Title | ||
---|---|---|
Evaluating Customer Satisfaction - Using Behavioral Analytics of Data-Intensive Software Systems. |
Abstract | ||
---|---|---|
This paper tackles the problem of constantly monitoring customer satisfaction. The goal is to reason about customer satisfaction automatically using data provided from a large software system customers are interacting with. The system under study is a mobile application which allows users to track their pets. The application and underlying system collect a large amount of data, including user interactions with the app and technical data related to the quality of the tracking process. The question is if those data can be efficiently exploited in order to determine customer satisfaction. Based on existing approaches to model customer satisfaction, we investigate relevant data sources with supposedly influence the satisfaction level of customers. We compare two different approaches, a hypothesis driven approach and a machine learning approach. The approaches are evaluated on an extracted dataset from a real world case study.
|
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3282373.3282384 | iiWAS |
Keywords | Field | DocType |
customer satisfaction, data mining, prediction | Data science,Customer satisfaction,Computer science,Software system,Behavioral analytics,Database | Conference |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gabriele Anderst-Kotsis | 1 | 9 | 3.54 |
Jürgen Ratzenböck | 2 | 0 | 0.34 |