The present research explores how sustainability practices affect customer relationship quality in retail stores. The study explores factors like sustainable product recommendations, smart energy efficiency displays, green certification, and eco-friendly packaging and their effect on customer engagement, customer perception, and loyalty. Using a cross-sectional approach, data was collected from 745 retail customers through structured surveys to understand their views on sustainability initiatives and their behavior patterns. The study employs Structural Equation Modelling-Partial Least Squares (SEM-PLS) using SMART PLS4 for data analysis laying the foundation of the study on Expectation-Confirmation Theory (ECT). The findings reveal that sustainable retail practices enhance customer interactions and highlight the importance of consumer perceptions in evaluating the effectiveness of these initiatives making it significant to improve customer relationship quality, leading to better business performance and increased loyalty. The significance of the study extends to its contribution to the United Nations Sustainable Development Goals (SDGs) by promoting responsible consumption and production (SDG12), partnerships for the Goals SDG 17, and industry, Innovation, and Infrastructure (SDG9). The conceptual framework built on ECT and architected by SEM-PLS aligns with SDG making the study highly relevant and novellas it integrates advanced sustainability practices with customer relationship quality, addressing a critical gap in the existing literature.

Prediction is a means of forecasting a future value by using and analyzing historical or current data. A popular neural network architecture used as a prediction model is the Recurrent Neural Network (RNN) because of its wide application and very high generalization performance. This study aims to improve the RNN prediction model’s accuracy using k-means grouping and PCA dimension reduction methods by comparing the five distance functions. Data were processed using Python software and the results obtained from the PCA calculation yielded three new variables or principal components out of the five examined. This study used an optimized RNN prediction model with k-means clustering by comparing the Euclidean, Manhattan, Canberra, Average, and Chebyshev distance functions as a measure of data grouping similarity to avoid being trapped in the local optimal solution. In addition, PCA dimension reduction was also used in facilitating multivariate data analysis. The k-means grouping showed that the most optimal distance is the average function producing a DBI value of 0.60855 and converging at the 9th iteration. The RNN prediction model results evaluated based on the number of RMSE errors which was 0.83, while that of MAPE was 8.62%. Therefore, it was concluded that the K-means and PCA methods generated a more optimal prediction model for the RNN method.

Purpose of the study: This study aims to develop and evaluate the Electronic Teacher Performance Assessment System (E-PKG) as a digital platform to transform teacher evaluation in vocational education from administrative compliance into strategic professional development to better align vocational graduate competencies with industry requirements. Methodology: This study employs a Research and Development (R&D) design through four stages: needs analysis via stakeholder consultation, prototype development using user-centered design, iterative field testing in vocational schools and industry partnerships, and refinement from empirical feedback. Data were collected from 34 respondents using questionnaires, structured observations, and interviews, and analyzed with descriptive statistics and thematic analysis. Main Findings: The E-PKG system reduced assessment completion time by 67%, eliminated data entry errors, and improved inter-rater reliability from 0.62 to 0.89. Real-time analytics supported evidence-based professional development planning. User satisfaction ranged from 3.88 to 4.26 (5-point scale), with highest scores for system stability and navigation ease, though challenges remained in interface clarity for non-technical users and indicator comprehension. Novelty/Originality of this study: This study introduces a comprehensive digital teacher assessment system specifically tailored to vocational education, directly linking evaluation results to industry competency frameworks. It advances knowledge by demonstrating how technology-mediated assessment can strategically connect quality improvement and workforce development in economically disadvantaged settings, while emphasizing the importance of pedagogical alignment, stakeholder inclusivity, and contextual adaptation.