Towards Active Learning Based Smart Assistant for Manufacturing

TL;DR

This paper presents a methodology for developing active learning-based smart assistants in manufacturing, demonstrated on demand forecasting, enabling knowledge acquisition and data labeling in data-scarce scenarios.

Contribution

It introduces a general approach for building active learning smart assistants tailored for manufacturing applications, with a specific demonstration on demand forecasting.

Findings

System effectively guides users through decision steps

Enables data collection and labeling in manufacturing contexts

Flexible methodology applicable to various manufacturing use cases

Abstract

A general approach for building a smart assistant that guides a user from a forecast generated by a machine learning model through a sequence of decision-making steps is presented. We develop a methodology to build such a system. The system is demonstrated on a demand forecasting use case in manufacturing. The methodology can be extended to several use cases in manufacturing. The system provides means for knowledge acquisition, gathering data from users. We envision active learning can be used to get data labels where labeled data is scarce.