CHAPTER 3: AUTOMATING A MANUAL TELEPHONE PROCESS
Mary Batcher, Kevin Cecco, Dennis K. J. Lin · Society for Industrial and Applied Mathematics eBooks · 1998
This article was written and prepared by U.S. Government employees on official time. It is in the public domain and not subject to U.S. copyright. The content of this article is the opinion of the writer and does not necessarily represent the position of the Internal Revenue Service. The mention of specific product or service in this article does not imply endorsement by any agency of the federal government to the exclusion of others which may be suitable. This case study illustrates the use of statistics to evaluate a new technology that will be implemented nationally in over 30 locations if it proves successful in a pilot study. Specifically, the case study is of an interactive telephone application that will let certain types of calls to the IRS be handled without the intervention of a staff person. When introducing new technology, it is important to consider the human interaction with that technology. The technology may function perfectly but the ability or willingness of people to use it may not be there. It is thus very important to pilot test new systems. The interactive telephone system was pilot tested and evaluated in terms of cost, customer satisfaction, and ease of use. This case study focuses on the assessment of cost, in terms of time to complete a transaction, and ease of use, in terms of the percent of users who successfully completed their transaction without requiring the assistance of IRS staff.1 The case study illustrates the use of hypothesis testing in decision making and the use of basic time series statistics and plots to examine periodic fluctuation over time. 1The customer satisfaction measure was an automated survey of a sample of callers. The caller was asked, at the end of the transaction, to participate in a short survey. The general satisfaction level from the survey was 93.6 percent and the survey response rate was 64.4 percent.