Creating a reliable predictive model is a vital part of business intelligence applications. However, without a proper benchmark, it is very difficult to assess how good a predictive model really is. Furthermore, existing literature does not provide much guidance on how to create such benchmarks. In this paper we address this gap by presenting a method for creating such a such a benchmark. We demonstrate the method by developing predictive models for truck turnaround time, created using both regression and classification methods. We use data generated in a simulated terminal for developing these models. We establish the parameters and parameter distributions of the simulation through a structured review of the relevant literature. We show that congestion, start time and route through the terminal together are good predictors of turnaround time, leading to adequate predictive performance. These results can then be used as a benchmark for predictive models on truck turnaround time, thereby demonstrating our general method for creating such benchmarks.
|Number of pages||10|
|Publication status||Published - 29 Mar 2016|
|Event||Big Data Interoperability for Enterprises (BDI4E) Workshop 2016 - Guimarães, Portugal|
Duration: 29 Mar 2016 → 30 Mar 2016
|Conference||Big Data Interoperability for Enterprises (BDI4E) Workshop 2016|
|Period||29/03/16 → 30/03/16|
van der Spoel, S., Amrit, C., & van Hillegersberg, J. (2016). A benchmark for predicting turnaround time for trucks at a container terminal. Paper presented at Big Data Interoperability for Enterprises (BDI4E) Workshop 2016, Guimarães, Portugal.