Call Center Call Count Prediction Model by Machine Learning
Authors:
- Yunhwan KeonYKYunhwan Keon
- Hyuna KimHKHyuna Kim
- Jin Young ChoiJCJin Young Choi
- Dongho KimDKDongho Kim
- Su Young KimSKSu Young Kim
- Seonho KimSKSeonho Kim
- 31 July 2018
- journal article
- Published by Korean Institute of Information Technology in JOURNAL OF ADVANCED INFORMATION TECHNOLOGY AND CONVERGENCE
- Vol. 8 (1) , 31-42
Abstract
This paper is to introduce efficient human resource management in call center industry by coming up with a model that predicts how much the staffing is most appropriate at such a call center for a given hour period. The project aims to understand the characteristics of call center data through exploratory data analysis, and to test the effectiveness of call center staffing by formulating the rule based on a machine learning model. We initially conducted exploratory data analysis to find insights and implemented a machine learning model to predict the value of the target variable which consequently translated into the number of human receptionists preferred. From our intensive experiments, we found that Random Forest gave the best performance for call center data analysis.Keywords
Funding Information
- Ministry of Science and ICT (R7116-16-1014)
This publication has 2 references indexed in Scilit:
- Data Mining with Rattle and R2011
- Random forest classifier for remote sensing classificationInternational Journal of Remote Sensing, 2005