The goal of this work was to create and assess machine-learning models for estimating the risk of budget overruns in developed projects. Finding the best model for risk forecasting required evaluating the performance of several models. Using a dataset of 177 projects took into account variables like environmental risks employee skill level safety incidents and project complexity. In our experiments, we analyzed the application of different machine learning models to analyze the risk for the management decision policies of developed organizations. The performance of the chosen model Neural Network (MLP) was improved after applying the tuning process which increased the Test R² from −0.37686 before tuning to 0.195637 after tuning. The Support Vector Machine (SVM), Ridge Regression, Lasso Regression, and Random Forest (Tuned) models did not improve, as seen when Test R² is compared to the experiments. No changes in Test R²’s were observed on GBM and XGBoost, which retained same Test R² across different tuning attempts. Stacking Regressor was used only during the hyperparameter tuning phase and brought a Test R² of 0. 022219.Decision Tree was again the worst model among all throughout the experiments, with no signs of improvement in its Test R²; it was −1.4669 for Decision Tree in all experiments arranged on the basis of Gender. These results indicate that although, models such as the Neural Network (MLP) sees improvements due to hyperparameter tuning, there are minimal improvements for most models. This works does highlight some of the weaknesses in specific types of models, as well as identifies areas where additional work can be expected to deliver incremental benefits to the structured applied process of risk assessment in organizational policies.

The emergence of the COVID-19 pandemic led to the need to move educational processes to virtual environments and increase the use of digital tools for different teaching uses. This led to a change in the habits of using information and communication technologies (ICT), especially in higher education. This work analyzes the impact of the COVID-19 pandemic on the frequency of use of different ICT tools in a sample of 950 Latin American university professors while focusing on the area of knowledge of the participating professors. To this end, a validated questionnaire has been used, the responses of which have been statistically analyzed. As a result, it has been proven that participants give high ratings to ICT but show insufficient digital competences for its use. The use of ICT tools has increased in all areas after the pandemic but in a diverse way. Differences have been identified in the areas of knowledge regarding the use of ICT for different uses before the pandemic. In this sense, the results suggest that Humanities professors are the ones who least use ICT for didactic purposes. On the other hand, after the pandemic, the use of ICT for communication purposes has been homogenized among the different knowledge areas.

Poverty, as a phenomenon, remains an obstacle to global sustainable development. Although a universal malaise, it is more prevalent in underdeveloped countries, including Nigeria. However, because of its devastating impacts on the Nigerian economy, such as increasing death rates, high crime rates, insecurity difficulties, threats to national cohesion, and so on, successive administrations have implemented poverty alleviation programs to mitigate the consequences of this disease. Worryingly, despite a multiplicity of projects and massive human and natural resources invested to match global standards, Nigeria remains impoverished. The curiosity at how these programs fail, either because of implementation hiccups or because elites’ wealth and power influence these programs spurred the paper to assess poverty alleviation policies and elitist approaches in Nigeria. The study employed the desk study approach, as it examined secondary sources such as books, journals, articles, and magazines. Its theoretical underpinning was the elite theory. The paper discovered that several factors such as corruption, the elitist nature of the policies which in disguise reflect public interests, lack of continuity, lack of coordination and monitoring system, misappropriation of public resources, and others, led to the poor performances of government in alleviating poverty in Nigeria. The paper concludes that, while the rate of poverty index in Nigeria rises year after year, poverty alleviation efforts in Nigeria have had little or no influence on the Nigerian economy, since most of these projects are purely reflective of the elites’ interests rather than the masses. Therefore, the paper recommends that for there to be a reduction in poverty incidence in Nigeria, a holistic developmental approach should be adopted, the policies formulated and implemented should sync with the needs of the citizens, and quality and viable programs should be sustained and financed irrespective of change in government; public accountability should be instilled; proper coordination and monitoring system should be domesticated, etc.

Photocatalysis, an innovative technology, holds promise for addressing industrial pollution issues across aqueous solutions, surfaces, and gaseous effluents. The efficiency of photodegradation is notably influenced by light intensity and duration, underscoring the importance of optimizing these parameters. Furthermore, temperature and pH have a significant impact on pollutant speciation, surface chemistry, and reaction kinetics; therefore, process optimization must consider these factors. Photocatalytic degradation is an effective method for treating water in environmental remediation, providing a flexible and eco-friendly way to eliminate organic contaminants from wastewater. Selectivity in photocatalytic degradation is achieved by a multidisciplinary approach that includes reaction optimization, catalyst design, and profound awareness of chemical processes. To create efficient and environmentally responsible methods for pollution removal and environmental remediation, researchers are working to improve these components.

This research delves into the urgent requirement for innovative agricultural methodologies amid growing concerns over sustainable development and food security. By employing machine learning strategies, particularly focusing on non-parametric learning algorithms, we explore the assessment of soil suitability for agricultural use under conditions of drought stress. Through the detailed examination of varied datasets, which include parameters like soil toxicity, terrain characteristics, and quality scores, our study offers new insights into the complexities of predicting soil suitability for crops. Our findings underline the effectiveness of various machine learning models, with the decision tree approach standing out for its accuracy, despite the need for comprehensive data gathering. Moreover, the research emphasizes the promise of merging machine learning techniques with conventional practices in soil science, paving the way for novel contributions to agricultural studies and practical implementations.