Applying Machine Learning for Duplicate Detection, Throttling and Prioritization of Equipment Commissioning Audits at Fulfillment Network

TL;DR

This paper applies NLP and machine learning to optimize equipment audit processes in warehouses by identifying duplicates, predicting check outcomes, and prioritizing tasks, leading to significant reductions in checks and cost savings.

Contribution

It introduces a novel NLP-based classifier for trimming checklists and a duplicate detection method to improve efficiency in warehouse audits.

Findings

Reduced 10%-37% of checks, saving costs

Achieved 90% AUC with NLP classifier

Identified 17% redundant checks

Abstract

VQ (Vendor Qualification) and IOQ (Installation and Operation Qualification) audits are implemented in warehouses to ensure all equipment being turned over in the fulfillment network meets the quality standards. Audit checks are likely to be skipped if there are many checks to be performed in a short time. In addition, exploratory data analysis reveals several instances of similar checks being performed on the same assets and thus, duplicating the effort. In this work, Natural Language Processing and Machine Learning are applied to trim a large checklist dataset for a network of warehouses by identifying similarities and duplicates, and predict the non-critical ones with a high passing rate. The study proposes ML classifiers to identify checks which have a high passing probability of IOQ and VQ and assign priorities to checks to be prioritized when the time is not available to perform all checks. This research proposes using NLP-based BlazingText classifier to throttle the checklists with a high passing rate, which can reduce 10%-37% of the checks and achieve significant cost reduction. The applied algorithm over performs Random Forest and Neural Network classifiers and achieves an area under the curve of 90%. Because of imbalanced data, down-sampling and upweighting have shown a positive impact on the models' accuracy using F1 score, which improve from 8% to 75%. In addition, the proposed duplicate detection process identifies 17% possible redundant checks to be trimmed.