Probabilistic Models for Manufacturing Lead Times

TL;DR

This paper compares various probabilistic models like Gaussian processes and neural networks for predicting manufacturing lead times, demonstrating their superior performance over traditional domain-based estimates with practical business implications.

Contribution

It introduces probabilistic modeling approaches to manufacturing lead times and provides a comprehensive comparison of their effectiveness on real-world data.

Findings

All models outperform the traditional benchmark.

Models show good calibration with empirical data.

Probabilistic models offer valuable insights for manufacturing processes.

Abstract

In this study, we utilize Gaussian processes, probabilistic neural network, natural gradient boosting, and quantile regression augmented gradient boosting to model lead times of laser manufacturing processes. We introduce probabilistic modelling in the domain and compare the models in terms of different abilities. While providing a comparison between the models in real-life data, our work has many use cases and substantial business value. Our results indicate that all of the models beat the company estimation benchmark that uses domain experience and have good calibration with the empirical frequencies.