Publication Search

This study examines customer churn prediction in subscription-based telecommunications from a digital marketing perspective using machine learning. The analysis utilizes a secondary dataset of 7,043 customer records that simulate behavioral, contractual, and financial attributes commonly found in telecom services. Three classification algorithms Logistic Regression, Random Forest, and Gradient Boosting are applied to model churn behavior. Data preprocessing includes handling missing values, encoding categorical variables, and splitting data into training and testing sets. Model performance is evaluated using accuracy, recall, and ROC-AUC, with emphasis on recall due to its importance in identifying at-risk customers. The results show that Gradient Boosting achieves the highest overall performance with an ROC-AUC of 0.84, while Logistic Regression provides relatively higher recall. Key drivers of churn include short-term contracts, higher monthly charges, and lower service engagement. However, recall remains moderate, indicating limitations in capturing complex behavioral factors. These findings suggest the need to combine predictive models with behavioral insights and highlight the importance of early customer engagement and long-term retention strategies.

The purpose of this study is to examine how online promotion, product innovation, and brand image affect product competitiveness in Batam City's flower bucket equipment industry (CV Acmeteam). This study employs a quantitative methodology, gathering information from 100 respondents via questionnaires using Simple Random Sampling with Slovin formula from a population of 135 active customers. Data were analyzed through validity tests, reliability tests (Cronbach's Alpha = 0.750), classical assumption tests (normality, multicollinearity, heteroscedasticity), multiple linear regression, partial t-test, simultaneous F-test, and coefficient of determination (R²). Results show that all questionnaire items are valid and reliable. The normality test (Asymp. Sig. = 0.866 > 0.05) indicates normally distributed data, and no multicollinearity (VIF < 10) or heteroscedasticity (Sig. > 0.05) was detected. Regression analysis reveals that online promotion (β = 0.521, Sig. = 0.041), product innovation (β = 0.668, Sig. = 0.033), and brand image (β = 0.458, Sig. = 0.049) each significantly influence product competitiveness. Simultaneously, all three variables are significant (F = 9.876, Sig. = 0.000) and explain 44.9% (R² = 0.449) of product competitiveness variance. Product innovation is the strongest predictor. This study concludes that strong brand image, continuous product innovation, and effective digital marketing are essential pillars for enhancing product competitiveness. Business actors must optimize these three elements to compete effectively in an increasingly open creative industry market.

This study aims to determine the effect of product availability, communication effectiveness, and promotional strategy on sales volume at PT.Distribusindo Cemerlang Jaya, a cosmetic and skincare distribution company in Batam city. The background of this research is based on pre-survey result indicating suboptimal sales volume along with operational challenges including stock shortages, communicatiob gaps, and limited promotional activities.ths research employs a quantitative method. The population consist of all comsumers, with a sample of 43 respondent selected using a saturated sampling technique. Data were collected through questionnaires using a likert scale and analyzed using validity and reliability test, classical assumption tests, multiple linear regression, t-test, F-test, and coefficient of determination (R²) with SPSS. Result show that partially, product availability does not significantly affect sales volume (sig. 0,313 > 0,05), and communication effectiveness also does not significantly affect sales volume (sig. 0,898 > 0,05). However, promotional strategy has a positive and significant effect  on sales volume (sig, 0,000 < 0,05). Simultaneously, all three variables significantly affect sales volume (F = 212.642, sig. 0,000 < 0,05). The coefficient of determination (R²) is 0,942 indicating that 94,2% of the variation in sales volume is explained by the three independent variables. Promotional strategy is the most dominant factor influencing sales volume is explained by the three independent variables. Promotional strategy is the most dominant factor influencing sales volume at PT.Distribusindo Cemerlang Jaya.  

This study aimed to examine the extent to which trust, perceived security, and ease of use of the GrabFood platform influence consumer transaction decisions in Batam City. The method used was descriptive quantitative, involving 204 respondents who had made purchases through GrabFood, selected through purposive sampling based on Jacob Cohen's formula to ensure representative results. Data were collected using a questionnaire and analyzed through a series of procedures, including validity and reliability testing, classical assumption checking, multiple linear regression, and hypothesis testing using t-tests and F-tests. The study findings revealed that trust contributed 22.0%, security 38.9%, and ease of use 23.2% to purchasing decisions. The coefficient of determination (R²) of 65.6% confirmed that these three factors simultaneously explained a significant portion of the variation in consumer purchasing behavior. Furthermore, t-tests and F-tests confirmed a positive and significant influence, both individually and collectively, on consumer decisions to use GrabFood.

This study aimed to uncover the extent to which eWOM, perceived brand image, and platform ease of use influence consumer purchasing decisions for Skintific moisturizer on Tokopedia. The method employed was descriptive quantitative, selecting a sample of 96 consumers who had purchased Skintific products, using a purposive sampling technique based on the Lemeshow formula to ensure representativeness. Data were collected through a questionnaire and then analyzed using a series of tests including validity, reliability, classical assumption checking, multiple linear regression, and hypothesis testing using t- and F-tests. The analysis showed that eWOM contributed 13.9% to purchasing decisions, brand image 23.4%, and ease of use 46.1%. The coefficient of determination (R²) of 75.4% indicates that these variables collectively explain most of the variation in purchasing decisions. The t- and F-tests confirmed a positive and significant influence, both individually and simultaneously, on consumer purchasing behavior on Tokopedia.

This study aims to explore the extent to which brand image, product quality, and trust influence purchasing decisions for Pixy two-way cake through the Blibli platform in Batam City. The approach used is quantitative descriptive, involving 100 consumers who previously purchased Pixy two-way cake on Blibli, selected through purposive sampling with Lemeshow calculation guidelines to ensure sample representativeness. Data collection was conducted using a questionnaire, then analyzed through validity and reliability tests, classical assumption evaluation, multiple linear regression, and hypothesis testing using t-tests and F-tests. The results of the regression analysis indicate that brand image has a 24.7% influence on purchasing decisions, product quality contributes 34.0%, and trust plays a role of 29.2%. Furthermore, the coefficient of determination (R²) shows that these three variables collectively explain 74.0% of the variation in purchasing decisions. The t-test and F-test confirm that the influence of each variable is significant and positive, both partially and simultaneously, on consumer purchasing decisions at Blibli in Batam City.

This study aims to analyze the influence of product quality, brand image, and promotion on purchasing decisions for Nivea products in Batam City. The population in this study were consumers who use Nivea products in the Lubuk Baja District area with an unknown population size. The sampling technique used the Jacob Cohen formula, resulting in a sample size of 204 respondents using a purposive sampling method. The research data were analyzed using multiple linear regression methods supported by data quality testing, classical assumption tests, influence tests, and hypothesis tests. The results of the regression analysis showed that product quality had a 31.5% influence on purchasing decisions, brand image had a 62.7% influence, and promotion had a 27.4% influence on purchasing decisions. Furthermore, the results of the coefficient of determination test showed that the variables of product quality, brand image, and promotion were able to explain 83.2% of the variation in purchasing decisions. In addition, the results of the T test and F test proved that the three independent variables had a positive and significant influence, both partially and simultaneously, on purchasing decisions for Nivea products in Batam City.

This study aims to analyze the effect of Brand Image, Product Quality, and Promotion on Purchase Decisions of Crocs sandals in Batam City. The research employs a quantitative approach using a survey method. Data were collected through questionnaires distributed to 119 respondents who are consumers of Crocs products in Batam City. The data analysis techniques include validity and reliability tests, classical assumption tests, multiple linear regression analysis, t-test, F-test, and coefficient of determination analysis, using SPSS version 26. The results indicate that Brand Image and Product Quality have a positive and significant effect on Purchase Decisions. Meanwhile, Promotion shows a positive but insignificant effect on Purchase Decisions. Simultaneously, Brand Image, Product Quality, and Promotion have a positive and significant effect on Purchase Decisions. The Adjusted R Square value of 0.905 indicates that 90.5% of the variation in Purchase Decisions can be explained by the three independent variables, while the remaining 9.5% is influenced by other factors not examined in this study. This research is expected to provide insights for companies in formulating more effective marketing strategies, particularly in strengthening brand image and improving product quality.

This study aims to examine the factors that influence consumer purchasing decisions for Nacific products in Batam City, with an emphasis on the role of digital marketing, E-WOM, and brand image. The research approach used is descriptive quantitative involving 204 respondents who have purchased Nacific products, selected through purposive sampling techniques based on Jacob Cohen's calculations to ensure the adequacy and representativeness of the sample. Data collection was carried out using a structured questionnaire, then analyzed through a series of statistical procedures including validity and reliability tests, classical assumption testing, multiple linear regression analysis, and hypothesis testing using t-tests and F-tests. The findings of the regression analysis revealed that the influence of digital marketing on purchasing decisions was recorded at 21.9%, E-WOM at 27.0%, and brand image at 34.0%. The coefficient of determination value of 0.722 confirms that digital marketing, E-WOM, and brand image simultaneously contribute 72.2% in explaining purchasing decisions. The results of the t-test and F-test indicate that digital marketing, e-WOM, and brand image each have a positive and significant influence on purchasing decisions, both partially and simultaneously.

This study aimed to examine the influence of promotional strategies and user-friendliness on consumer purchasing decisions on the ShopeeFood platform in Batam City. The research used a descriptive quantitative approach, involving 100 actively transacting respondents, selected through purposive sampling based on Lemeshow's calculation guidelines to ensure sample representativeness. Data were collected through a structured questionnaire and analyzed using a series of validity and reliability tests, classical assumption checks, multiple linear regression, and hypothesis testing using t- and F-tests. The research findings indicated that promotions contributed 42.4% to purchasing decisions, while user-friendliness contributed 26.0%. The coefficient of determination (R²) of 78.9% confirmed that these two variables collectively explained most of the variation in purchasing behavior. The results of the t- and F-tests confirmed that promotions and user-friendliness had a significant influence, both partially and simultaneously, emphasizing the importance of integrating effective digital marketing strategies and an intuitive application interface to drive consumer decisions on ShopeeFood in Batam City.

This study aims to elaborate on the determinants of consumer purchasing decisions by emphasizing the role of social media, trust levels, and product quality in the Blibli e-commerce ecosystem in Batam City. The applied methodological framework is based on a descriptive quantitative approach involving 204 respondents with active transaction track records, selected through a purposive sampling technique based on the Jacob Cohen formula to ensure proportionality and validity of sample representation. Empirical data were collected through a structured questionnaire, then processed using comprehensive statistical analysis stages that include instrument validity and reliability testing, classical assumption evaluation, multiple linear regression modeling, and hypothesis testing through partial (t) and simultaneous (F) tests. The analysis results revealed that social media intensity contributed 14.1% to purchasing decisions, trust influenced 36.0%, while product quality influenced 40.4%. The coefficient of determination (R²) value of 86.4% indicates that the three exogenous variables simultaneously have substantial explanatory power towards variations in purchasing decisions. The t-test and F-test findings consistently confirm the significant influence of both individual and collective factors, thus confirming that strengthening digital presence, platform credibility, and consistent product quality are strategic foundations in guiding the preferences and purchasing intentions of Blibli consumers in Batam City.

This study aims to comprehensively examine the role of brand image, trust, and promotional intensity in shaping purchasing decisions for Maybelline two-way cake cosmetic products in Batam City. The implemented research design adopted a descriptive quantitative approach involving 204 participants who had actual experience in purchasing the product in question. Respondents were determined through purposive sampling technique based on Jacob Cohen's calculations to ensure empirical representativeness of the research sample. Primary data were collected through the distribution of structured questionnaire instruments, then processed and analyzed using hierarchical statistical stages that included testing the validity and reliability of the instrument, verification of classical assumptions, multiple linear regression modeling, and hypothesis testing through partial (t) and simultaneous (F) tests. Empirical findings indicate that brand image contributes 23.9% to purchasing decisions, trust influences 39.1%, while promotion contributes the most dominant influence at 14.7%. The coefficient of determination (R²) value of 82.9% indicates that the three independent variables are simultaneously able to explain variations in consumer purchasing decisions in a substantial proportion. The results of both partial and simultaneous tests confirm a positive and significant influence between brand image, trust, and promotion on purchasing decisions for Maybelline cosmetics in Batam.

This study was conducted to systematically explore the influence of the level of ease of transactions and the quality of e-commerce services on the process of determining consumer purchasing decisions in Batam City. The research framework was built with a descriptive-oriented quantitative approach through the involvement of 100 respondents who actively utilize digital transaction services, which were determined using a purposive sampling technique based on the Lemeshow formulation to ensure the adequacy and representativeness of the sample. Empirical data were collected through a structured questionnaire and then processed using statistical analysis stages that included testing the validity and reliability of the instrument, evaluation of classical assumptions, multiple linear regression modeling, and verification of hypotheses through t-tests and F-tests. The results of data processing revealed that the variable of ease of transactions contributed 18.8% to purchasing decisions, while service quality contributed an influence of 63.5%. The coefficient of determination (R²) reaching 73.3% indicates that both independent variables simultaneously have substantial explanatory power towards variations in consumer purchasing behavior. Both partial and simultaneous testing confirmed a significant influence, thus confirming that simplifying transaction mechanisms and strengthening digital service quality are strategic determinants in driving e-commerce consumer purchasing decisions in Batam City.

This study aims to analyze the influence of influencer marketing, brand image, and e-WOM on purchasing decisions on the Shopee marketplace. A quantitative descriptive approach was used, involving 204 Shopee consumers who had previously purchased specific products. They were selected using purposive sampling based on Jacob Cohen's calculation guidelines to ensure the sample accurately represented the population. Data were collected through a questionnaire, which was then analyzed using validity and reliability tests, classical assumption evaluation, multiple linear regression, and hypothesis testing using t-tests and F-tests. The regression analysis showed that influencer marketing had a 34.8% influence on purchasing decisions, brand image contributed 32.7%, and e-WOM had an influence of 20.0%. Furthermore, the coefficient of determination (R²) showed that these three variables together explained 86.9% of the variation in consumer purchasing decisions. The t- and F-tests confirmed that each variable had a significant and positive influence, both partially and simultaneously, on purchasing decisions on the Shopee marketplace.

This study aims to determine the extent to which product innovation, brand image, and digital marketing influence the purchasing decisions of Scarlett Whitening consumers in the city of Batam. The subjects of this study are individuals who have used Scarlett Whitening products in Batam City in 2025. The population size could not be determined precisely, so the sample size was determined using the Lemeshow formula, with a total of 100 respondents selected through purposive sampling. The analysis method used is multiple linear regression, supported by a series of tests, including data quality tests, classical assumption tests, and hypothesis tests. The analysis results show that product innovation has an influence of 27.7%, brand image of 28.4%, and digital marketing of 26.5% on consumer purchasing decisions. Meanwhile, the coefficient of determination (R²) value indicates that simultaneously, these three variables can explain 28.9% of the variation in purchasing decisions. Furthermore, the results of the t-test and F-test prove that product innovation, brand image, and digital marketing have a significant effect, both partially and simultaneously, on the purchasing decisions for Scarlett Whitening products in Batam City. Keywords: Product Innovation,Brand Image, Digital Marketing, Purchase Decision.

This study aims to analyze the financial distress condition of PT Garuda Indonesia (Persero) Tbk during the period 2015–2024 using the Springate and Grover models. The research employs a quantitative descriptive approach with secondary data obtained from the company’s annual financial statements. Financial distress analysis is conducted by calculating financial ratios included in each model to describe the company’s financial condition over the observation period. The results indicate that PT Garuda Indonesia (Persero) Tbk experienced financial distress during several periods, particularly before and during the COVID-19 pandemic, which was reflected in weakened liquidity, declining profitability, and reduced efficiency in asset utilization. However, following the financial restructuring process after 2021, both the Springate and Grover models show an improvement in the company’s financial condition, indicating a transition toward a more stable non-distress status. Although the Springate and Grover models use different financial indicators and classification approaches, both are able to descriptively capture the dynamics of financial distress experienced by the company. The differences in classification results reflect the distinct focus of each model, where the Springate model is more sensitive to liquidity and operational performance, while the Grover model emphasizes asset profitability. Therefore, the combined use of both models provides a more comprehensive overview of the financial distress condition of PT Garuda Indonesia (Persero) Tbk during the research period.

This study aims to analyze the effect of inflation and interest rates on the stock prices of banking companies listed in the IDX80 index on the Indonesia Stock Exchange for the 2019–2024 period. Research data were obtained from official reports of banking company stock prices as well as inflation and interest rate data from Bank Indonesia. The study used a quantitative approach with multiple linear regression methods through the SPSS application, and classical assumption tests were conducted as a requirement for analysis. The study population included all IDX80 banking companies, with a saturated sampling technique resulting in five banks that met the criteria during the study period. The results of the partial test indicate that inflation has a positive and significant effect on stock prices, while interest rates have a negative and significant effect on stock prices. This indicates that stable inflation can still improve the performance of the banking sector, while rising interest rates tend to depress stock prices due to increased borrowing costs and a shift in investment to other instruments. The results of the simultaneous test also show that inflation and interest rates together have a significant effect on the stock prices of IDX80 banking companies. The results show that inflation has a significant positive effect on stock prices with a significance value of 0.034, while interest rates have a significant negative effect with a significance value of 0.018. Simultaneously, inflation and interest rates have a significant effect on stock prices with a calculated F value of 14.549 > Ftable 2.70 and a significance of 0.000 < 0.05.

This study aims to analyze the effect of financial literacy and lifestyle on financial management of students of the Management Study Program at Universitas Pamulang. This research uses a quantitative method with an associative approach, with data collected through questionnaires distributed to 160 respondents. Data analysis was conducted using validity tests, reliability tests, classical assumption tests, simple and multiple linear regression analysis, t-test, F-test, and coefficient of determination (R²). The results show that partially financial literacy has a positive and significant effect on financial management with a t-value of 7,161 > t-table 1.975 and a significance value of 0.000 < 0.05, while lifestyle also has a positive and significant effect with a t-value of 6,881 > t-table 1.975 and a significance value of 0.000 < 0.05. Simultaneously, financial literacy and lifestyle have a significant effect on financial management with an F-value of 853.671 > F-table 3.05 and a significance value of 0.000 < 0.05. The coefficient of determination of 0.916 indicates that 91,6% of the variation in students’ financial management is explained by financial literacy and lifestyle, while the remaining 8,4% is influenced by other factors outside this study.

Abstract: Lesson Study is a collaborative process where teachers identify learning problems, plan improvements, implement instruction with one teacher teaching and others observing, evaluate, revise, re-teach, re-evaluate, and disseminate results. This method serves as a reference for HOTS-based classroom instruction aimed at enhancing learning motivation, student achievement, and critical thinking. The community service was conducted at the Tadris Social Sciences Study Program, FTIK, UIN Sayyid Ali Rahmatullah, and MI Podorejo, Sumber Gempol, Tulungagung, through planning, implementation, and reflection stages. This study employed a descriptive qualitative method with a sequential design covering preparation, micro-teaching training, school mentoring, Lesson Study implementation, and comprehensive final evaluation. Observations from this Lesson Study revealed that students demonstrated critical thinking and active participation in learning. This activity is expected to foster synergy among lecturers, teachers, and pre-service teachers in designing, implementing, and evaluating teaching-learning activities, making instructional methods more creative, innovative, and adaptive to technological advancements.

This study aims to develop and implement an artificial intelligence-based reading learning application using Deep Learning technology to enhance the literacy skills of eighth-grade junior high school students. The research employed the Kemmis & McTaggart Classroom Action Research model combined with a mixed-methods approach. Data collection involved pretests and posttests, complemented by observations, interviews, and questionnaires. The findings revealed that the use of this application significantly improved students' reading comprehension, question-answering skills, and overall engagement in the learning process. Key features of the application, such as adaptive learning technology, allowed for real-time adjustments to the difficulty level of the material, which catered to each student’s individual learning pace. Additionally, the provision of instant feedback enhanced the learning experience by helping students understand their progress and areas for improvement. These results suggest that the application is an effective tool in fostering literacy development and aligns with the goals of the Independent Curriculum. Consequently, this Deep Learning-based application offers a promising innovation for improving student literacy skills in the digital age.