Summary of Predicting Customer Satisfaction by Replicating the Survey Response Distribution, By Etienne Manderscheid and Matthias Lee
Predicting Customer Satisfaction by Replicating the Survey Response Distribution
by Etienne Manderscheid, Matthias Lee
First submitted to arxiv on: 19 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
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 The paper addresses the issue of biased customer satisfaction (CSAT) measurements in call centers, where only a fraction of customers complete the survey after their calls. This leads to inaccurate average CSAT values and missed opportunities for coaching and follow-up. To mitigate this bias, the authors propose a model that predicts CSAT on unsurveyed calls, ensuring accurate replication of the distribution of survey responses. The method can be applied to various multiclass classification problems, improving class balance and minimizing changes upon model updates. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Call centers want to know if customers are happy with their service. But, only some customers fill out a survey after a call, which makes it hard to get an accurate picture of how satisfied most customers really are. This paper shows how to predict customer satisfaction on calls where the customer didn’t take the survey. The goal is to make sure the predicted scores match the actual responses from surveyed customers as closely as possible. This can help call centers improve their service and make better decisions. |
Keywords
* Artificial intelligence * Classification
