Lestari Agusalim

Customer loyalty has become a critical factor for sustaining competitiveness in the hotel industry, particularly in increasingly digital and data-driven business environments. Although hotels continuously generate large volumes of transactional customer data, transforming this data into actionable insights for customer retention and marketing decision-making remains a significant challenge. This study proposes an Explainable Machine Learning Framework for hotel customer loyalty prediction using transactional behavioral data. The study used a publicly available hotel customer transaction dataset from the Mendeley Data repository, comprising 2,000 customer records. A supervised machine learning approach was employed using Logistic Regression, Decision Tree, Random Forest, XGBoost, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes. Model performance was evaluated using Stratified K-Fold Cross-Validation and classification metrics, including Accuracy, Precision, Recall, F1-Score, and ROC-AUC. Experimental results demonstrated that all evaluated models achieved perfect classification performance, with Accuracy, Precision, Recall, F1-Score, and ROC-AUC values reaching 1.000. SHAP analysis revealed that frequency_of_bookings, days_since_last_booking, total_meal_charges, and total_revenue_generated were the primary drivers of customer loyalty prediction, while average_stay_duration showed minimal influence. The findings indicate that booking frequency and customer recency are the most influential behavioral factors affecting loyalty outcomes. From a managerial perspective, the proposed framework provides actionable insights for customer retention, customer segmentation, loyalty programs, and personalized marketing strategies. This study contributes to predictive customer analytics and Explainable Artificial Intelligence by integrating predictive accuracy with transparent interpretation of customer behavior in hotel loyalty management.

Indonesia’s expanding gig economy has reshaped the labor market, offering flexibility while deepening social protection disparities. This study examines the gap in social protection coverage between formal employees and gig workers—online and local—within Indonesia’s employment landscape. Using microdata from August 2018, 2021, and 2023 National Labor Force Surveys (Sakernas), the analysis focuses on the service sector, where gig work is concentrated. A binary logistic regression with marginal effects was used to estimate the probability of workers’ participation in Indonesia’s social security programs. Findings revealed persistent, significant disparities: Online gig workers were 33% less likely and local gig workers 23% less likely to be covered than formal employees. These inequalities widened during and after the COVID-19 pandemic, especially in health and occupational accident insurance. Further analysis showed that disparities were more pronounced among male and urban workers. These results underscore structural vulnerabilities in Indonesia’s dual labor system and highlight the need for inclusive, adaptive social protection reforms. Recommendations include integrating gig workers into national social security schemes through shared contributions, strengthening digital and social protection literacy, and establishing a legal framework that recognizes platform-based employment as part of Indonesia’s labor market.

This study aims to analyze the Marriage Wage Premium (MWP) phenomenon among Generation Z (Gen Z) workers in Indonesia, with a focus on wage differences between those who are married and those who are unmarried. Using data from the National Labor Force Survey for the period of August 2018-2023 published by BPS-Statistics Indonesia, this research employs a logit regression analysis method to explore the impact of marital status on the probability of earning a low wage. The analysis results show that marital status significantly affects the likelihood of earning a low wage, with married workers having a 5.09% higher probability of earning a low wage compared to unmarried workers. Additionally, the analysis reveals that married female workers are more likely to earn a low wage compared to married male workers, with a larger gap observed among women. These findings contradict the classical MWP theory, which asserts that married workers, particularly men, tend to have higher wages. This result suggests that factors such as a more flexible labor market structure, changes in social norms, and the dominance of the informal sector and gig economy may contribute to this phenomenon. Based on these findings, it is recommended that labor policies in Indonesia give more attention to work flexibility and work-life balance, especially for young workers. Programs supporting informal sector workers and policies aimed at reducing gender-based wage disparities are also necessary to create a more equitable labor market for Gen Z.

The low-wage workers play a vital role in supporting in Indonesia's economy but remain highly vulnerable and are often excluded from social protection policies. This study aims to profile low-wage workers and provide insights for policymakers to improve social protection measures. The research utilizes repeated cross-sectional microdata from the National Labor Force Survey (Survei Angkatan Kerja Nasional/Sakernas) between August 2018 and August 2023, a logistic regression model with marginal effects was applied to identify key characteristics of low-wage workers. The findings show that the primary characteristics of low-wage workers are low education levels and working fewer than 20 hours per week. This group is predominantly female, unmarried or divorced, and from younger generations (Gen Z). They are often employed in the informal sector, lacking specific skills, and are mostly working in agriculture. The COVID-19 pandemic worsened their vulnerabilities, amplifying economic risks that persist post-pandemic. The policy implications include expanding educational opportunities to enhance workers' employability, followed by implementing skill training and job placement programs. Additionally, extending minimum wage coverage to both formal and informal sectors, along with offering flexible work arrangements and subsidized childcare, particularly for women, can further support these workers. Furthermore, extending social protection to include social security and healthcare, with incentives for employer contributions, is essential. During crises, policies prioritizing healthcare access, income support, and job protection are crucial for ensuring the economic security of low-wage workers and reducing inequalities.

Community Service through PLS-SEM Training with SmartPLS 4 aims to enhance the analytical skills of facilitators in the Beginner Independent Workforce Program. This program is designed to strengthen the entrepreneurial capacity of beginner entrepreneurs in Indonesia, focusing on the development of micro and small businesses through comprehensive training in business planning, marketing, financial management, and product development. The training method used is participatory and practical, incorporating a real-project simulation with a focus on field data collected by participants, who are facilitators. This method encourages active engagement, allowing facilitators to directly apply their own data in PLS-SEM analysis to understand relationships between variables influencing business success. This method provides a solid foundation for making more data-driven, informed decisions. The participatory approach used in the training allows facilitators to be directly involved in the mentoring process, helping beginner entrepreneurs with relevant and effective solutions. The training results show a significant improvement in facilitators' analytical skills, with an average pre-test score of 53 and a post-test score of 89.5. The Wilcoxon Signed-Rank test confirms a significant difference, indicating the training's effectiveness in enhancing the quality and effectiveness of mentoring. Additionally, facilitators are able to provide better insights into market potential and guide beginner entrepreneurs in facing market challenges.

Religion plays a crucial role not only in shaping individual and group behavior but also in influencing governance structures and economic performance. Many countries incorporate religion into their constitutions, with some adopting official state religions as the foundation of governance, thereby creating theocratic states. This study aims to explore the relationship between religion and state governance, as well as the relationship between religion and economic performance, based on the classification of countries by religion. The data for this analysis is sourced from the World Bank and the Pew Research Center. It encompasses GDP per capita figures for 133 countries for the years 1990 and 2022, along with estimates of the global population by religion in 2050, derived through a cohort-component technique. A descriptive and comparative approach is utilized to explore the relationship between religion, governance, and the economic performance of these nations. This study finds that countries with an official state religion, supported by strong governance and prudent resource management, tend to achieve better economic outcomes, as evidenced by higher GDP per capita levels. Conversely, countries with weak governance or without clear religious support often experience economic stagnation. The findings recommend the importance of integrating religious values into inclusive and sustainable development policies.

Among the most pressing environmental challenges, climate change is anticipated to pose the highest global threat in the coming decade. This research examines the impact of political economic development on per capita CO2 emissions in 29 countries with state religions, applying the frameworks of Environmental Kuznets Curve (EKC) and Pollution Haven Hypothesis (PHH). Employing the Panel Autoregressive Distributed Lag (PARDL) model, the study analyzes data from 1990 to 2022, incorporating both time series and cross-sectional information. The model’s robustness is verified by replacing CO2 emissions per capita with ecological footprint per person. Results indicate that the EKC hypothesis is not supported in most nations, particularly low-income countries still heavily dependent on fossil fuels. In contrast, the PHH hypothesis is confirmed over the long term, with foreign direct investment (FDI) inflows contributing to increase per capita CO2 emissions, especially in countries with lax environmental regulations. Energy consumption and industrial sector contributions significantly affect emissions, while renewable energy consistently reduces CO2 output. Furthermore, democratic political systems are associated with higher emissions, particularly in rapidly growing economies. The study suggests implementing faith-based and sustainability-oriented approaches, such as a faith-driven economy that incorporates spiritual values into green economic policies. Additionally, faith-based investing is recommended to encourage ethical and environmentally responsible business practices. These strategies aim to help countries with official religions strike a balance between economic growth and environmental conservation in the face of climate change.

Income inequality remains a significant issue in developing countries like Indonesia, affecting societal well-being unevenly. Economic growth is often considered a key indicator of social welfare, but its benefits are not always distributed equitably. When economic growth coincides with high levels of income inequality, it suggests that only certain groups reap greater benefits while others are left behind. Therefore, it is essential to analyze whether there are disparities in the influence of economic growth on income inequality in Indonesia before and during the COVID-19 pandemic. Using a random effects model and 12 years of data (2010–2021), this analysis reveals that economic growth does not significantly affect income inequality in Indonesia, challenging the Kuznets hypothesis. Domestic investment (DIN) also shows no influence on income inequality. In contrast, the human development index (HDI) consistently has a significant negative impact on income inequality across both periods. Meanwhile, foreign direct investment (FDI) positively impacts income inequality. There is no difference in the influence of HDI and FDI on income inequality before and during COVID-19. These findings emphasize the importance of improving human resource quality as an effective strategy for addressing income inequality, particularly by enhancing access to education, healthcare services, and overall social welfare.

This study aims to analyze the effectiveness of the monetary policy transmission mechanism through the interest rate channel on inflation in Indonesia. The economic variables used in this study include the Bank Indonesia interest rate, deposit interest rate, and loan interest rate, with data spanning from January 2011 to December 2023. The method employed is the Error Correction Model (ECM) analysis, which allows the researcher to evaluate the relationship between these variables in both the short and long term. The results of the ECM analysis show that the Bank Indonesia interest rate, as one of the primary instruments of monetary policy, has a positive and statistically significant relationship with inflation in both the short and long term. In other words, each increase in the Bank Indonesia interest rate consistently raises inflation during both periods, highlighting the key role of the benchmark interest rate in the transmission of monetary policy in Indonesia. On the other hand, the variables of the deposit interest rate and loan interest rate exhibit different results. Both variables show a negative and statistically significant relationship with inflation in the short and long term. This means that an increase in the deposit and loan interest rates tends to reduce inflation, indicating that raising interest rates in these instruments can help mitigate inflationary pressures by curbing consumption, investment, and the amount of money circulating in the market. This study provides important insights into how the monetary policy transmission mechanism operates in Indonesia through the interest rate channel and highlights the differing impacts of the Bank Indonesia interest rate and other interest rates on inflation over various timeframes.

This study aims to prove whether the efficiency wage theory applies in Indonesia using panel data analysis consisting of 33 provinces over a nine-year period (2010-2018). The theory posits that wage increases enhance worker productivity. The empirical findings confirm the validity of the efficiency wage theory in Indonesia, particularly in urban areas. Nominal wages have a larger positive impact on labor productivity compared to real wages and provincial minimum wages (PMW). An increase in women’s wages significantly influences labor productivity more than male wages. However, if the wage gap between males and womens widens, it can decrease aggregate labor productivity, leading to inefficiencies in the labor market and reducing the competitiveness of Indonesian workers. Geographically, wage increases in urban areas boost labor productivity, but this effect is not applicable to rural areas. The widening wage gap between urban and rural areas can increase labor productivity but may also widen development disparities between regions. Therefore, it is recommended that the government formulate wage policies supporting the welfare and productivity of workers without gender or regional discrimination. The People’s Representative Council (DPR) should enact comprehensive laws protecting women’s rights. The government, in collaboration with the legislature, can provide workforce training in rural areas to enhance knowledge and skills.Keywords: efficiency wage theory, wages, productivity, labor, wages gapAbstrak Penelitian ini bertujuan untuk membuktikan apakah teori upah efisiensi berlaku di Indonesia menggunakan analisis data panel yang terdiri atas 33 provinsi dalam kurun waktu sembilan tahun (2010-2018). Teori tersebut menyatakan bahwa kenaikan upah akan meningkatkan produktivitas pekerja. Hasil penelitian ini mengonfirmasi teori upah efisiensi secara empiris terbukti terjadi di Indonesia, khususnya di wilayah perkotaan. Upah nominal memiliki dampak positif yang lebih besar dibandingkan upah riil dan upah minimum provinsi (UMP) terhadap produktivitas tenaga kerja. Kenaikan upah perempuan berpengaruh lebih signifikan terhadap produktivitas tenaga kerja dibandingkan laki-laki. Namun, apabila kesenjangan upah antara laki-laki dan perempuan melebar makan akan menurunkan produktivitas tenaga kerja secara agregat sehingga menciptakan inefisiensi di pasar tenaga kerja dan mengurangi daya saing tenaga kerja Indonesia. Secara kewilayahan, peningkatan upah di perkotaan meningkatkan produktivitas tenaga kerja, tetapi tidak berlaku untuk wilayah pedesaan. Lebar kesenjangan upah antara kota dan desa dapat meningkatkan produktivitas tenaga kerja, namun dapat pula memperluas ketimpangan pembangunan antarwilayah. Oleh karena itu, pemerintah disarankan untuk merumuskan kebijakan upah yang mendukung kesejahteraan dan produktivitas tenaga kerja tanpa diskriminasi gender atau wilayah. Dewan Perwakilan Rakyat (DPR) perlu mengeluarkan undang-undang perlindungan hak-hak perempuan secara komprehensif. Pemerintah bersama DPR dapat menyediakan pelatihan tenaga kerja di pedesaan untuk meningkatkan pengetahuan dan keterampilan.Kata kunci: teori upah efisiensi, upah, produktivitas, tenaga kerja, kesenjangan upah