Authors - My-Phuong Ngo, Hoang-Thanh Ngo, Loan T.T. Nguyen Abstract - Automated classification of enterprise support tickets is a foundational natural language processing (NLP) task for intelligent service management systems. While trans-former-based models have achieved strong performance on benchmark datasets, their behavior under real-world enterprise constraints—such as class imbalance, do-main shift, calibration reliability, and retraining cost—remains insufficiently under-stood. This paper presents a comprehensive and reproducible NLP framework for enterprise ticket classification, systematically evaluating classical machine learning baselines, full fine-tuning of transformer encoders, and parameter-efficient fine-tuning using Low-Rank Adaptation (LoRA). Extensive experiments are conducted on a large enterprise-style ticket corpus using time-based splits, out-of-domain testing, imbalance stress, calibration analysis, inference latency, and ablation studies. Results show that transformer-based models substantially outperform classical baselines, while LoRA achieves comparable performance to full fine-tuning with significantly reduced training overhead. The proposed evaluation protocol and findings provide practical guidance for deploying robust and efficient NLP systems in enterprise environments.
Open Zoom