Social media-based e-commerce consumer behavior prediction model in marketing strategy DOI Creative Commons
Min Zhou

Applied Mathematics and Nonlinear Sciences, Journal Year: 2024, Volume and Issue: 9(1)

Published: Jan. 1, 2024

Abstract The rapid development of information technology has entered the era network big data, online shopping for young people become a fashion, and social media platforms have gathered large amount consumer purchase data. In this paper, current facing problem user consumption behavior prediction accuracy, data mining is referenced to analyze predict behavior. entropy weight method used segment e-commerce consumers based on RFM, basis, simple Bayesian model construct an algorithm suitable analyzing predicting using Consumers are categorized into important value customers (7.21%), (18.76%), retention (7.32%), general (9.86%), (37.14%), (19.71%). accuracy rate (ACC) media-based 84.92%, which allows more accurate predictions. study provides scientific foundation or enterprise decision-making, incubates emerging industries by addresses major needs, becomes new engine promoting progress.

Language: Английский

Transforming document management for environmental sustainability: the mediating effect of pro-environmental culture and service satisfaction in higher education institutions DOI Creative Commons
Jessie Bravo, Carlos Valdivia, Roger Alarcón

et al.

Frontiers in Sustainability, Journal Year: 2025, Volume and Issue: 5

Published: Jan. 8, 2025

This research investigates the factors influencing environmental sustainability in a Peruvian higher education institution (HEI), using Structural Equation Modeling (SEM) with SmartPLS. The methodology included data collection through questionnaires administered to students, alumni, and professors, followed by SEM analysis assess relationships between technological support (TS), document management (DM), open government (OG), pro-environmental organizational culture (POC), service satisfaction (SS), (ES). findings emphasize that infrastructure significantly enhances management, which turn boosts promotes culture. emerges as most powerful mediator, impacting sustainability. Although also contributes positively, its effect is less pronounced. Furthermore, transparency access information improve albeit lesser impact. Sociodemographic variables such gender academic program within influence relationship examined variables, suggesting these characteristics can affect perception effectiveness of practices. study provides robust foundation for designing effective strategies promote institutions would contribute fulfillment SDGs.

Language: Английский

Citations

0
A New Predictive Method for Classification Tasks in Machine Learning: Multi-Class Multi-Label Logistic Model Tree (MMLMT) DOI Creative Commons
Bita Ghasemkhani, Kadriye Filiz Balbal, Derya Birant

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(18), P. 2825 - 2825

Published: Sept. 12, 2024

This paper introduces a novel classification method for multi-class multi-label datasets, named logistic model tree (MMLMT). Our approach supports learning to predict multiple class labels simultaneously, thereby enhancing the model’s capacity capture complex relationships within data. The primary goal is improve accuracy of tasks involving classes and labels. MMLMT integrates regression (LR) decision (DT) algorithms, yielding interpretable models with high predictive performance. By combining strengths LR DT, our offers flexible powerful framework handling Extensive experiments demonstrated effectiveness across range well-known datasets an average 85.90%. Furthermore, achieved 9.87% improvement compared results state-of-the-art studies in literature. These highlight MMLMT’s potential as valuable learning.

Language: Английский

Citations

3
Online Machine Learning for Intrusion Detection in Electric Vehicle Charging Systems DOI Creative Commons

Fazliddin Makhmudov,

Dusmurod Kilichev, Ulugbek Giyosov

et al.

Mathematics, Journal Year: 2025, Volume and Issue: 13(5), P. 712 - 712

Published: Feb. 22, 2025

Electric vehicle (EV) charging systems are now integral to smart grids, increasing the need for robust and scalable cyberattack detection. This study presents an online intrusion detection system that leverages Adaptive Random Forest classifier with Windowing drift identify real-time evolving threats in EV infrastructures. The is evaluated using real-world network traffic from CICEVSE2024 dataset, ensuring practical applicability. For binary detection, model achieves 0.9913 accuracy, 0.9999 precision, 0.9914 recall, F1-score of 0.9956, demonstrating highly accurate threat It effectively manages concept drift, maintaining average accuracy 0.99 during events. In multiclass attains 0.9840 0.9831 event 0.96. computationally efficient, processing each instance just 0.0037 s, making it well-suited deployment. These results confirm machine learning methods can secure source code publicly available on GitHub, reproducibility fostering further research. provides a efficient cybersecurity solution protecting networks threats.

Language: Английский

Citations

0
Active Learning in the Extraction of Organic Compounds: A Study of Undergraduate Chemistry Students DOI Creative Commons
Jana Jakubčinová, Melánia Feszterová, Veronika Silliková

et al.

Education Sciences, Journal Year: 2024, Volume and Issue: 14(10), P. 1051 - 1051

Published: Sept. 26, 2024

This study investigates the impact of active learning on acquisition competencies and outcomes in context organic chemistry education. Specifically, this focuses implementation extraction an unknown mixture compounds using acidic basic solutions. research is based “ex post facto” involving 40 first-year undergraduate students who are pre-service teachers at a Slovak public university. aims to analyse students’ performance, identify common problems encountered, assess advantages disadvantages approach. The data collection instruments included structured report best practices university education questionnaire evaluate experiences assessment systems used. compares effectiveness online face-to-face teaching methods for practical coursework. key findings from comparison these differences achieved, e.g., answers tasks 2–6 questionnaire. Group B respondents had higher number correct responses lower variability compared A respondents. difference may indicate improvement comprehension instruction over period. Differences scores between groups be due random composition groups, which we found through statistical analysis. Full-time felt more engaged satisfied. More than half said that they preferred interactions help them better understand material. While provided greater flexibility accessibility, lacked hands-on interaction, negatively impacted their skills. results learning, particularly laboratory exercises, positive professional outcomes. also highlights

Language: Английский

Citations

0
Social media-based e-commerce consumer behavior prediction model in marketing strategy DOI Creative Commons
Min Zhou

Applied Mathematics and Nonlinear Sciences, Journal Year: 2024, Volume and Issue: 9(1)

Published: Jan. 1, 2024

Abstract The rapid development of information technology has entered the era network big data, online shopping for young people become a fashion, and social media platforms have gathered large amount consumer purchase data. In this paper, current facing problem user consumption behavior prediction accuracy, data mining is referenced to analyze predict behavior. entropy weight method used segment e-commerce consumers based on RFM, basis, simple Bayesian model construct an algorithm suitable analyzing predicting using Consumers are categorized into important value customers (7.21%), (18.76%), retention (7.32%), general (9.86%), (37.14%), (19.71%). accuracy rate (ACC) media-based 84.92%, which allows more accurate predictions. study provides scientific foundation or enterprise decision-making, incubates emerging industries by addresses major needs, becomes new engine promoting progress.

Language: Английский

Citations

0