Publication Search

This study is intended to identify the impact of Online Customer Reviews and Product Quality Perceptions on Skintific Purchase Decisions on TikTok Shop. This study applies a quantitative approach through causal methods. Involving 96 respondents who have purchased and used Skintific products on the platform. Data analysis was carried out through the stages of classical assumption tests (normality, multicollinearity, and heteroscedasticity), and used multiple linear regression to test the research hypothesis. The findings show that online customer reviews and product quality perceptions have a positive and significant influence on purchase decisions, both when tested individually and together. The adjusted coefficient of determination (Adjusted R²) reaches 0.875, which means that 87.5% of the variation in purchase decisions can be explained by the two independent variables, while the remaining 12.5% is influenced by external elements outside of this model. Among the two variables studied, Online Customer Reviews were proven to have a dominant influence on Purchase Decisions, with a higher Beta value than Product Quality Perception. This conclusion emphasizes that positive reviews from customers and a good view of product quality are the main drivers for consumers to purchase Skintific products on TikTok Shop. Thus, companies are advised to maintain product reputation through consistent quality as well as optimize digital communication strategies based on customer reviews to improve consumer purchasing decisions.

The development of social media-based e-commerce, especially TikTok Shop, has created new challenges and opportunities in building customer loyalty, especially in the highly competitive local cosmetics industry. One of the most popular local brands is Emina, which targets young consumers with an affordable price approach and halal label. However, the level of customer loyalty is still a crucial issue that needs to be strengthened so that business sustainability is maintained. The urgency of this research lies in the need to understand how live streaming and halal labeling, as two relevant marketing strategies in the digital era, are able to shape purchasing interest that leads to customer loyalty. This study uses a quantitative approach with the PLS-SEM technique to test the relationship between variables with 115 TikTok Shop user respondents in Semarang City. The results show that live streaming and halal labeling have a significant effect on purchasing interest and customer loyalty, and purchasing interest is proven to mediate the relationship between the two variables and customer loyalty. These findings indicate the importance of integrating interactive visual approaches and religious belief values in digital marketing strategies for cosmetic products.

This study aims to classify customer payment methods at 17 Coffee & Eatery using machine learning algorithms, namely Naïve Bayes and Support Vector Machine (SVM). The increasing use of digital and non-cash payments has generated large volumes of transaction data that are rarely analyzed optimally, even though such data contain valuable information for business decision making. This research used secondary transaction data collected from January to March 2025, consisting of 10,147 transaction records. The dataset included several attributes such as order time, payment time, transaction type, total sales, number of items, and payment method. Data preprocessing was performed through data cleaning, feature engineering, normalization, and label encoding before being divided into training and testing sets with an 80:20 ratio. The Naïve Bayes and SVM models were then trained and evaluated using accuracy, precision, recall, F1-score, and ROC–AUC metrics. The results show that both algorithms were able to classify payment methods effectively, but SVM achieved higher accuracy and more stable performance than Naïve Bayes. These findings indicate that SVM is more suitable for handling complex and heterogeneous transaction patterns. The implementation of machine learning for transaction classification can support more efficient financial management and data-driven decision making for small and medium enterprises in the culinary sector.

The development of information technology has encouraged restaurants and cafés to function not only as dining places, but also as venues for hosting various events. However, the event reservation process at Rumah Makan Ny. Hartini and Café Rain is still carried out manually through logbooks, telephone calls, and WhatsApp, resulting in problems such as unorganized data, delayed confirmations, and miscommunication with customers. In addition, the manual system limits access to information regarding venue availability, reservation schedules, and additional facilities required by customers. This study aims to develop a web-based event reservation information system using the prototyping method. The system design was carried out using Unified Modeling Language (UML), including use case diagrams, activity diagrams, and class diagrams to model user interactions, process flows, and system structure. The results of the study show that the developed system is able to automate the reservation process, customer data recording, reservation confirmation, schedule management, and additional facilities management. This system improves operational efficiency, data accuracy, and service quality, while also making it easier for customers to make reservations independently and obtain information quickly and accurately.

This research aims to examine how prices and reviews influence consumers 'purchasing decisions on the Shopee platform in Jambi City. The rapid development of e-commerce has encouraged consumers to be more careful and discerning when selecting products, making price and product reviews important considerations in buying decisions. This study employed a quantitative approach via a survey method for data collection. The questionnaires were distributed online and successfully gathered responses from active Shopee users in Jambi City. Purposive sampling was employed to make sure that respondents met research criteria. The information gathered underwent analysis using IBM SPSS Statistics 27, which involved conducting assessments of validity, reliability, and classical assumptions, and multiple regression tests to see the impact of each variable on buying decisions. The study revealed that product price and reviews hold an important and relevant impact on consumer buying decisions. This research indicates that the more competitive the price and the better the quality, the bigger the possibility of customers buying products on Shopee.

This study aims to analyze the comparison of small business development strategies in improving the income of traders in traditional markets around Medan City. The research employed a qualitative descriptive approach using interviews, observations, and documentation involving three traders of fruit, vegetables, and tomatoes. The results show that each trader applies different strategies depending on the characteristics of their commodities and business capacity. Fruit and tomato traders tend to implement quality sorting, price adjustments, and trust-building through honest customer service. Meanwhile, the vegetable trader relies more on traditional approaches such as giving bonuses to customers. Market facilities significantly influence the effectiveness of business strategies, where traders with proper stalls are better able to maintain income stability compared to those using temporary tents in muddy and uncomfortable areas. Seasonal factors also strongly affect income fluctuation as they determine the quality and supply of commodities. This study concludes that small business development strategies in traditional markets are shaped not only by traders’ managerial abilities but also by market infrastructure conditions and external environmental factors. It is recommended that market managers improve market facilities to support the sustainability of small traders’ businesses.

The increasing volume of online hotel reviews provides valuable insights into customer perceptions but poses challenges for manual analysis due to its unstructured nature. This study aims to compare the performance of Recurrent Neural Network (RNN) and Bidirectional Encoder Representations from Transformers (BERT) in hotel review sentiment analysis. A total of 20,491 TripAdvisor hotel reviews were classified into three sentiment categories: negative, neutral, and positive. The research methodology includes text preprocessing, stratified data splitting, class imbalance handling using Random Over-Sampling, tokenization, and supervised model training. Model performance was evaluated using a confusion matrix and classification metrics. The results indicate that BERT outperforms RNN, achieving an accuracy of 80.54%, while RNN reached 62.21%. BERT demonstrated superior capability in capturing contextual and semantic information in hotel reviews. These findings suggest that transformer-based models are more effective for sentiment analysis of complex textual data in the hospitality domain and can support data-driven service improvement strategies.    

This study aims to analyze the influence of Corporate Image and Service Quality through Customer Satisfaction on Customer Loyalty at Semen Indonesia distributors in Gresik using the Structural Equation Modeling (SEM) approach. The study population consisted of 102 customers, all of whom were sampled. The results indicate that Corporate Image and Service Quality have a significant influence on Customer Satisfaction. Both variables were also shown to have a significant influence on Customer Loyalty. However, unlike several previous research findings, Customer Satisfaction did not have a significant influence on Customer Loyalty. This finding indicates that in the context of the cement distribution business, customer loyalty is not formed solely from satisfaction, but is more influenced by other factors such as consistent service quality, a strong corporate image, competitive pricing, and long-term business relationships. This study emphasizes the importance of strengthening image and improving service quality as key strategies for maintaining customer loyalty.

Queueing systems play an important role in evaluating service performance, especially in small-scale businesses such as barbershops, where fluctuating customer arrival patterns and limited service capacity often lead to long waiting times. This study aims to analyze the performance of barbershop services using the M/M/1 queueing model and an analytical approach based on experimentally tested arrival (λ) and service (μ) rates. The model was selected because it represents a single-server system with Poisson arrivals and exponentially distributed service times, closely matching real barbershop operational characteristics. Using assumed realistic parameters, the analysis shows that when λ = 12 customers per hour and μ = 6 customers per hour, the system becomes unstable with a utilization rate (ρ) exceeding 1, indicating continuous queue growth. Further simulations with increased service rates demonstrate significant improvements: at μ = 15, the system achieves ρ = 0.8 with an average waiting time of 16 minutes, while at μ = 13, the system remains stable but experiences a long waiting time of approximately 55 minutes. These findings emphasize that barbershop performance is highly sensitive to service speed and that even small increases in μ can produce substantial improvements in queue stability and customer waiting times. The study concludes that barbershops must ensure adequate service capacity—either through optimizing service duration, improving worker efficiency, or adding servers—to maintain service quality and enhance customer satisfaction.

In the contemporary digital marketplace, consumers increasingly face diverse product choices and brand communications. Understanding the mechanisms through which product quality and brand perception influence customer loyalty remains critical for competitive advantage. The mediating role of customer trust in this relationship has received limited empirical attention within Indonesian market contexts. This research analyzes the direct and indirect effects of product quality and brand perception on customer loyalty, with customer trust as a mediating variable, using Partial Least Squares Structural Equation Modeling (PLS-SEM) methodology on 103 respondents. A quantitative cross-sectional survey design was employed, collecting data via Likert-scale questionnaires (1-5) with 15 measurement items across four latent constructs: Product Quality (5 items), Brand Perception (4 items), Customer Trust (3 items), and Customer Loyalty (3 items). Data analysis utilized PLS-SEM via SmartPLS 3.0, including assessment of measurement model validity (outer model), structural relationships (inner model), and mediation effects through bootstrapping (5000 iterations). The outer model demonstrated adequate validity with 12 of 15 indicators loading above 0.7, and all constructs meeting composite reliability (CR > 0.7) and average variance extracted (AVE > 0.5) criteria. The inner model revealed that product quality significantly influenced customer trust (β = 0.624, p < 0.001), while brand perception showed no significant direct effect (β = 0.045, p = 0.767). Customer trust strongly predicted loyalty (β = 0.650, p < 0.001). Product quality demonstrated a significant indirect effect on loyalty through trust (β = 0.405, p < 0.001), indicating full mediation. The model explained 43.5% of trust variance and 42.2% of loyalty variance. Product quality emerged as the dominant antecedent of customer trust and loyalty, while brand perception did not significantly contribute. Trust served as the critical mechanism translating quality into loyalty. These findings suggest that companies should prioritize quality assurance and consistent delivery over brand marketing campaigns for sustainable loyalty development. The research contributes to mediation theory in consumer behavior and provides actionable strategic guidance for practitioners in emerging markets.

This study presents a high-accuracy real-time soft failure detection framework for large-scale fiber-to-the-home(FTTH) optical access network using a hybrid ensemble of Isolation Forest and One-Class Support Vector Machine (OCVSM). The proposed model was trainde and validated on a real-word multivariate performance dataset comprising more than 1.8 million samples collected at 5-minute intervals from 50 Optical Line Terminal (OLTs) and over 3,000 Optical Network Terminals (ONTs) across a five-month periode(June-October 2025). Ground-truth validation was performed using 111 confirmed network incidents in October 2025 affecting 12,990 customer. The hybrid ensemble achieved Precision 0.940, Recall 0.982, with an average detection delay of only 7.8 minutes-representing an 87.7% reduction compared to conventional manual response (63.5 minutes). The framework significantly outperforms traditional threesholding and recent ML-based methods while demonstrating practical deployability in live operational enviroments.

Customer satisfaction has become a major focus in the development of modern services as the role of the service sector in the regional economy increases, including in the city of Balikpapan. However, the literature discussing customer satisfaction models shows conceptual and methodological fragmentation, requiring a systematic synthesis to identify theoretical patterns and current research developments. This study aims to map customer satisfaction models in the service industry through a Systematic Literature Review (SLR) approach using the PRISMA guidelines. A total of 20 articles selected from the last five years were analyzed to identify dominant constructs, methodological approaches, and relevant research trends. The review results show that customer satisfaction models have evolved from traditional service quality-based approaches to models that integrate customer experience, perceived value, trust, and digital dimensions such as personalization and AI-based services. The findings also emphasize the importance of local context, especially in the service sector in Balikpapan, where cultural factors, customer behavior, and the dynamics of city growth influence the structure of satisfaction models. Overall, this study provides a synthesis framework that can be used as a theoretical and practical foundation for designing service quality improvement strategies and developing a further research agenda in the service sector.

This study aims to evaluate the effectiveness of the implementation of the marketing mix in SMEs in the laundry service sector, focusing on the 7P elements: product, price, promotion, place, process, people, and physical evidence. The research uses a descriptive qualitative method with data collection techniques including interviews, observations, and documentation with laundry business owners. The results show that a diverse range of services, competitive pricing, strategic location, and structured work processes contribute to the sustainability of the business. However, challenges such as unpredictable weather, timeliness, limited facilities, and suboptimal promotion still pose barriers to improving service quality. The findings highlight the importance of strengthening digital promotion, modernizing equipment, and improving the accuracy and consistency of human resources (HR) to enhance the effectiveness of the marketing mix. With improvements in these areas, laundry SMEs can enhance their competitiveness and provide better service to customers, thus strengthening their position in a competitive market.

The growth of e-commerce in Indonesia has led to an increase in product reviews, including for beauty products on Tokopedia and Shopee. These reviews serve as important sources of information to assess consumer satisfaction; however, manually analyzing thousands of reviews daily is impractical. This study applies Natural Language Processing (NLP) with Naive Bayes, C4.5, XGBoost algorithms to classify sentiment in Indonesian-language reviews. The dataset used consists of 76,256 reviews labeled as positive, negative, and neutral. The research stages include text preprocessing, feature representation using BoW and TF-IDF, data balancing through SMOTE, and model performance evaluation based on accuracy, precision, and recall. Differences in results among the algorithms were analyzed using ANOVA. The results show that Naive Bayes achieved the highest accuracy at 67.71%, followed by XGBoost at 65.91%, and C4.5 at 58.39%, with Naive Bayes performing best in identifying positive and negative sentiments, while XGBoost and C4.5 handled more complex data patterns effectively. These findings provide guidance for sentiment analysis in Indonesian and support businesses in obtaining automated insights from customer reviews to improve product quality and services.

This study aims to examine business models in the gypsum sector by utilizing the Business Model Canvas (BMC) framework. The gypsum business is one of the fields that is growing rapidly in line with the increasing need for residential construction, building renovation, and aesthetic and functional interior design. However, to be able to survive and compete in an increasingly competitive market, gypsum business actors are required to have a business model that is structured, adaptive, and value-oriented for customers. This study uses a qualitative approach with a descriptive type of research. Data collection was carried out through in-depth interviews and direct observation of Nury Gipsum's business located in Klaten Regency. The results show that all nine elements in the Business Model Canvas, namely key partners, key activities, key resources, value offerings, customer relationships, distribution channels, customer segments, cost structure, and revenue streams, have been optimally implemented. Thus, the Business Model Canvas has proven to be effective in providing a comprehensive overview of business operations and can be a strategic basis for decision-making and gypsum business development in the future.

Automatic motorcycle spare part sales have increased along with the high use of automatic two-wheeled vehicles in the community. To support optimal sales strategies and stock management, customer purchasing pattern analysis is required. This study uses the FP-Growth algorithm to identify association patterns between automatic motorcycle spare part products that are frequently purchased together. FP-Growth was chosen because of its ability to efficiently find frequent itemsets without the need to generate candidate itemsets as in the Apriori algorithm. Transaction data is processed to form an FP-Tree which is then extracted to find relationships between items. The analysis results show combinations of products that frequently appear together, such as brake pads and engine oil, which can be used as a basis for compiling sales packages, product placement, and product recommendations. By implementing the FP-Growth algorithm, spare part stores or workshops can improve service and efficiency in sales management.

This study aims to analyze the application of the franchising system on business performance in the beverage franchise business through a case study of Mitra Minuman Siap Saji. The approach used is qualitative with a case study design, with data collection techniques in the form of in-depth interviews, operational observations, and supporting documentation. The results show that the implementation of standardized Standard Operating Procedures (SOPs), franchisor support in the form of training, raw material supplies, and periodic monitoring contribute significantly to improving business stability, product quality consistency, and customer satisfaction. However, there are limitations in flexibility and several communication obstacles that have the potential to affect the effectiveness of the partnership. The relatively strict contract structure also impacts partners' perceptions of local innovation space, although it is generally still viewed as providing business security and business model clarity. These findings emphasize that a balance between franchisor control and partner autonomy, accompanied by open communication and fair contract design, is a key factor in creating sustainable business performance in a franchising system.

The skincare industry in Indonesia is experiencing rapid growth, primarily driven by the significant development of e-commerce and increased consumer awareness of self-care. This surge has resulted in intense competition among brands. This comparative study aims to analyze the role of trust as a mediating variable that connects price fairness, celebrity endorsements, and e-WOM to repurchase intentions for two brands: Somethinc (a science-based brand) and Wardah (a halal-based brand). A quantitative research method was used, involving a survey with a 5-point Likert scale distributed to 150 millennials and Gen Z respondents in Semarang City. The data were analyzed using PLS-SEM (SmartPLS). The findings reveal that both celebrity endorsements and trust have a significant impact on repurchase intentions for both brands. In contrast, price fairness and e-WOM do not have a significant direct effect on either brand. However, the study shows that trust effectively mediates the influence of price fairness, celebrity endorsements, and e-WOM on repurchase intentions. This underscores the vital role of trust in enhancing customer loyalty to Somethinc and Wardah. These findings suggest that strengthening brand trust in skincare products can significantly boost customer loyalty.

The rapid growth of e-commerce platforms in Indonesia, particularly Tokopedia, has resulted in a large volume of consumer reviews containing valuable information regarding customer perceptions and satisfaction. However, manual analysis of such reviews is inefficient and prone to subjectivity, necessitating an automated approach based on machine learning. This study aims to classify the sentiment of sports product reviews on Tokopedia into positive, negative, and neutral categories by applying Logistic Regression, Support Vector Machine (SVM), and Random Forest using the Term Frequency–Inverse Document Frequency (TF-IDF) approach. The data were collected through web scraping of Indonesian-language sports product reviews and processed through several preprocessing stages, including data cleaning, case folding, tokenization, stopword removal, and stemming. Feature representation was performed using TF-IDF to transform textual data into numerical vectors, after which the dataset was divided into training and testing sets with an 80:20 ratio. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results indicate that the application of TF-IDF significantly improves the performance of all models, with SVM consistently achieving the most optimal performance compared to Logistic Regression and Random Forest. These findings demonstrate that classical machine learning algorithms combined with TF-IDF remain highly effective for sentiment analysis of Indonesian-language text. The implications of this study are expected to assist sellers in understanding customer opinions, support consumers in making informed purchasing decisions, and serve as a foundation for the development of sentiment analysis and recommendation systems on e-commerce platforms.

This study aims to analyze the influence of product quality on consumer satisfaction in the Kipang Sisera Panyabungan Business. The research method used is a quantitative approach with data collection techniques through observation, interviews, and questionnaire distribution to 96 respondents who are customers of Kipang Sisera. The data obtained were analyzed using validity, reliability, and regression analysis tests with the help of SPSS 25. The results of the validity test showed that all items in the questionnaire were valid with a rtable value of > (0.1689), while the results of the reliability test using Alpha Cronbach showed a value of > 0.60, which means that the research instrument is trustworthy. The results of the partial regression test (t-test) showed that product quality had a positive and significant effect on consumer satisfaction with a significance value of 0.000 < 0.05. The determination coefficient (R²) test showed that product quality contributed 62.9% to consumer satisfaction, while the rest was influenced by other variables that were not studied in this study. These findings indicate that improving product quality, both in terms of taste, packaging, and quality consistency, is very important in maintaining consumer satisfaction and the sustainability of Kipang Sisera's business in the midst of market competition.