Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.15666 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909119787565056 |
|---|---|
| author | Pi, Shu-Ting Hsieh, Cheng-Ping Liu, Qun Zhu, Yuying |
| author_facet | Pi, Shu-Ting Hsieh, Cheng-Ping Liu, Qun Zhu, Yuying |
| contents | Building machine learning models can be a time-consuming process that often takes several months to implement in typical business scenarios. To ensure consistent model performance and account for variations in data distribution, regular retraining is necessary. This paper introduces a solution for improving online customer service in e-commerce by presenting a universal model for predict-ing labels based on customer questions, without requiring training. Our novel approach involves using machine learning techniques to tag customer questions in transcripts and create a repository of questions and corresponding labels. When a customer requests assistance, an information retrieval model searches the repository for similar questions, and statistical analysis is used to predict the corresponding label. By eliminating the need for individual model training and maintenance, our approach reduces both the model development cycle and costs. The repository only requires periodic updating to maintain accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15666 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Universal Model in Online Customer Service Pi, Shu-Ting Hsieh, Cheng-Ping Liu, Qun Zhu, Yuying Machine Learning Artificial Intelligence Information Retrieval Building machine learning models can be a time-consuming process that often takes several months to implement in typical business scenarios. To ensure consistent model performance and account for variations in data distribution, regular retraining is necessary. This paper introduces a solution for improving online customer service in e-commerce by presenting a universal model for predict-ing labels based on customer questions, without requiring training. Our novel approach involves using machine learning techniques to tag customer questions in transcripts and create a repository of questions and corresponding labels. When a customer requests assistance, an information retrieval model searches the repository for similar questions, and statistical analysis is used to predict the corresponding label. By eliminating the need for individual model training and maintenance, our approach reduces both the model development cycle and costs. The repository only requires periodic updating to maintain accuracy. |
| title | Universal Model in Online Customer Service |
| topic | Machine Learning Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2402.15666 |