Summary of Teacher-student Learning on Complexity in Intelligent Routing, by Shu-ting Pi et al.
Teacher-Student Learning on Complexity in Intelligent Routing
by Shu-Ting Pi, Michael Yang, Yuying Zhu, Qun Liu
First submitted to arxiv on: 24 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This machine learning paper presents a novel framework for routing customers to appropriate agents in e-commerce settings, with the goal of minimizing the time spent on each contact. The framework consists of two parts: a teacher model that scores the complexity of customer contacts based on post-contact transcripts, and a student model that predicts complexity based on pre-contact data only. The approach is designed to reduce transfers between agents, improving overall customer experience. Experiments demonstrate the effectiveness of this framework in achieving this goal. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper develops a machine learning system to help e-commerce websites quickly direct customers to the right person who can help them. Right now, each customer interaction takes around 10-15 minutes, which is a lot! To make things better, they created two parts: one that looks at what happened after someone contacted the website (like how long it took and what was said), and another that predicts what’s going to happen before someone contacts the website. This system can really help make customers happy by getting them to the right person faster. |
Keywords
* Artificial intelligence * Machine learning * Student model * Teacher model
