Leveraging Predictive Analytics to Assess Operations Metrics
Name
Artman_Kong_Capstone_LeveragingPredictiveAnalyticsToAssessOperationsMetrics.pdf
Description
Supply Chain Management capstone research project
Size
2.01 MB
Format
Adobe PDF
Checksum (MD5)
8ac458e79e6603ebb26990fbcf996bca
Author(s)
Kong, Chiwei
Artman, Nicholas Charles Samuel
Date Issued
June 16, 2021
Abstract
Many firms rely on key performance indicators (KPIs) to manage their business. Though countless metrics exist, it can be difficult for companies to identify which metrics are driving their performance. This is problematic within industry, as insignificant KPIs can lead to misguided management insights. This research analyzes how companies and organizations can assess operational metrics utilizing predictive analytics. Additionally, it shows how firms can leverage their metrics to prepare for future objectives and identify key predictive indicators. This analysis comprises an assortment of predictive modeling techniques to evaluate manufacturing and inventory metrics for a firm identified as Company XYZ. These modeling approaches include multiple linear regression, random forest, LASSO regression, and backward elimination. Our analysis found four of the ten performance metrics reviewed to be significant in predicting a production efficiency metric. Using these four metrics, we applied a multiple linear regression model to assign coefficients that could be leveraged for sensitivity analysis. Our results ultimately identified key predictive indicators and created sensitivity analysis to help management teams prepare for future endeavors. This research demonstrates that predictive analytics can be used as a fast and cost- effective approach for companies to review their performance metrics.
Subjects
Digital Transformation
Supply Chain Strategy
Terms of Use
CC0 1.0 Universal
Persistent DSpace Link
