Scholarlink

<p>This study examines the role of e-commerce solutions in Human Resource Management (HRM) for enhancing employee engagement and operational efficiency through digital platforms. Ethics and society in the age of digital transformation are critically examined through a social intelligence–driven deep learning framework for enhancing HRM decision-making and employee engagement. A deep learning approach based on a Deep Recurrent Neural Network–Autoencoder hybrid model is proposed to analyze employee behavior patterns, engagement levels, and retention trends. The model is evaluated using a dataset comprising 4,200 employee records and 38,000 interaction logs collected from a digital HRM platform. Stratified sampling is applied to ensure balanced representation. The proposed framework integrates data preprocessing, temporal feature extraction, and Ant Colony Optimization to improve predictive performance. Key HRM strategies, including reward systems, training programs, and flexible working arrangements, are also analyzed for their impact on engagement. Experimental results show that the proposed model achieves 98% prediction accuracy, along with high precision, recall, and F1-score. These results indicate robust classification performance. The findings support effective data-driven HRM decision-making and improved organizational productivity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating e-commerce solutions into HRM & people management: enhancing employee engagement and operational efficiency through digital platforms

  • 期刊论文

  • 发表日期：

    2026年5月27日

查看全文
  • Mohan Reddy Sareddy,
  • Md. Johirul Islam,
  • R. Hemnath,
  • M. Suresh Kumar,
  • P. Dhivya

摘要

This study examines the role of e-commerce solutions in Human Resource Management (HRM) for enhancing employee engagement and operational efficiency through digital platforms. Ethics and society in the age of digital transformation are critically examined through a social intelligence–driven deep learning framework for enhancing HRM decision-making and employee engagement. A deep learning approach based on a Deep Recurrent Neural Network–Autoencoder hybrid model is proposed to analyze employee behavior patterns, engagement levels, and retention trends. The model is evaluated using a dataset comprising 4,200 employee records and 38,000 interaction logs collected from a digital HRM platform. Stratified sampling is applied to ensure balanced representation. The proposed framework integrates data preprocessing, temporal feature extraction, and Ant Colony Optimization to improve predictive performance. Key HRM strategies, including reward systems, training programs, and flexible working arrangements, are also analyzed for their impact on engagement. Experimental results show that the proposed model achieves 98% prediction accuracy, along with high precision, recall, and F1-score. These results indicate robust classification performance. The findings support effective data-driven HRM decision-making and improved organizational productivity.