Artificial Intelligence (AI) Driven Proactive Customer Service Excellence Platform in e-commerce Industry
DOI:
https://doi.org/10.15680/IJCTECE.2025.0801011Keywords:
E-commerce, Customer Service, AI, MLAbstract
In this paper, quantitative research was conducted using AI models to classify and rank customer service messages in e-commerce. Accuracy, efficiency, and severity ranking Five model types, namely RNN, LSTM, CNN-BERT hybrid, DistilBERT, and BERT were tested. The findings demonstrate that transformer models are better than traditional deep learning models in all key metrics. DistilBERT is an algorithm that offers the most appropriate tradeoff between speed, accuracy and memory consumption, thus suitable in real-time application. Transformer models were also more stable in prediction of severity. The results justify the use of current NLP systems in the context of faster, more precise, and responsive automation of customer service
References
[1] Fu, M., Guan, J., Zheng, X., Zhou, J., Lu, J., Zhang, T., Zhuo, S., Zhan, L., & Yang, J. (2020). ICS- Assist: Intelligent Customer Inquiry Resolution recommendation in online customer service for large E-Commerce businesses. In Lecture notes in computer science (pp. 370–385). https://doi.org/10.1007/978-3-030-65310-1_26
[2] Fu, M., Guan, J., Zheng, X., Zhou, J., Lu, J., Zhang, T., Zhuo, S., Zhan, L., & Yang, J. (2020b). ICS- Assist: Intelligent Customer Inquiry Resolution recommendation in online customer service for large E-Commerce businesses. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2008.13534
[3] Teng, L., Liu, Y., Liu, J., & Song, L. (2024). End-Cloud Collaboration Framework for advanced AI customer service in e-commerce. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.07122
[4] Taneja, K., Vashishtha, J., & Ratnoo, S. (2024). Transformer based Unsupervised learning approach for imbalanced text sentiment analysis of E-Commerce reviews. Procedia Computer Science, 235, 2318–2331. https://doi.org/10.1016/j.procs.2024.04.220
[5] Zhang, Y., Lau, R. Y. K., Xu, J. D., Rao, Y., & Li, Y. (2024). Business chatbots with deep learning technologies: state-of-the-art, taxonomies, and future research directions. Artificial Intelligence Review, 57(5). https://doi.org/10.1007/s10462-024-10744-z
[6] Li, F., Chen, H., Xu, G., Qiu, T., Ji, F., Zhang, J., & Chen, H. (2020). AliMeKG. AliMeKG, 2581–
2588. https://doi.org/10.1145/3340531.3412685
[7] Mangalam, R. (2024). Customer Sentiment Analysis for E-Commerce: A Hybrid approach using CNNs & BERT. International Journal for Research in Applied Science and Engineering Technology, 12(11), 592–596. https://doi.org/10.22214/ijraset.2024.65126
[8] Alshamari, M. A. (2023). Evaluating user satisfaction using Deep-Learning-Based sentiment analysis for social media data in Saudi Arabia’s telecommunication sector. Computers, 12(9), 170. https://doi.org/10.3390/computers12090170
[9] Grigoraș, A., & Leon, F. (2023). Transformer-Based model for predicting customers’ next
purchase day in e-Commerce. Computation, 11(11), 210. https://doi.org/10.3390/computation11110210
[10] Bird, J. J., & Lotfi, A. (2024). Customer service chatbot enhancement with attention-based transfer learning. Knowledge-Based Systems, 301, 112293.
