Institutional Repository of Vilnius University
Elektroninio klientų aptarnavimo srauto modeliavimas /
Abstract
dc:descriptionThis work models electronic customer flow and analyzes the themes of these inquiries. Data from January 2026 was used for the study. In this study, a tagging system analysis was performed by day of the week using the Chisquare test and standardized residual analysis. Poisson and Negative Binomial Regression models were used to model customer traffic, and AIC, BIC, MAPE, and likelihood ratio tests were used to compare the models. In addition, autocorrelation and overdispersion analyses were conducted, and ARIMA models were used. The study found that certain tags vary by the day of the week and tend to appear more or less frequently depending on the day. It was also found that the amount of customer queries exhibits daily tendencies and noticeable recurring trends. According to the analysis, the Negative Binomial Regression model is a better fit for the total customer traffic and email flow, and the simpler Poisson model is suitable for the live chat flow data. The findings of this study can help plan customer service staff schedules, as knowing the customer flow forecasts and trends can help better allocate resources.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Šeputytė, Rugilė,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308333347&prefLang=en_US