International Journal on Advanced Science, Engineering and Information Technology, Vol. 9 (2019) No. 1, pages: 1-7, DOI:10.18517/ijaseit.9.1.7545

Design and implementation of a Marking Strategy to Increase the Contactability in the Call Centers, Based on Machine Learning

Leonel Hernandez, Henner Guzman, Jose Ospino, Jean Freyle, Andri Pranolo


Jamar is a company that belongs to the furniture sector, which manufactures and sells furniture and accessories for the home. Customer calls are one of the most trusted channels used in contact centers. Currently, the contactability indicator has a goal of 40% and is at 31%. The enemies of the efficiency of this channel are the terrible dimensioning, customers who evade answering these calls by identifying the numbers, non-market numbers in the databases, failures in the technological resources. Therefore, a proposal was made to design and implement a marking strategy in the call center, supported by a statistical model for dimensioning. Likewise, emerging technology such as Machine Learning is performed to help the marking strategy in outbound campaigns, reconfiguration of the dialplan to make it more efficient, and a redundant architecture design in the operators. Basic concepts of Teletraffic are explained, showing its primary functions, relevant for the management of the company's telephone system. In the same way, fundamentals of the Asterisk IP PBX are exposed, one of the most used in our environment due to its versatility and low implementation cost. The methodology of descriptive and applied research is used for the development of the project. The results and discussion show the dialing strategy and some call statistics from previous years, necessary to establish a correct dimensioning of the solution. The proposed solution allows having redundancy management for SIP and trunk operators, to have backup and reliability in case of failure.


network; calls; dialplan; machine learning; asterisk.

Viewed: 1071 times (since abstract online)

cite this paper     download