As market saturation and competitive pressure intensify within the banking sector, the mitigation of customer churn has emerged as a critical concern. Given that the cost of acquiring new clients substantially exceeds that of retaining existing ones, the development of highly accurate churn prediction models has become imperative. In this study, a hybrid customer churn prediction model was developed by integrating Sentence Transformers with a stacking ensemble learning architecture. Customer behavioral data containing textual content was transformed into dense vector representations through the use of Sentence Transformers, thereby capturing contextual and semantic nuances. These embeddings were combined with normalized structured features. To enhance predictive performance, a stacking ensemble method was employed to integrate the outputs of multiple base models, including random forest, Gradient Boosting Tree (GBT), and Support Vector Machine (SVM). Experimental evaluation was conducted on real-world banking data, and the proposed model demonstrated superior performance relative to conventional baseline approaches, achieving notable improvements in both accuracy and the area under the curve (AUC). Furthermore, the analysis of model outputs revealed several salient predictors of customer attrition, such as anomalous transaction behavior, prolonged inactivity, and indicators of dissatisfaction with customer service. These insights are expected to inform the development of targeted intervention strategies aimed at strengthening customer retention, improving satisfaction, and fostering long-term institutional growth and stability.

Significant advancements in artificial intelligence (AI) have transformed clinical decision-making, particularly in disease detection and management. Endometriosis, a chronic and often debilitating gynecological disorder, affects a substantial proportion of reproductive-age women and is associated with pelvic pain, infertility, and a reduced quality of life. Despite its high prevalence, non-invasive and accurate diagnostic methods remain limited, frequently resulting in delayed or missed diagnoses. In this study, a novel diagnostic framework was developed by integrating deep learning (DL) with explainable artificial intelligence (XAI) to address existing limitations in the early and non-invasive detection of endometriosis. Abdominopelvic magnetic resonance imaging (MRI) data were obtained from the Crestview Radiology Center in Victoria Island, Lagos State. Preprocessing procedures, including Digital Imaging and Communications in Medicine (DICOM)-to-PNG conversion, image resizing, and intensity normalization, were applied to standardize the imaging data. A U-Net architecture enhanced with a dual attention mechanism was employed for lesion segmentation, while Gradient-weighted Class Activation Mapping (Grad-CAM) was incorporated to visualize and interpret the model’s decision-making process. Ethical considerations, including informed patient consent, fairness in algorithmic decision-making, and mitigation of data bias, were rigorously addressed throughout the model development pipeline. The proposed system demonstrated the potential to improve diagnostic accuracy, reduce diagnostic latency, and enhance clinician trust by offering transparent and interpretable predictions. Furthermore, the integration of XAI is anticipated to promote greater clinical adoption and reliability of AI-assisted diagnostic systems in gynecology. This work contributes to the advancement of non-invasive diagnostic tools and reinforces the role of interpretable DL in the broader context of precision medicine and women's health.

The selection of optimal text embedding models remains a critical challenge in semantic textual similarity (STS) tasks, particularly when performance varies substantially across datasets. In this study, the comparative effectiveness of multiple state-of-the-art embedding models was systematically evaluated using a benchmarking framework based on established machine learning techniques. A range of embedding architectures was examined across diverse STS datasets, with similarity computations performed using Euclidean distance, cosine similarity, and Manhattan distance metrics. Performance evaluation was conducted through Pearson and Spearman correlation coefficients to ensure robust and interpretable assessments. The results revealed that GIST-Embedding-v0 consistently achieved the highest average correlation scores across all datasets, indicating strong generalizability. Nevertheless, MUG-B-1.6 demonstrated superior performance on datasets 2, 6, and 7, while UAE-Large-V1 outperformed other models on datasets 3 and 5, thereby underscoring the influence of dataset-specific characteristics on embedding model efficacy. These findings highlight the importance of adopting a dataset-aware approach in embedding model selection for STS tasks, rather than relying on a single universal model. Moreover, the observed performance divergence suggests that embedding architectures may encode semantic relationships differently depending on domain-specific linguistic features. By providing a detailed evaluation of model behavior across varied datasets, this study offers a methodological foundation for embedding selection in downstream NLP applications. The implications of this research extend to the development of more reliable, scalable, and context-sensitive STS systems, where model performance can be optimized based on empirical evidence rather than heuristics. These insights are expected to inform future investigations on embedding adaptation, hybrid model integration, and meta-learning strategies for semantic similarity tasks.

The effects of polycarboxylate superplasticizer (PCE) on the rheological properties and workability of cement-based composites were investigated by testing parameters such as static yield stress, dynamic yield stress, plastic viscosity, slump flow, bleeding rate, and penetration depth. The correlation between the dosage of PCE and the rheological parameters of fresh cement-based composites was analyzed. The results indicated that with an increase in the PCE dosage, the static yield stress, dynamic yield stress, and plastic viscosity of fresh cement-based composites decreased, demonstrating that PCE can improve the rheological properties of these composites. As the PCE dosage increased, the slump flow and bleeding rate of fresh cement-based composites also increased, but the rate of change decreased at higher dosages. Additionally, with an increase in PCE dosage, the penetration depth gradually increased, while the penetration depth difference ($\Delta {H}$) decreased. Furthermore, the compressive strength of cement-based composite cubes slightly decreased with an increase in PCE dosage.

Seed Quality is an important area of agriculture and directly influences crop yield and germination percentage. Visual examination forms the foundation of traditional seed testing techniques, which are cumbersome, inflexible, and inefficient for effective assessment. This study proposed an automated approach to seed quality assessment based on physical measurement using machine learning and image processing techniques. Snapshots of the new seeds were captured and underwent feature extraction, segmentation, and image improvement to explore notable morphological attributes, such as size and colour. To tag seeds as "good" or "bad" based on physical characteristics, Support Vector Machines (SVMs) are used as a reference model. Rather, Convolutional Neural Networks (CNNs) have been utilised for deep feature extraction and classification. Experimental findings indicate that CNNs perform better than conventional machine learning models, with a scalable and highly accurate method of seed quality assessment. Future use will utilise quantum machine learning to improve prediction and facilitate sustainable, precision agriculture. The improved framework, optimised with great care for onion seeds, is a major breakthrough in increasing the agricultural productivity of onion cultivation.

Transformer-based language models have demonstrated remarkable success in few-shot text classification; however, their effectiveness is often constrained by challenges such as high intraclass diversity and interclass similarity, which hinder the extraction of discriminative features. To address these limitations, a novel framework, Adaptive Masking Bidirectional Encoder Representations from Transformers with Dynamic Weighted Prototype Module (AMBERT-DWPM), is introduced, incorporating adaptive masking and dynamic weighted prototypical learning to enhance feature representation and classification performance. The standard BERT architecture is refined by integrating an adaptive masking mechanism based on Layered Integrated Gradients (LIG), enabling the model to dynamically emphasize salient text segments and improve feature discrimination. Additionally, a DWPM is designed to assign adaptive weights to support samples, mitigating inaccuracies in prototype construction caused by intraclass variability. Extensive evaluations conducted on six publicly available benchmark datasets demonstrate the superiority of AMBERT-DWPM over existing few-shot classification approaches. Notably, under the 5-shot setting on the DBpedia14 dataset, an accuracy of 0.978±0.004 is achieved, highlighting significant advancements in feature discrimination and generalization capabilities. These findings suggest that AMBERT-DWPM provides an efficient and robust solution for few-shot text classification, particularly in scenarios characterized by limited and complex textual data.

Ensuring the integrity of goods during cold chain transportation remains a critical challenge in logistics, as it is essential to preserve product quality, freshness, and compliance with stringent safety standards. Strategic decision-making in this context requires the prioritization of customer requirements and the optimal allocation of limited operational resources. In response to these demands, an integrated Multi-Criteria Decision-Making (MCDM) model was developed by combining the Best-Worst Method (BWM), Quality Function Deployment (QFD), and Measurement of Alternatives and Ranking according to Compromise Solution (MARCOS) approach. Within this framework, BWM was utilized to determine the relative importance of user requirements, which were then mapped onto specific operational resources through QFD to identify critical resource elements and derive their corresponding weights. These weights, subsequently treated as evaluation criteria in the MARCOS method, were applied to assess the performance of Third-Party Logistics (3PL) providers. The proposed methodology was validated through a case study involving eight user requirements and seven key resources. The findings indicated that precise temperature control and delivery speed were the most critical user requirements, whereas advanced temperature sensors and vehicles with cooling systems were identified as the most significant resources. Based on the MARCOS evaluation, Provider 1 emerged as the most optimal 3PL alternative. This integrated decision-making model offers a systematic and data-driven approach for aligning customer priorities with resource capabilities, thereby enabling logistics providers to enhance service quality, operational efficiency, and strategic competitiveness in temperature-sensitive supply chains. The model also demonstrates practical scalability and adaptability across diverse cold chain scenarios.