“ServPort”: Process Reengineering in Optimization of The Process in Vehicle Service Station

Abstract

The usage of vehicles is increasing across the world. Thus, vehicle maintenance has become a key factor when considering vehicles' continuous performance, which leads to the increasing need for vehicle service providers. However, there are some challenges faced by vehicle service providers when providing a high-quality service within a reasonable price range for their customers. A process optimization solution for vehicle service centers named as ‘ServPort’ is proposed through this study to provide a solution to the challenges experienced by vehicle service providers and to support them in providing a quality service at a fair price to their clients. According to the findings, a process optimization solution was not yet introduced for the vehicle service sector in Sri Lanka. Therefore, this paper addresses the selected machine learning models and the approaches taken to optimize the process in a vehicle service station by predicting key fields in a vehicle service station. Under this, customer retention and its impact on the vehicle service center's profitability were predicted using linear regression algorithm, which achieved 99.29% accuracy rate. In comparison, other selected machine learning models achieved lower accuracy rates. When predicting employee efficiency, decision tree model achieved 90% accuracy rate, whereas linear regression algorithm achieved only 50% accuracy rate. To predict the next vehicle service date, logistic regression algorithm, which performed with an accuracy rate of 98% was used.