This research presents a novel approach utilizing a self-enhanced chimp optimization algorithm (COA) for feature selection in crowdfunding success prediction models, which offers significant improvements over existing methods. By focusing on reducing feature redundancy and improving prediction accuracy, this study introduces an innovative technique that enhances the efficiency of machine learning models used in crowdfunding. The results from this study could have a meaningful impact on how crowdfunding campaigns are designed and evaluated, offering new strategies for creators and investors to increase the likelihood of campaign success in a rapidly evolving digital funding landscape.

This paper aims to develop a holistic framework for the Maqasid al-Shariah in Responsible Investment (MSRI) index for selected publicly listed companies in the Malaysian capital market. To test the validity of the MSRI framework, a sample of 30 publicly listed companies from 2021 was selected using purposive sampling. The framework consists of eight themes with forty-five elements to evaluate companies based on their annual reports, sustainability reports, and public disclosures. The scores are classified into three categories: Shariah compliant, Shariah non-compliant, and Hajiyyat. Out of the 30 selected companies, the summary of MSRI scores concludes that twenty (20) companies were identified as Shariah compliant, while the remaining four (4) were classified as Shariah non-compliant, and six (6) as Hajiyyat. Overall, the results of the analyses show that the sustainability of the company and society has a higher percentage than the wealth preservation of companies. This research differs substantially from prior work by offering a novel approach that develops a holistic framework integrating Maqasid al-Shariah with elements of responsible investment. This study believes it can provide valuable guidance for formulating Islamic investment public policy for selected investment portfolios.

The growth of mobile Internet has facilitated access to information by minimizing geographical barriers. For this reason, this paper forecasts the number of users, incomes, and traffic for operators with the most significant penetration in the mobile internet market in Colombia to analyze their market growth. For the forecast, the convolutional neural network (CNN) technique is used, combined with the recurrent neural network (RNN), long short-term memory network (LSTM), and gated recurrent unit (GRU) techniques. The CNN training data corresponds to the last twelve years. The results currently show a high concentration in the market since a company has a large part of the market; however, the forecasts show a decrease in its users and revenues and the growth of part of the competition. It is also concluded that the technique with the most precision in the forecasts is CNN-GRU.

This study focuses on the use of the Soil and Water Assessment Tool (SWAT) model for water budgeting and resource planning in Oued Cherraa basin. The combination of hydrological models such as SWAT with reliable meteorological data makes it possible to simulate water availability and manage water resources. In this study, the SWAT model was employed to estimate hydrological parameters in the Oued Cherra basin, utilizing meteorological data (2012–2020) sourced from the Moulouya Hydraulic Basin Agency (ABHM). The hydrology of the basin is therefore represented by point data from the Tazarhine hydrological station for the 2009–2020 period. In order to optimize the accuracy of a specific model, namely SWAT-CUP, a calibration and validation process was carried out on the aforementioned model using observed flow data. The SUFI-2 algorithm was utilized in this process, with the aim of enhancing its precision. The performance of the model was then evaluated using statistical parameters, with particular attention being given to Nash-Sutcliffe efficiency (NSE) and coefficient of determination (R²). The NSE values for the study were 0.58 for calibration and 0.60 for validation, while the corresponding R² values were 0.66 and 0.63. The study examined 16 hydrological parameters for Oued Cherra, determining that evapotranspiration accounted for 89% of the annual rainfall, while surface runoff constituted only 6%. It also showed that groundwater recharge was pretty much negligible. This emphasized how important it is to manage water resources effectively. The calibrated SWAT model replicated flow patterns pretty well, which gave us some valuable insights into the water balance and availability. The study’s primary conclusions were that surface water is limited and that shallow aquifers are a really important source of water storage, especially for irrigation during droughts.