A data mining experimentation framework to improve six sigma projects

Abstract

The complexity and dynamics have been increased in the last years in the field of telecom operations. Due to this, many challenges were introduced in this area especially in handling the trouble tickets of the customer proactively before it occurs. Six Sigma is selected by one of the biggest telecom operators in the Middle East to achieve a breakthrough improvement in the quality of operations to achieve better customer experience and better operations efficiency through reducing the repeat rate of trouble tickets coming from the customer. In this paper, we propose an experimentation framework that integrates the Cross Industry Standard Process for Data Mining (CRISP-DM), as one of most widely adopted framework for developing data mining solutions with the phases of Six Sigma Define-Measure-Analyze-Improve-Control (DMAIC) project as one of the most used methodologies. The objective is to improve the six sigma projects by introducing data mining techniques into their phases to achieve a breakthrough quality improvement through bringing more insights from the massive data of telecom operations that represents the voice of the customer (VOC) and the voice of machine (VOM). A case study is used to show an implementation approach for the framework proposed in the paper by one of the biggest telecom operators in the Middle East.