Authors:

Rishita Korapati

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

This research demonstrates how integrating predictive analytics with prescriptive analytics (i.e., optimization) can identify key operational drivers among garment industry employees to enhance managerial decision- making. We formulate and solve an optimization model with parameters estimated from a linear regression predictive model of employee working behavior and labor outcomes in the garment manufacturing industry. This solution empowers managers to make informed decisions on optimizing employee performance to achieve desired production outputs. Motivated by studies from Rahim et al. (2017) and Imran et al. (2019), which highlight significant economic losses due to inefficiencies in the garment industry, our approach underscores the necessity of combining predictive modeling with optimization. This integration aims to identify the most effective actions to enhance productivity. The garment industry, employing millions and accounting for 84% of export earnings in Bangladesh alone, faces annual losses amounting to billions of dollars due to low productivity and escalating costs. Our findings suggest that substantial savings can be achieved with this innovative approach of integrating predictive and prescriptive analytics, compared to the use of predictive analytics alone, as previously documented in academic literature. Keywords: Predictive Analytics; Prescriptive Analytics; Optimization Model; Garment Industry; Employee Productivity

Source:

Purdue University / 2024

Topics:

No topics listed

Co-authors:

Rishita Korapati