Accurate prediction of US Treasury bond yields is crucial for investment strategies and economic policymaking. This paper explores the application of advanced machine learning techniques, specifically Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) models, in forecasting these yields. By integrating key economic indicators and policy changes, our approach seeks to enhance the precision of yield predictions. Our study demonstrates the superiority of LSTM models over traditional RNNs in capturing the temporal dependencies and complexities inherent in financial data. The inclusion of macroeconomic and policy variables significantly improves the models’ predictive accuracy. This research underscores a pioneering movement for the legacy banking industry to adopt artificial intelligence (AI) in financial market prediction. In addition to considering the conventional economic indicator that drives the fluctuation of the bond market, this paper also optimizes the LSTM to handle situations when rate hike expectations have already been priced-in by market sentiment.

This study aimed to determine the socio-economic poverty status of those living in rural areas using data surveys obtained from household expenditure and income. Machine learning-based classification and clustering models were proven to provide an overview of efforts to determine similarities in poverty characteristics. Efforts to address poverty classification and clustering typically involve comprehensive strategies that aim to improve socio-economic conditions in the affected areas. This research focuses on the combined application of machine learning classification and clustering techniques to analyze poverty. It aims to investigate whether the integration of classification and clustering algorithms can enhance the accuracy of poverty analysis by identifying distinct poverty classes or clusters based on multidimensional indicators. The results showed the superiority of machine learning in mapping poverty in rural areas; therefore, it can be adopted in the private sector and government domains. It is important to have access to relevant and reliable data to apply these machine learning techniques effectively. Data sources may include household surveys, census data, administrative records, satellite imagery, and other socioeconomic indicators. Machine learning classification and clustering analyses are used as a decision support tool to gain an understanding of poverty data from each village. These strategies are also used to describe the profile of poverty clusters in the community in terms of significant socio-economic indicators present in the data. Village clusters based on an analysis of existing poverty indicators are grouped into high, moderate, and low poverty levels. Machine learning can be a valuable tool for analyzing and understanding poverty by classifying individuals or households into different poverty categories and identifying patterns and clusters of poverty. These insights can inform targeted interventions, policy decisions, and resource allocation for poverty reduction programs.

Credit risk assessment is one of the most important aspects of financial decision-making processes. This study presents a systematic review of the literature on the application of Artificial Intelligence (AI) and Machine Learning (ML) techniques in credit risk assessment, offering insights into methodologies, outcomes, and prevalent analysis techniques. Covering studies from diverse regions and countries, the review focuses on AI/ML-based credit risk assessment from consumer and corporate perspectives. Employing the PRISMA framework, Antecedents, Decisions, and Outcomes (ADO) framework and stringent inclusion criteria, the review analyses geographic focus, methodologies, results, and analytical techniques. It examines a wide array of datasets and approaches, from traditional statistical methods to advanced AI/ML and deep learning techniques, emphasizing their impact on improving lending practices and ensuring fairness for borrowers. The discussion section critically evaluates the contributions and limitations of existing research papers, providing novel insights and comprehensive coverage. This review highlights the international scope of research in this field, with contributions from various countries providing diverse perspectives. This systematic review enhances understanding of the evolving landscape of credit risk assessment and offers valuable insights into the application, challenges, and opportunities of AI and ML in this critical financial domain. By comparing findings with existing survey papers, this review identifies novel insights and contributions, making it a valuable resource for researchers, practitioners, and policymakers in the financial industry.

This study comprehensively evaluates the system performance by considering the thermodynamic and exergy analysis of hydrogen production by the water electrolysis method. Energy inputs, hydrogen and oxygen production capacities, exergy balance, and losses of the electrolyzer system were examined in detail. In the study, most of the energy losses are due to heat losses and electrochemical conversion processes. It has also been observed that increased electrical input increases the production of hydrogen and oxygen, but after a certain point, the rate of efficiency increase slows down. According to the exergy analysis, it was determined that the largest energy input of the system was electricity, hydrogen stood out as the main product, and oxygen and exergy losses were important factors affecting the system performance. The results, in line with other studies in the literature, show that the integration of advanced materials, low-resistance electrodes, heat recovery systems, and renewable energy is critical to increasing the efficiency of electrolyzer systems and minimizing energy losses. The modeling results reveal that machine learning programs have significant potential to achieve high accuracy in electrolysis performance estimation and process view. This study aims to contribute to the production of growth generation technologies and will shed light on global and technological regional decision-making for sustainable energy policies as it expands.

This study aims to identify the causes of delays in public construction projects in Thailand, a developing country. Increasing construction durations lead to higher costs, making it essential to pinpoint the causes of these delays. The research analyzed 30 public construction projects that encountered delays. Delay causes were categorized into four groups: contractor-related, client-related, supervisor-related, and external factors. A questionnaire was used to survey these causes, and the Relative Importance Index (RII) method was employed to prioritize them. The findings revealed that the primary cause of delays was contractor-related financial issues, such as cash flow problems, with an RII of 0.777 and a weighted value of 84.44%. The second most significant cause was labor issues, such as a shortage of workers during the harvest season or festivals, with an RII of 0.773. Additionally, various algorithms were used to compare the Relative Importance Index (RII) and four machine learning methods: Decision Tree (DT), Deep Learning, Neural Network, and Naïve Bayes. The Deep Learning model proved to be the most effective baseline model, achieving a 90.79% accuracy rate in identifying contractor-related financial issues as a cause of construction delays. This was followed by the Neural Network model, which had an accuracy rate of 90.26%. The Decision Tree model had an accuracy rate of 85.26%. The RII values ranged from 68.68% for the Naïve Bayes model to 77.70% for the highest RII model. The research results indicate that contractor financial liquidity and costs significantly impact construction operations, which public agencies must consider. Additionally, the availability of contractor labor is crucial for the continuity of projects. The accuracy and reliability of the data obtained using advanced data mining techniques demonstrate the effectiveness of these results. This can be efficiently utilized by stakeholders involved in construction projects in Thailand to enhance construction project management.

This study explores the intricate relationship between emotional cues present in food delivery app reviews, normative ratings, and reader engagement. Utilizing lexicon-based unsupervised machine learning, our aim is to identify eight distinct emotional states within user reviews sourced from the Google Play Store. Our primary goal is to understand how reviewer star ratings impact reader engagement, particularly through thumbs-up reactions. By analyzing the influence of emotional expressions in user-generated content on review scores and subsequent reader engagement, we seek to provide insights into their complex interplay. Our methodology employs advanced machine learning techniques to uncover subtle emotional nuances within user-generated content, offering novel insights into their relationship. The findings reveal an inverse correlation between review length and positive sentiment, emphasizing the importance of concise feedback. Additionally, the study highlights the differential impact of emotional tones on review scores and reader engagement metrics. Surprisingly, user-assigned ratings negatively affect reader engagement, suggesting potential disparities between perceived quality and reader preferences. In summary, this study pioneers the use of advanced machine learning techniques to unravel the complex relationship between emotional cues in customer evaluations, normative ratings, and subsequent reader engagement within the food delivery app context.