Convolutional Neural Network and Capsule Network Fusion for Effective Attrition Classification

Abstract

In today’s rapidly evolving corporate landscape, employee attrition has emerged as a critical challenge for organizations aiming to sustain a skilled and motivated workforce. This paper introduces a novel approach to address the complex task of employee attrition classification by leveraging the combined power of Convolutional Neural Networks (CNNs) and Capsule Networks. The proposed fusion of CNNs and Capsule Networks capitalizes on their distinct strengths in feature extraction and capturing hierarchical relationships within data, respectively. By integrating these cutting-edge deep learning architectures, we present a holistic framework that enhances the accuracy and interpretability of attrition prediction models. Our experiments on real-world employee attrition datasets demonstrate the superior performance of the CNN and Capsule Network fusion approach compared to traditional methods. The fusion model achieves not only higher classification accuracy but also provides valuable insights into the underlying factors contributing to attrition.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 33 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.