Publisher
University of Tennessee at Chattanooga
Place of Publication
Chattanooga (Tenn.)
Abstract
Introduction Organizations are interested in finding ways to cut down on lost productivity while simultaneously minimizing injuries to employees. The private sector of the workforce accounts for over 2.8 million illnesses and injuries in the U.S. (BLS, 2018, 2019, 2020). The Data Analytics Readiness Tool (DART), was created to ascertain an organization’s advanced analytical capabilities on whether their data can be used to perform descriptive, diagnostic, predictive, and prescriptive analytics. For organizations to take further proactive steps for employee safety and avoid injuries before they occur, the DART's feedback is essential for improving their safety measurement systems to use additional predictive analytic approaches. Methodology The DART is a self-assessment tool used to measure data maturity and analytic capabilities (Leslie et al., 2024). DART was applied to two years of data (2022-2023) provided by a large oil refinery in the American Southwest. The data examined consisted of behavioral observations, safety audits, and injury data ranging from close-calls and first-aids, to more severe incidents including injuries requiring long-term treatment. HR-related examinations consisted of overtime and scheduled/unscheduled hours. These results were aggregated providing “readiness” scores determining which variables can be in predictive analyses (Leslie et al., 2024). Scores above 75% were optimal, while scores below 50% were suboptimal. Results The organizational and variable readiness scores mostly exceeded optimal levels (Leslie et al. 2024). The readiness scores inferred from those scores were personnel, centralized database, employee participation, and management use with all but centralized databases being optimal. The variable readiness scores of safety-related and HR-related variables all exceeded the optimal level (Leslie et al., 2024). Thus, the safety-related and HR data received, passed the DART criteria and can be used for further predictive analyses. When compared to previous applications of the DART, this organization exceeded the overall optimal levels of two other companies. Conclusion Using the DART has allowed for the ability to assess and implement safe work practices (Ezerins et al., 2022). Even though some of the variables did not meet the 75% threshold for predictive analytics, the overall findings can still provide insight into whether an organization is ready for predictive analytics to provide beneficial results. These results show the benefits that a self-assessment tool can provide not only within a safety context but also for broader organizational practices. Organizations can leverage predictive analytics to create dynamic employee value propositions by anticipating the needs and expectations of their employees.
Date
11-9-2024
Subject
Industrial and organizational psychology
Document Type
posters
Language
English
Rights
http://rightsstatements.org/vocab/InC/1.0/
License
http://creativecommons.org/licenses/by/4.0/
Included in
Aiming for Success with DART: Determining Data Analytics Readiness for Targeted Results
Introduction Organizations are interested in finding ways to cut down on lost productivity while simultaneously minimizing injuries to employees. The private sector of the workforce accounts for over 2.8 million illnesses and injuries in the U.S. (BLS, 2018, 2019, 2020). The Data Analytics Readiness Tool (DART), was created to ascertain an organization’s advanced analytical capabilities on whether their data can be used to perform descriptive, diagnostic, predictive, and prescriptive analytics. For organizations to take further proactive steps for employee safety and avoid injuries before they occur, the DART's feedback is essential for improving their safety measurement systems to use additional predictive analytic approaches. Methodology The DART is a self-assessment tool used to measure data maturity and analytic capabilities (Leslie et al., 2024). DART was applied to two years of data (2022-2023) provided by a large oil refinery in the American Southwest. The data examined consisted of behavioral observations, safety audits, and injury data ranging from close-calls and first-aids, to more severe incidents including injuries requiring long-term treatment. HR-related examinations consisted of overtime and scheduled/unscheduled hours. These results were aggregated providing “readiness” scores determining which variables can be in predictive analyses (Leslie et al., 2024). Scores above 75% were optimal, while scores below 50% were suboptimal. Results The organizational and variable readiness scores mostly exceeded optimal levels (Leslie et al. 2024). The readiness scores inferred from those scores were personnel, centralized database, employee participation, and management use with all but centralized databases being optimal. The variable readiness scores of safety-related and HR-related variables all exceeded the optimal level (Leslie et al., 2024). Thus, the safety-related and HR data received, passed the DART criteria and can be used for further predictive analyses. When compared to previous applications of the DART, this organization exceeded the overall optimal levels of two other companies. Conclusion Using the DART has allowed for the ability to assess and implement safe work practices (Ezerins et al., 2022). Even though some of the variables did not meet the 75% threshold for predictive analytics, the overall findings can still provide insight into whether an organization is ready for predictive analytics to provide beneficial results. These results show the benefits that a self-assessment tool can provide not only within a safety context but also for broader organizational practices. Organizations can leverage predictive analytics to create dynamic employee value propositions by anticipating the needs and expectations of their employees.
Department
University of Tennessee at Chattanooga. Dept. of Psychology