This study thoroughly examined the use of different machine learning models to predict financial distress in Indonesian companies by utilizing the Financial Ratio dataset collected from the Indonesia Stock Exchange (IDX), which includes financial indicators from various companies across multiple industries spanning a decade. By partitioning the data into training and test sets and utilizing SMOTE and RUS approaches, the issue of class imbalances was effectively managed, guaranteeing the dependability and impartiality of the model’s training and assessment. Creating first models was crucial in establishing a benchmark for performance measurements. Various models, including Decision Trees, XGBoost, Random Forest, LSTM, and Support Vector Machine (SVM) were assessed. The ensemble models, including XGBoost and Random Forest, showed better performance when combined with SMOTE. The findings of this research validate the efficacy of ensemble methods in forecasting financial distress. Specifically, the XGBClassifier and Random Forest Classifier demonstrate dependable and resilient performance. The feature importance analysis revealed the significance of financial indicators. Interest_coverage and operating_margin, for instance, were crucial for the predictive capabilities of the models. Both companies and regulators can utilize the findings of this investigation. To forecast financial distress, the XGB classifier and the Random Forest classifier could be employed. In addition, it is important for them to take into account the interest coverage ratio and operating margin ratio, as these finansial ratios play a critical role in assessing their performance. The findings of this research confirm the effectiveness of ensemble methods in financial distress prediction. The XGBClassifier and RandomForestClassifier demonstrate reliable and robust performance. Feature importance analysis highlights the significance of financial indicators, such as interest coverage ratio and operating margin ratio, which are crucial to the predictive ability of the models. These findings can be utilized by companies and regulators to predict financial distress.

Delay is the leading challenge in completing Engineering, Procurement, and Construction (EPC) projects. Delay can cause excess costs, which reduces company profits. The relationship between subcontractors and the main contractor is a critical factor that can support the success of an EPC project. The problematic financial condition of the main contractor can cause delay in payments to subcontractors. This research will set a model that combines the system dynamics and earned value method to describe the impact of subcontractor advance payments on project performance. The system dynamics method is used to model and analyze the impact of interactions between variables affecting project performance, while the earned value method is applied to quantitatively evaluate project performance and forecast schedule and cost outcomes. These two methods are used complementarily to achieve a holistic understanding of project dynamics and to optimize decision-making. The designed model selects the optimum scenario for project time and costs. The developed model comprises project performance, costs, cash flow, and performance forecasting sub-models. The novelty in this research is a new model for optimizing project implementation time and costs, adding payment rate variables to subcontractors and subcontractor performance rates. The designed model can provide additional information to assist project managers in making decisions.

Accurate demand forecasting is key for companies to optimize inventory management and satisfy customer demand efficiently. This paper aims to Investigate on the application of generative AI models in demand forecasting. Two models were used: Long Short-Term Memory (LSTM) networks and Variational Autoencoder (VAE), and results were compared to select the optimal model in terms of performance and forecasting accuracy. The difference of actual and predicted demand values also ascertain LSTM’s ability to identify latent features and basic trends in the data. Further, some of the research works were focused on computational efficiency and scalability of the proposed methods for providing the guidelines to the companies for the implementation of the complicated techniques in demand forecasting. Based on these results, LSTM networks have a promising application in enhancing the demand forecasting and consequently helpful for the decision-making process regarding inventory control and other resource allocation.

Background: According to the 2023 World Economic Forum report, the impact of Artificial Intelligence (AI) and automation on the job market was more significant than originally projected. Although 2018 research forecasted significant job losses balanced by job creation, current data indicates otherwise. Between 2023 and 2027, it is anticipated that 69 million new jobs will be created due to advancements in AI, however, this will be offset by the loss of 83 million jobs, leading to a net decrease of 14 million jobs worldwide. Roles related to AI, digitalization, and sustainability, such as AI specialists and renewable energy engineers are expected to grow, while those in clerical and administrative sectors are most at risk of decline. This shift underscores the need for reskilling and adapting to evolving fields, as nearly 44% of workers skills will face disruption by 2027. The demand for analytical thinking, technological literacy, and adaptability will grow as companies increasingly adopt frontier technologies. Objectives: (1) identify key variables influencing adaptability of college graduates in Indonesia, (2) quantify the strength of relationships between these variables to understand the combined effect on graduate adaptability. The research also aims to (3) develop theoretical and practical recommendations to strengthen ICIL policy and equip students with the relevant skills needed to thrive in an ever-changing job market. Methodology: The research focuses on predicting future employment trends, adaptability, and learning agility (LA), along with the implications for improving the Independent Campus Independent Learning (ICIL) policy. It focused on the significant unemployment rate among college graduates, along with the lack of research on the relationship between job change predictions, graduates’ adaptability, and the impact on graduates’ general well-being. The mixed-method strategy with quantitative analysis was used to conduct this research with data collected from 284 ICIL participants through online survey. The gathered data was evaluated using Structural Equation Modeling (SEM) with Lisrel version 10. Results: The result showed that job trend projections significantly influence responsiveness, which demonstrated a robust association between employment trend predictions and LA. Responsiveness significantly influenced learning agility which indicated no significant direct association between job trend projections and graduate adaptability. Conclusion: The research emphasized the need to consider adaptability as a concept with multiple dimensions. It proposed incorporating these factors into strategies for education and human resources development in order to better equip graduates for the demands of a constantly changing work market. Unique contribution: This research focused on adaptability as a multifaceted concept that consist of the ability to forecast job trends, be sensitive, and possess LA. It offered a deeper understanding of the relationships between these variables as discussed in the human resources literature. Technology, corporate culture, and training played a critical role in connecting employment trend prediction with the ability to respond effectively. Key recommendation: Institutions should implement a comprehensive approach to the development of human resources, with emphasis on fostering critical thinking, analytical abilities, and the practical application of information. By employing these tactics, higher education institutions may effectively equip graduates with both academic proficiency and the ability to adapt and thrive in quickly changing organizational environments, leading to the production of robust and versatile workers.

The study explores improving opportunities of forecasting accuracy from the traditional method through advanced forecasting techniques. This enables companies to optimize inventory management, production planning, and reducing the travelling time thorough vehicle route optimization. The article introduced a holistic framework by deploying advanced demand forecasting techniques i.e., AutoRegressive Integrated Moving Average (ARIMA) and Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) models, and the Vehicle Routing Problem with Time Windows (VRPTW) approach. The actual milk demand data came from the company and two forecasting models, ARIMA and RNN-LSTM, have been deployed using Python Jupyter notebook and compared them in terms of various precision measures. VRPTW established not only the optimal routes for a fleet of six vehicles but also tactical scheduling which contributes to a streamlined and agile raw milk collection process, ensuring a harmonious and resource-efficient operation. The proposed approach succeeded on dropping about 16% of total travel time and capable of making predictions with approximately 2% increased accuracy than before.

Fire hazard is often mapped as a static conditional probability of fire characteristics’ occurrence. We developed a dynamic product for operational risk management to forecast the probability of occurrence of fire radiative power in the locally possible near-maximum fire intensity range. We applied standard machine learning techniques to remotely sensed data. We used a block maxima approach to sample the most extreme fire radiative power (FRP) MODIS retrievals in free-burning fuels for each fire season between 2001 and 2020 and associated weather, fuel, and topography features in northwestern south America. We used the random forest algorithm for both classification and regression, implementing the backward stepwise repression procedure. We solved the classification problem predicting the probability of occurrence of near-maximum wildfire intensity with 75% recall out-of-sample in ten annual test sets running time series cross validation, and 77% recall and 85% ROC-AUC out-of-sample in a twenty-fold cross-validation to gauge a realistic expectation of model performance in production. We solved the regression problem predicting FRP with 86% r² in-sample, but out-of-sample performance was unsatisfactory. Our model predicts well fatal and near-fatal incidents reported in Peru and Colombia out-of-sample in mountainous areas and unimodal fire regimes, the signal decays in bimodal fire regimes.