@inproceedings { , title = {Predicting service levels using neural networks.}, abstract = {In this paper we present a method to predict service levels in utility companies, giving them advanced visibility of expected service outcomes and helping them to ensure adherence to service level agreements made to their clients. Service level adherence is one of the key targets during the service chain planning process in service industries, such as telecoms or utility companies. These specify a time limit for successful completion of a certain percentage of tasks on that service level agreement. With the increasing use of automation within the planning process, the requirement for a method to evaluate the current plan decisions effects on service level outcomes has surfaced. We build neural network models to predict using the current state of the capacity plan, investigating the accuracy when predicting both daily and weekly service level outcomes. It is shown that the models produce a high accuracy, particularly in the weekly view. This provides a solution that can be used to both improve the current planning process and also as an evaluator in an automated planning process.}, conference = {37th SGAI International innovative techniques and applications of artifical intelligence conference 2017 (AI 2017)}, doi = {10.1007/978-3-319-71078-5\_35}, isbn = {9783319710778}, note = {COMPLETED -- AAM rec'd from contact 11/2/2019 LM -- Requested AAM from contacts 7/2/2019 LM -- Info via WoS alert 20/12/2018 ADDITIONAL INFORMATION: Ainslie, Russell ; McCall, John -- Panel B}, pages = {411-416}, publicationstatus = {Published}, publisher = {Springer}, url = {http://hdl.handle.net/10059/3295}, keyword = {Neural network, NN, Prediction, Service levels, Early stopping strategy, Planning}, year = {2017}, author = {Ainslie, Russell and McCall, John and Shakya, Sid and Owusu, Gilbert} editor = {Bramer, Max and Petridis, Miltos} }