COMPARISON OF DATA ANALYTICS APPROACHES USING SIMULATION

Published

December 9, 2018

Author(s)

Sanjay Jain, Anantha Narayanan Narayanan, Yung-Tsun Lee

Abstract

Selecting the right data analytics (DA) approach for an application is rather complex. Obtaining sufficient and right kind of data for evaluating these approaches is a challenge. Simulation models can support this process by generating synthetic data where collecting real data under different conditions would be difficult or impossible. Simulation models can also be used to validate DA models by generating new data under varying conditions. This can help in the evaluation of alternative DA approaches across expected range of operational scenarios. This paper reports on use of simulation to select an approach to support the order promising function in manufacturing. Manufacturers need to quickly estimate cycle times for incoming orders for promising delivery dates. Two DA approaches, Neural Network and Gaussian Process Regression, are evaluated using data generated by a manufacturing simulation model. The applicability of the two approaches is discussed in the context of the selected application.

Proceedings Title

Proceedings of 2018 Winter Simulation Conference

Conference Dates

December 9-12, 2018

Conference Location

Gothernburg, SE

Conference Title

2018 Winter Simulation Conference

Pub Type

Conferences

Download Paper

Local Download

Keywords

Virtual factory, simulation, synthetic data, neural networks, Gaussian process regression

Citation

Jain, S. , Narayanan, A. and Lee, Y. (2018), COMPARISON OF DATA ANALYTICS APPROACHES USING SIMULATION, Proceedings of 2018 Winter Simulation Conference, Gothernburg, SE, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=926264 (Accessed October 1, 2025)