website's design. This study used a waterfall model in conjunction with the research and development (R&D) approach. Starting with the requirements stage, this process moves on to desing, implementation, testing, and verification before coming to an end with maintenances. Thes result of study show that We-Retag website was highly appropriate for usage in ARFF unit of SMB II airport based on validation from IT and material specialist with average scale of 87%. In addition, the average scale obtained from the questionnaire filled out by ARFF personnel was 89 %. The benefit of this research is to increase the effectiveness in chemical foam quality test record and expected its usage can be disseminated to other airport throughout Indonesia in similar operational context