ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
COMPARISON LINEAR REGRESSION AND RANDOM FOREST MODELS FOR PREDICTION OF UNDERGROUND DROUGHT LEVELS IN FOREST FIRES
Get PDFThe increase in forest fires poses a significant risk due to its impact on underground dryness, which can cause long-term environmental damage and challenge fire suppression efforts. This research aims to develop a prediction model for underground drought levels in the context of forest fires using machine learning techniques. The methodology used in this research follows the CRISP-DM (Cross-Industry Standard Process for Data Mining) framework, which includes the stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. This study analyzes a forest fire dataset, applies encoder labels to transform categorical variables, and uses linear regression and random forest models to predict underground drought levels. The goal is to create a predictive model that can help inform wildfire risk management strategies by anticipating underground drought levels. The results showed that the random forest model achieved higher prediction accuracy than the linear regression, with an R-squared value of 0.97. This suggests that the random forest model is a more robust tool for predicting underground drought levels, providing valuable insights for forest fire management. This research contributes to the understanding of underground drought levels, aiding the development of effective wildfire risk management strategies
PREDICTING STUNTING IN TODDLERS IN WEST JAVA USING LINEAR REGRESSION BASED ON POVERTY LEVELS
Get PDFChildren's growth is disrupted by stunting, a chronic nutritional condition brought on by a prolonged shortage of nutrient intake. Under-five stunting is a major issue that affects many nations, particularly those with high rates of poverty. The aim of this research is to use the linear regression method based on the proportion of poverty to predict the risk of stunting in children under five in West Java. Growing children are particularly vulnerable to stunting, which can have long-term effects on their development and health. The research site was selected in West Java Province due to the region's high stunting rates and nofigur poverty rate. Precise forecasts are required to surmount the current issues. The research methodology employed is the descriptive quantitative technique. The data, which was projected using percentage values, covered the years 2014–2020. This study uses linear regression as its algorithm. According to the study's findings, there will be an 8.55% chance of toddler stunting in West Java in 2024. It is hoped that the government would be able to lower the risk of stunting by estimating the proportion of risk
EFIKASI DIRI SEBAGAI MEDIASI DALAM HUBUNGAN LINGKUNGAN KAMPUS DAN MANAJEMEN WAKTU PADA PRESTASI MAHASISWA
Get PDFAcademic achievement is a crucial indicator of the success of higher education processes; therefore, understanding the factors that influence it is essential. A supportive campus environment and effective time management have been widely studied as key determinants of student academic performance, with self-efficacy often positioned as a mediating variable that links the two. At the Faculty of Economics and Business, University of Jember, field findings reveal several issues such as unstable internet access, limited discussion spaces, and underutilized academic advising services, all of which potentially affect students’ self-efficacy and academic achievement. This study aims to analyze the influence of the campus environment and time management on students’ academic performance, with self-efficacy as a mediating variable. A quantitative approach was employed using Partial Least Square Structural Equation Modeling (PLS-SEM) processed through SmartPLS 4.0. The research sample total in 270 respondents by purposive sampling consisted of active undergraduate students at the Faculty of Economics and Business, University of Jember. The results show that both the campus environment and time management have a positive and significant impact on academic achievement. Moreover, self-efficacy was found to play a significant mediating role in the relationship between campus environment and time management with academic performance. These findings highlight the importance of enhancing student self-efficacy through a well-managed learning environment and effective time management training to foster better academic outcomes.Penelitian ini bertujuan untuk menganalisis pengaruh lingkungan kampus dan manajemen waktu terhadap prestasi mahasiswa dengan efikasi diri sebagai variabel mediasi. Penelitian ini menggunakan pendekatan kuantitatif dengan metode Partial Least Square Structural Equation Modeling (PLS-SEM) yang diolah melalui SmartPLS 4.0. Sampel penelitian ini adalah mahasiswa aktif di Fakultas Ekonomi dan Bisnis Universitas Jember. Hasil penelitian menunjukkan bahwa lingkungan kampus dan manajemen waktu berpengaruh positif dan signifikan terhadap prestasi mahasiswa. Selain itu, efikasi diri juga terbukti berpengaruh signifikan dan mampu memediasi hubungan antara lingkungan kampus dan manajemen waktu terhadap prestasi mahasiswa. Temuan ini menekankan pentingnya peran lingkungan belajar yang mendukung dan keterampilan manajemen waktu dalam meningkatkan keyakinan diri serta prestasi akademik mahasiswa
ANALISIS KEPUASAN PELANGGAN AGEN PERJALANAN ONLINE (OTA) APLIKASI MOBILE DI YOGYAKARTA: PENDEKATAN KUANTITATIF
Get PDFAs a leading tourist destination, Yogyakarta has seen a significant increase in the number of visitors, which has also driven the use of digital platforms for accommodation needs. This study aims to analyze consumer satisfaction with the use of Online Travel Agent (OTA) applications for hotel reservations in Yogyakarta. The study employs a quantitative approach through a survey of 130 respondents who have made hotel reservations using OTAs such as Traveloka, Tiket.com, and Agoda. The data were analyzed using multiple linear regression with the aid of SPSS. The results indicate that the Price and Promotion variable has a significant influence on purchasing decisions, while other variables such as Service Quality, User Experience, and Security and Trust do not show significant partial effects. However, all variables collectively have a significant influence on purchasing decisions. These findings can serve as a reference for OTA application developers to enhance features related to pricing and cancellation policies in order to improve user satisfaction.Abstract— This study aims to analyze consumer satisfaction with the use of Online Travel Agent (OTA) applications for hotel reservations in Yogyakarta. As a leading tourist destination, Yogyakarta has seen a significant increase in the number of visitors, which has also driven the use of digital platforms for accommodation needs. The study employs a quantitative approach through a survey of 130 respondents who have made hotel reservations using OTAs such as Traveloka, Tiket.com, and Agoda. The data were analyzed using multiple linear regression with the aid of SPSS. The results indicate that the Price and Promotion variable has a significant influence on purchasing decisions, while other variables such as Service Quality, User Experience, and Security and Trust do not show significant partial effects. However, all variables collectively have a significant influence on purchasing decisions. These findings can serve as a reference for OTA application developers to enhance features related to pricing and cancellation policies in order to improve user satisfaction.
Keywords: OTA, consumer satisfaction, mobile application, hotel reservation, multiple linear regression.
Abstrak— Penelitian ini bertujuan untuk menganalisis tingkat kepuasan konsumen terhadap penggunaan aplikasi Online Travel Agent (OTA) dalam melakukan reservasi hotel di Yogyakarta. Kota Yogyakarta sebagai destinasi wisata unggulan menunjukkan peningkatan signifikan dalam jumlah wisatawan, yang turut mendorong penggunaan platform digital untuk kebutuhan akomodasi. Penelitian menggunakan pendekatan kuantitatif melalui survei terhadap 130 responden yang pernah melakukan reservasi hotel melalui OTA seperti Traveloka, Tiket.com, dan Agoda. Data dianalisis menggunakan regresi linier berganda dengan bantuan SPSS. Hasil penelitian menunjukkan bahwa variabel Harga dan Promo berpengaruh signifikan terhadap keputusan pembelian, sedangkan variabel lain seperti Kualitas Layanan, User Experience, dan Keamanan dan Kepercayaan tidak menunjukkan pengaruh yang signifikan secara parsial. Namun, secara simultan semua variabel berpengaruh signifikan terhadap keputusan pembelian. Temuan ini dapat menjadi acuan bagi pengembang aplikasi OTA untuk meningkatkan fitur-fitur yang berkaitan dengan harga dan kebijakan pembatalan guna meningkatkan kepuasan pengguna.
Kata Kunci: OTA, kepuasan konsumen, aplikasi mobile, reservasi hotel, regresi linier bergand
ADDRESSING DIGITAL STARTUP FAILURE THROUGH THE AGILE METHODOLOGY APPROACH: A SYSTEMATIC LITERATURE REVIEW
Get PDFStartups are recognized as emerging enterprises that contribute to job creation, economic stabilization, and national development. Digital startups are formed to address challenges within their environments. This study aims to provide solutions and preventive measures for digital startup failures, given the persistently high global failure rate of 90%. A systematic literature review (SLR) was conducted to identify Agile-based Critical Success Factors (CSFs), which were then mapped as solutions to mitigate digital startup failures. Based on the findings, the most significant contributing factor to the failure of digital startups is insufficient funding (i.e., running out of capital or financial resources). To address this issue, the agile method offers relevant solutions that can be mapped to the problem, namely the adoption of “Iterative Budget Management,” “Accurate Effort Estimation,” and “Risk Management Strategies.” This study provides practitioners with valuable insights, knowledge, and reference points regarding the critical success factors (CSFs) derived from agile practices, which can serve as strategic mechanisms for mitigating failure in early-stage startups. Moreover, the research is expected to contribute new theoretical understanding that informs potential solutions to prevent digital startup failure
EVALUATION OF USER PERCEPTIONS AND SATISFACTION THROUGH SENTIMENT ANALYSIS NEWS APPLICATIONS WITH NAIVE BAYES
Get PDFThe development of digital technology has driven the transformation of mass media into online news platforms such as Detikcom, Kompas.id, and CNN Indonesia. Competition among these news applications has created the need to evaluate user perceptions of service quality. This study aims to analyze user sentiment toward the three news applications based on reviews from the Google Play Store. The methods employed include web scraping, text pre-processing, labeling using the IndoBERT model, feature extraction with the TF-IDF method, and sentiment classification with the Naive Bayes algorithm. To address class imbalance in the dataset, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. Model evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results show that the Naive Bayes model achieved high accuracy, namely 88.5% for Kompas.id, 88.8% for Detikcom, and 90.8% for CNN Indonesia. The analysis also revealed that positive reviews are more dominant, although recurring criticisms were identified regarding advertisements and technical performance of the applications. The use of Generative AI further assisted in automatically summarizing opinions and sentiment patterns. These findings provide valuable insights for developers in enhancing user experience and refining the features of digital news application
APPLYING TREE BASED MODEL FOR CROP RECOMMENDATION SYSTEM BASED ON SOIL PARAMETERS AND WEATHER CONDITIONS
Get PDFThe massive population in Indonesia needs to be supported by various sectors so that the population's needs are met. One of these sectors is agriculture. The problems are unpredictable climate change and weather and changes in land use from previously agricultural land to housing. In addition, plant quality is also influenced by soil quality and other abiotic factors, comprising rainfall, temperature, and humidity. Plant quality affects the increase in crop yields. A plant recommendation system based on plant parameters must help farmers determine the best plants according to agricultural land conditions. The recommended plants to be used include mango, cotton, rice, mungbeans, and apple. This work aims to create a plant recommendation system utilizing criteria related to plant requirements through a machine learning methodology. The stages in this study start with data collection, preprocessing, partitioning, modelling, performance evaluation, and a recommender system. This study’s results indicate that the Random Forest method achieved the best accuracy at 0.9981, followed by XGBoost at 0.9909 and Decision Tree at 0.9873. The system provided recommendations for plant types based on user inpu
PENERAPAN JARINGAN SYARAF TIRUAN DENGAN ALGORITMA BACKPROPAGATION DALAM MEMPREDIKSI PRODUKSI TANAMAN PADI
Get PDFRice is a staple food crop in Indonesia, including in West Sumatra Province, which plays an important role in national food security. This study aims to develop a rice production prediction model using Artificial Neural Networks (ANN) with the Backpropagation algorithm. Historical rice production data from 2006 to 2023 in 19 regencies/cities in West Sumatra Province were used as the data basis. The research methods include data collection from BPS West Sumatra, data preprocessing, prediction process using the Backpropagation algorithm, and accuracy testing of the prediction results. The results show that ANN with the Backpropagation algorithm can predict rice production with an accuracy rate of 82.56% using an architecture with 16 neurons in the input layer, 9 neurons in the hidden layer, and 1 neuron in the output layer. This prediction model is expected to assist farmers and the government in planning optimal rice production, thereby increasing production and the welfare of farmers in West Sumatra Province. Thus, this research provides significant contributions in supporting decision-making in the agricultural sector, particularly in efforts to enhance food security and the welfare of farmers in the regio
EVALUASI PENERIMAAN MAHASISWA TERHADAP APLIKASI AKADEMIK MOBILE: PENDEKATAN TECHNOLOGY ACCEPTANCE MODEL (TAM)
Get PDFMobile applications are widely used in educational environments to accelerate various academic and administrative tasks. Their presence has enhanced service effectiveness, expedited decision-making, and improved the digital campus ecosystem. This study was conducted to evaluate the acceptance level of MyNusa Student, a mobile-based academic application for students. The Technology Acceptance Model (TAM) framework was employed in this research to assess students’ acceptance of the MyNusa Student application. A total of 238 respondents, all registered students using the application, provided data for this study. Data analysis was carried out using Structural Equation Modeling (SEM) with a Partial Least Squares (PLS) approach to examine the relationships among variables: Perceived Ease of Use, Perceived Usefulness, Attitude Toward Using, Behavioral Intention to Use, and Actual Usage. The results indicated that all relationships among variables were statistically significant. The most influential relationship was observed between Perceived Ease of Use and Perceived Usefulness, followed by the relationship between Attitude Toward Using and Behavioral Intention to Use, and subsequently, Actual Usage. The findings suggest that the primary elements influencing students’ positive perceptions of the application—which in turn affect their intention and actual usage patterns—are their evaluations of its usefulness and utility. The practical implications highlight the need for continuous improvement in usability and utility aspects, with a focus on enhancing ease of use, optimizing core features such as real-time data updates, and improving technical as well as system security aspects
MACHINE LEARNING FOR EMPLOYMENT POSITION MAPPING
Get PDFEmployee performance directly impacts organizational efficiency, yet traditional HR analytics often lack predictive precision. This study bridges HR theory and machine learning by evaluating tree-based algorithms for employee data analysis. Using a dataset of 15,227 employee records, we tested the Bagged Decision Tree algorithm, focusing on variables such as talent, career values, and aspirations. The Bagged Decision Tree achieved 98.65% accuracy, with talent and career values as key predictors. Excluding aspiration values reduced accuracy slightly to 98.57%, while excluding career values lowered it significantly to 92.13%. These findings highlight the robustness of the Bagged Decision Tree in HR analytics and emphasize the importance of variable selection, particularly career values and talent, in predicting performance outcomes. Future work should further explore real-world implementation challenges