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 article discusses one of the problems of using digital technologies, namely the complexity of assessing the effectiveness of their implementation. Since the use of digital twins at the enterprises of the fuel and energy complex (FEC) has recently become relevant, the authors have chosen the digital twins technology for consideration in this article. For the successful implementation of digital technologies, the authors propose a system of evaluation indicators that will measure the effectiveness of Digital Twins implementation and determine the benefits obtained. The advantages of digital twins include improved management and monitoring, optimization of production processes, prediction of equipment failures, as well as reduced maintenance costs and increased overall efficiency of FEC systems. As a methodological basis for the study, authors use the system of balanced indicators proposed by R. Kaplan and D. Norton, which served as the basis for the development of a set of performance indicators of the fuel and energy complex enterprise with the introduction of digital twins. As a result of the study, a list of indicators for monitoring the effectiveness of digital twins implementation was determined. The study identifies performance indicators for digital twin implementation, with future research aimed at quantitative assessments. The enterprise can implement a digital twin system with a WACC of 10.99%, payback period of 8.06 years, IRR exceeding the discount rate by 9.07%, a 3.5% reduction in harmful emissions, and a 2.5% efficiency increase.

An exhaustive analysis and evaluation of fertility indicators in a society including many ethnic groups might provide valuable insights into any discrepancies. This study aims to systematically analyse the fertility rates over specific periods and investigate the differences in levels and patterns between local and expatriate women in Saudi Arabia using the existing data. This analysis used data from credible sources published by the General Authority for Statistics in the Saudi census 2022. The calculation of period fertility indicators started with the most straightforward rates and advanced to more complex ones, followed by a comprehensive description of the advantages and disadvantages of each. The aim was to ascertain fluctuations in fertility rates and analyse temporal patterns. Multiple studies consistently show that the fertility rate among expats in Saudi Arabia is lower than that among Saudi native women. However, the reason for this discrepancy still needs to be discovered since the definitive effect of contraceptive techniques has yet to be confirmed. Moreover, the reproductive trends that have occurred since the early 1980s will persist, although with additional precautions in place.

In the modern economy, non-financial reporting has become an essential tool for evaluating the social performance of companies. This article explores the importance of non-financial reporting as a central element in assessing sustainable performance, focusing on analyzing sustainability reports published by 20 companies listed on the Bucharest Stock Exchange (BVB). The study examines how these companies approach environmental, social, and governance (ESG) aspects in their reports and what is the relationship between these aspects and financial reporting indicators. Through the statistical analysis of the non-financial reports published by companies participating in the study with the help of the Pearson coefficient and the regression equations, the correlation between the financial and non-financial indicators is determined in order to validate the research hypotheses. The results indicate increased attention to transparency and social responsibility, highlighting the correlation between sound reporting practices and cooperative performance by combining social and environmental aspects with financial information. The research also highlights the challenges encountered in the reporting process and the level of compliance with international sustainability standards.

This research aims to delineate the ecocity indicators from the local perspectives in urban communities in the Northeast of Thailand. The research was quantitative survey research. Data was collected from a sample of 400 people who live in Khon Kaen Municipality and Udon Thani Municipality using a questionnaire. Data was analyzed by descriptive statistics and factor analysis. We found that the eco-city indicators from the perspective of people in the urban communities in the Northeast of Thailand were divided into three main criteria: a) economic perspectives; b) social perspectives; and c) environmental perspectives. When considering each aspect, it was found that the economic perspective had a total of 9 issues with an average of 3.06 out of 5.00, the social perspective had a total of 16 issues with an average of 3.76 out of 5.00, and the environmental perspective had a total of 14 issues with an average at 3.00 out of 5.00.