Publication Search

This study aims to develop an accurate predictive model for identifying students at risk of academic dropout using Decision Tree and Random Forest algorithms. The research utilizes a publicly available dataset sourced from Kaggle, which includes academic and demographic features such as GPA, attendance, credit load, financial aid status, and exam scores. The methodology involves several stages: data collection, preprocessing (handling missing values, encoding categorical variables, and feature scaling), model training, and evaluation using performance metrics such as Accuracy, Precision, Recall, F1-Score, and Confusion Matrix. Results show that the Random Forest algorithm outperforms Decision Tree in terms of accuracy and robustness, with notable feature importance on math, reading, and writing scores. The findings highlight the potential of machine learning in early detection of dropout risks and provide actionable insights for academic institutions to design timely interventions. This research contributes to the growing field of educational data mining and supports data-driven decision-making processes in higher education management.

Lungs are vital organs in the human respiratory system, responsible for fulfilling the body's oxygen needs. If the lungs experience health problems, it can have adverse effects on the human respiratory system. Common causes of lung diseases are usually due to inhaling air contaminated by dust, smoke, viruses, and bacteria. This study aims to compare the performance of two classification algorithms, namely Random Forest and Naive Bayes, in predicting lung diseases. The data used was obtained from the Kaggle website and processed using RapidMiner software. The attributes involved include smoking habits, pre-existing conditions, staying up late, exercise activities, age, and outcomes. Based on the test results, the Random Forest algorithm demonstrated the best performance with an accuracy of 93%, while the Naive Bayes algorithm achieved an accuracy of 87%. These findings indicate that the Random Forest algorithm outperforms the Naive Bayes algorithm in terms of lung disease prediction accuracy.

This study proposes a hybrid approach combining Frequent Itemset Mining (FIM) and Algorithms and Genetic Algorithm for product layout optimization with a case study at PT. MPI Pharmacy. The FIM Algorithms is employed to extract association rules from 1,000 beauty product sales transactions, while the Genetic Algorithm is utilized to perform product placement based on these rules generated, with storage space constraints. Implementation results demonstrate that this hybrid approach successfully identifies 18 key association rules (support >15, confidence >80%) and proposes an optimal layout configuration model that reduces customer travel distance by 25 compared to conventional layouts used by MPI Pharmacy. The Genetic Algorithm solves complex rule-based optimization problems for product placement, which are limited by traditional market basket analysis (MBA) approaches that rely solely on association rules. This hybrid sistem not only improves pharmacy operational efficiency at PT MPI (reducing service time by 18) but also increases cross-selling opportunities by 22. Hence, inventory operations management impproved efficiently. The research findings contribute to the field of retail space optimization by effectively integrating association rule mining and evolutionary computation.  

The purpose study aims to analize the effect of the environmental social governance & tax agresivity with Role political connection as moderation variable. In this study the theory used as the basis for this test is Legistimachy theory & Political Cost Hypotesis theory, This study aims to examine the environmental, social and governance aspects of tax aggressiveness and to examine whether political connections can moderate environmental social governance on tax aggressiveness in manufacturing, mining, & agro companies listed on the Indonesia Stock Exchange (IDX).. Sample measurements in this research were using quantitative techniques.  The objects used as samples in this test were 60 companies The type of data used as the research object is documentary, namely financial reports of companies by selecting the time period 2021 to 2023 respectively. This research uses outer model, inner model & hypothesis testing. The results show that each dimension of the environment social and governance does not have a direct effect on tax aggressiveness with a significance value of p value above 0.05 and t statistic shows a coefficient below 1.966. However, the indirect effect shows that political connections can act as a negative moderator of the relationship between the environment and tax aggressiveness with a significance value of p value 0.020 and t statistic 2.330. In addition, political connections can also act as a positive moderator of the relationship between governance and tax aggressiveness with a significance value of p value 0.004 and t statistic 2.906. However, political connections cannot moderate the relationship between the social environment and tax aggressiveness with a significance value of p value e 0.081 and t statistic 1.745.

By using earnings management and cash flow as intervening variables, this study aims to investigate how company value is influenced by ownership structure, company characteristics, and capital structure. This research method employs a quantitative approach. The secondary data used in this study comes from the financial statements of mining sector companies listed on the Indonesia Stock Exchange from 2019 to 2023. Smart-PLS software is used to perform data analysis. Out of the eleven proposed hypotheses, only hypothesis H3 is accepted, which indicates that Ownership Structure has a significant impact on Company Value.  

Penelitian ini bertujuan untuk mengelompokkan penjualan berbagai merek beras di UD. Nainggolan menggunakan algoritma K-Means Clustering. UD. Nainggolan merupakan usaha yang bergerak di bidang penjualan sembako, termasuk beras dari berbagai merek. Permasalahan utama yang dihadapi adalah kesulitan dalam memahami tren penjualan dan preferensi pelanggan, yang berdampak pada pengelolaan stok dan strategi pemasaran. Penelitian ini memanfaatkan data penjualan dari Maret 2024 hingga Februari 2025, dengan fokus pada 9 merek beras. Data dianalisis untuk diklasterisasikan ke dalam 2 kategori:, laris, dan kurang laris. Hasil dari penelitian ini adalah sebuah sistem berbasis web yang dibangun menggunakan PHP dan MySQL, yang mampu mengelompokkan penjualan beras berdasarkan algoritma K-Means. Sistem ini diharapkan dapat membantu pihak manajemen dalam pengambilan keputusan terkait pengelolaan stok dan strategi penjualan yang lebih efisien dan tepat sasaran.

The mining sector in Indonesia inherently involves high OSH (Occupational Safety and Health) and Environmental risks, necessitating strict adherence to regulations like Ministerial Decree of Energy and Mineral Resources No. 1827/2018 and Directorate General of Mineral and Coal Decree No. 185/2019. PT Putra Perkasa Abadi (PPA) at the Borneo Indobara Site launched the Indobara Pillar Program to optimize SHE (Safety, Health, Environment) performance and achieve "gold category" status. This research aims to analyze the effectiveness of the program's implementation from February to June 2024, and to identify its supporting and hindering factors. As a case study, this research will describe the implementation process, evaluate target achievement, and analyze influencing factors. Despite the program's launch, January 2024 data showed initial challenges: 67% overall program achievement, with only 38% of programs being effective. Key issues included inconsistent monitoring, unsuitable forms, poor synchronization of internal leading indicator data, insufficient understanding among SHE Group Leaders, and suboptimal personal safety awareness. These challenges directly impacted SHE performance targets. In conclusion, this in-depth analysis is expected to identify how the Indobara Pillar Program can be optimized, contribute to OSH/SHE literature, and enhance the company's safety culture comprehensively.

PT. PLN (Persero) UP3 Binjai faces challenges in handling electricity usage violations that increase every year. Lack of utilization of data violations that can be utilized to produce useful information in supporting strategic decision making by PLN, especially in the implementation of Electricity Usage Control (P2TL) activities. This study aims to identify customer violation patterns based on rayon, power, and type of violation with data mining methods using the K-Means Clustering algorithm. The results of the study show that the 3rd cluster represents the most violation-prone area, namely in the West Binjai Rayon, with a power of 450 VA and the most frequent type of P2 violation. The results of the study show that the K-Means algorithm with the Elbow method is able to systematically group data violations based on certain characteristics. The results of this study can provide recommendations to PLN UP3 Binjai to improve the effectiveness of monitoring and enforcement strategies through a more targeted approach.  

This study aims to examine the implementation of post-mining environmental rehabilitation programs carried out by PT Bukit Asam Tbk in the Tanjung Enim mining area, South Sumatra. Coal mining activities have significant ecological impacts, especially on vegetation damage, soil erosion, and habitat degradation. In this context, rehabilitation efforts are a crucial step to restore the ecosystem and ensure environmental sustainability. The method used in this study is a qualitative literature study with a descriptive-analytical approach to official company documents, environmental reports, and relevant academic references. The results of the study indicate that PT Bukit Asam has implemented various rehabilitation strategies, including revegetation, wastewater management, and community empowerment through agroforestry programs. The success of this program is reflected in the increased vegetation cover, land stability, and biodiversity indicators in the reclamation area. However, challenges such as natural factors and limited supervision still need to be addressed. In conclusion, the rehabilitation practices carried out by this company can be used as a model for sustainable post-mining management in Indonesia. This study recommends the need for multi-sector collaboration and increased transparency and monitoring technology to support long-term effectiveness.

This study aims to analyze the effect of audit quality, earnings power, and risk-taking behavior on firm performance, while also testing the moderating role of the risk management committee. The research was conducted on 18 mining companies listed on the Indonesia Stock Exchange (IDX) during the 2019–2023 period. A quantitative approach was employed using moderated regression analysis (MRA). The results show that only earnings power has a positive and significant effect on firm performance, whereas audit quality and risk-taking behavior have no significant effect. Additionally, the risk management committee strengthens the influence of audit quality on firm performance but does not moderate the relationship between earnings power or risk-taking behavior and performance. These findings suggest that internal oversight through the risk management committee is only effective in the context of audit but not yet optimal in managing earnings or risk-taking. This study contributes to corporate governance literature in the mining sector by emphasizing the importance of an active and strategic risk management committee.  

Crime is a social issue that continues to evolve alongside increasing community activity and regional development. This study aims to Cluster crime data in Binjai City based on the location of incidents using the K-Means algorithm and the Cross Industry Standard Process for Data Mining (CRISP-DM) approach. The data were obtained from the Binjai Police Department, with attributes including the type of crime, time of occurrence, and location, categorized by district. A comprehensive data preprocessing stage was carried out, involving the extraction of information from raw data, normalization of crime type labels, and conversion of categorical data into numerical form using label encoding. The optimal number of Clusters was determined using the Silhouette score method, which yielded the best result at K = 10. The Clustering results were further evaluated using the Davies-Bouldin Index (DBI) to ensure Cluster quality. The analysis revealed that Binjai Utara District has the highest number of crimes, particularly aggravated theft (curat), which frequently occurs from early morning to late morning. This Clustering is expected to provide valuable insights for authorities in formulating more targeted and data-driven regional security strategies.

Background: Coal mining is one of the industrial sectors with broad impacts on environmental conditions and public health. Communities living near mining areas are at risk of exposure to air pollution, water contamination, ecosystem disruption, and increased disease burden, particularly respiratory illnesses. Objective: This study aims to systematically review scientific evidence on the impact of coal mining on health and the environment in communities living around mining areas in Indonesia. Methods: This literature review analyzed seven scientific publications from 2014 to 2024, obtained from university repositories and accredited national journals. Inclusion criteria included studies conducted in Indonesia, relevance to health and/or environmental issues, and complete data presentation. Each article was thematically extracted and analyzed. Results: The studies revealed that coal mining activities contribute to increased cases of ARI (acute respiratory infections), pharyngitis, digestive disorders, and even potential exposure to natural radioactivity. Environmental impacts included air pollution from coal dust, decreased water quality, and unmanaged mining residues. Some studies also highlighted significant public health costs, despite companies having obtained environmental certifications. Conclusion: The health and environmental impacts of coal mining on surrounding communities are real and multidimensional. Therefore, a cross-sectoral approach involving environmental monitoring, public education, and evidence-based policymaking is needed to minimize long-term risks.

Public transportation, with Transjakarta as its main pillar, requires a deep understanding of customer behavior to improve service quality and maintain loyalty. This study aims to segment Transjakarta customers using data mining techniques, specifically the K-Means Clustering algorithm, based on the RFM (Recency, Frequency, Monetary/Value) behavioral model. 37,900 rows of raw transaction data were processed into a clean database, resulting in 1,917 unique customers for analysis. The RFM metrics were then normalized using Min-Max Scaler. The optimal number of clusters was evaluated using the Elbow Curve and Silhouette Score Methods, which led to the determination of k = 4 clusters. The segmentation results identified four customer groups requiring specific strategies: Cluster 3 (Champions) with high R, F, and V (requiring rewards and retention); Cluster 0 (Active, Low Value) with high R and F but low V (requiring upsells and cross-sells); Cluster 1 (Potential/At-Risk); and Cluster 2 (Dormant/Lost). Preliminary analysis (EDA) showed that nearly half of customers (49.3%) used Bank DKI cards, dominated by the productive age group (25–45 years old), with the Rusun Kapuk Muara–Penjaringan route being the busiest. The main managerial recommendation is to strengthen the partnership with Bank DKI and optimize services in this busy corridor.

The purpose of this study is to analyze the state impact caused by each corruption case in Indonesia from 2022-2025. This research uses descriptive qualitative research. The data in this study are secondary data sourced from scientific journal articles, reports from anti-corruption organizations, such as TI, ICW, KPK, and mass media. Data collection techniques are in the form of literature studies with analysis techniques by analyzing data reduction or selecting relevant information, presenting data arranged systematically, and drawing conclusions. The results of this study show that these cases resulted in very significant state economic losses, reaching trillions of rupiah. In addition to financial losses, corruption also has a negative impact on the environment, infrastructure, business climate, and public trust in the government and BUMN. Extensive environmental damage occurred due to illegal mining practices, while BTS 4G projects were hampered in their construction, and in other cases reduced investor and public confidence. Overall, the corruption exposed weaknesses in oversight and governance systems in SOEs and government projects.

Mining is a two-edged sword, which makes a positive contribution to the economy but has a negative impact in the form of environmental degradation. Reclamation is a step taken in restoring former mining land to provide sustainable social, economic, and environmental benefits. This requires an early understanding of reclamation for the younger generation as agents of change. This community service activity aims to provide socialization about the concept, urgency, and practice of mine reclamation to students of Senior High School Number 19 Palembang as a form of environmental education towards sustainable mining. The methods used include interactive presentations and joint discussions. The results of the activity showed a significant increase in students' understanding of the issue of mine reclamation, as well as high enthusiasm and active participation in the entire series of activities. This activity contributes to fostering ecological awareness among students, as well as a form of collaboration between higher education institutions and schools in supporting sustainable development in the mining sector. The development of a collaborative-based follow-up program is needed so that this environmental education can take place continuously.

In the Kutai Basin area, seasonal changes such as high rainfall can significantly increase groundwater content, so that the effect of water content on the shear strength of claystone, increasing water content in rocks tends to decrease shear strength. Water in the pores or fractures can increase pore water pressure and reduce effective normal stress. Shear strength is one of the most important mechanical parameters used to assess soil and rock stability, this parameter is very important in slope stability analysis, foundation planning, and various civil engineering and mining applications. Therefore, this study was conducted to determine whether the water content in rocks can affect the strength of rocks in receiving shear forces. The method used in this study is more quantitative and specific to the effect of water content on the shear strength of claystone in this area. Increasing water content in rocks tends to reduce shear strength. This study was conducted by taking claystone samples from several locations in the Kutai Basin. Data collection in the form of primary data and secondary data for testing physical properties and testing mechanical properties, in testing physical properties, the water content value will be taken as supporting data which is one of the factors that affect rock strength, in testing mechanical properties, claystone shear strength data will be taken. From the results of the physical properties test calculations, the air content in each Formation is obtained, namely, in the Kampungbaru Formation the minimum air content value is 15.54% and the maximum is 20.17%, in the Balikpapan Formation the minimum air content value is 10.21% and the maximum is 12,88%, in the Palaubalang Formation the minimum air content value is 10.49% and the maximum is 22.87%. The results of the strength of the claystone in receiving shear forces in the Kutai Basin are the Muara Jawa location 0.486MPa, Tanah Datar location 0.500 MPa, Sanga-sanga location 0.333 MPa, Muara Badak location 0.269, Air Putih location 0.711MPa, Mugirejo location 0.021 MPa and Lempake location 0.092 MPa.

This study aims to evaluate the performance of the loading and unloading equipment in coal mining activities at the Mahakam Pit, PT Insani Bara Perkasa Site Km 11, East Kalimantan. The research was motivated by the importance of achieving mechanical equipment performance standards according to the Decree of the Minister of Energy and Mineral Resources No. 1827 of 2018. Data were obtained through direct observation and analysis of actual working time and evaluation of operational constraint factors. The results of the analysis showed that before the evaluation, the mechanical availability (MA) value was 87.24%, physical availability (PA) 88.51%, availability utilization (UA) 88.73%, and effective utilization (EU) 78.54%. After evaluating the constraint time, there was an increase in all parameters: MA to 88.71%, PA to 89%, UA increased to 90%, and EU reached 80%. This evaluation also had an impact on increasing the productivity of the loading and unloading equipment from 268.41 bcm/hour to 284.43 bcm/hour. Thus, the evaluation of work obstacles is proven to be effective in increasing the efficiency and productivity of the digging-loading equipment at the research location.

The mining system applied by PT Bukit Baiduri Energi is an open pit mining system utilizing the open-pit method. The application of the open-pit method creates a depression that has a high potential to become a catchment area for both surface runoff and groundwater. In the mining pit of PT Bukit Baiduri Energi, there is a sump located at an elevation of -86 meters above sea level (mdpl). The planned mining boundary is at an elevation of -110 mdpl. Therefore, this research aims to determine the area of the catchment, runoff discharge values, sump capacity, and pump capacity, so that the volume of incoming water can be known, allowing for the control of the sump to prevent overflow that could disrupt mining activities.. Based on the data obtained and the calculations performed, the catchment area was found to be 103.42 ha. In the calculation of runoff discharge using the rational method, the total runoff discharge entering sump A9 was found to be 4,211.66 m3/day. The capacity of the sump was measured at 125,187.62 m3. In the pump capacity calculation, the pump capacity based on the pumping discharge was found to be 2,926.80 m3/day.

Disposal area is an area at an open pit mine that is used as a place to store or dispose of worthless materials. Disposal must also follow the specified safety factor standards, if the disposal design is not safe after being analyzed by a geotechnical engineer, the design must be redesigned to achieve the desired safety factor value. One way to increase the fk value is to make a Counterweight plan in making disposal. Where Counterweight is a fill material that is made with special treatment so that the soil bearing capacity increases which functions to withstand the load on it. Landslides on disposal slopes are one of the serious problems faced in mining activities, especially in areas with vulnerable geological and topographic conditions. PT Jembayan Muarabara, which operates in Marangkayu District, Kutai Kartanegara Regency, East Kalimantan Province, is no exception to this challenge. The A–A’ cross section shows a safety factor value of 1.118 in saturated conditions, which indicates that the slope is at a stable limit and needs to be improved through engineering such as adding counterweights. The B–B’ cross-section has a safety factor value of 2.332, which is included in the safe category and has met the provisions of the ESDM Ministerial Decree No. 1827 K/30/MEM/2018. The C-C’ cross-section has a safety factor value of 1.511, which is included in the safe category and has met the provisions of the ESDM Ministerial Decree No. 1827 K/30/MEM/2018.

This study aims to identify the leading economic sectors in East Kalimantan Province and analyze their influence on the development of the National Capital of the Archipelago (IKN) as an economic superhub. Using secondary data from 2019–2023, the analysis applies Location Quotient (LQ), Dynamic LQ (DLQ), Shift-Share, and SWOT methods to evaluate the regional economy. Results show that the mining and quarrying sector remains dominant, while agriculture and processing industries demonstrate stable potential for sustainable growth. The study also highlights the urgency of economic diversification, human capital development, and renewable energy as strategic steps to reduce dependence on extractive sectors. The formation of a collaborative blueprint between regional governments, businesses, and communities with the IKN Authority is proposed to strengthen connectivity and economic integration. This research provides critical insights for policy formulation to support East Kalimantan’s transformation as a central player in national development.