2
Discussion Thread: Management
Introductory Paragraph:
I have chosen to research how data science can be implemented alongside Lean Six
Sigma. To better understand the topic, I will begin by defining what Lean Six Sigma and data
science are while also briefly introducing how they can work together within the DMAIC
lifecycle. Lean Six Sigma is a methodology for implementing continuous improvement into an
organization (Zwetsloot et al., 2018). DMAIC is a project implementation tool for design,
measure, analysis, improvement, and control. DMAIC is a standard step-based tool within Lean
Six Sigma for solving complex organizational issues. Data science is the study that utilizes and
seeks to understand data usage (Zwetsloot et al., 2018). The researched studies were used to
determine how data science could improve upon the standard methodology used within Lean Six
Sigma.
Current Trends Paragraph:
The most powerful lesson extracted from the research was combining DMAIC from Lean
Six Sigma with CRISP-DM from data science. CRISP-DM is to data science as DMAIC is to
Lean Six Sigma. CRISP-SM is the most widely used and comprehensive data science
methodology that stands for Cross Industry Standard Process for Data Mining (Zwetsloot et al.,
2018). Separately they have proven to be excellent tools within their industries. Combining these
two tools adds another layer of depth to project analysis and completion that otherwise could not
exist (Zwetsloot et al., 2018). Both the DMAIC and CRISP-DM methodologies follow a step-by-
step framework. The research provides a real-world example of how the two tools are
3
interconnected to create a more thorough execution for each of the five significant processing
steps.
One of the primary weaknesses behind Lean Six Sigma is the inability to pull extensive
data for the initial analysis of a project. The standard DMAIC methodology for Lean Six
Sigma5is utilized with small data sets. The utilization of data science analytics allows for the
extraction of big data sets that primary Lean Six Sigma methodologies could not calculate. Data
science5provides5data-specific tools to be utilized during the five phases of the DMAIC
lifecycle.5Data mining techniques can be used within the design phase to extract
enough5information to define the current5issue at hand (Gupta et al., 2019). The5data mined and
analyzed can create process maps5that utilize confidence5intervals and process sigma
checks5(Gupta et al., 2019). Decision trees and other5analytical methods can be used within the
analysis phase to figure out the identified5issue's root cause.5The5improvement phase5has
been5identified as the most advanced and valuable technology utilized for data science.5Using
data science, artificial5intelligence, and simulation creation, and5implementation5can be used
within the5improvement5phase (Gupta et al., 2019).5Modern software allows Lean Six Sigma
practitioners and Data Scientists5to plugin-specific data to extract a particular set of outcomes
that can be utilized to push through the5improvement phase.5The data and tools amassed
throughout the first four phases can be continuously monitored and used during the control
phase. All these options would not be possible without the usage of Data Science within Lean
Six Sigma.5
Future Research Paragraph:
4
The study of Lean Six Sigma5is continuously evolving as technology5improves. Findings
from fifty-two5articles were conducted to provide their conclusions on Lean Six Sigma. That
leaves thousands of articles that remain to be analyzed and synthesized with Lean Six Sigma and
Business Management (Gupta et al., 2019).55The study of MDAIC can revolutionize the usage of
Lean Six Sigma for specific business sectors. Future studies could branch off into the financial,
healthcare, or other business sectors to expand upon the valuable utilization of the MDAIC
framework (Koppel & Chang, 2021).5 One of the weaknesses of any analysis is the significant
amount of information required to write a synthesis. Future studies could branch beyond the
financial industry while analyzing research from a broader range of modern articles (Vashishth et
al., 2017).5
5
References
Gupta, S., Modgil, S., & Gunasekaran, A. (2020). Big data5in lean six sigma: A review and
further research directions.5International Journal of Production Research,558(3), 947–
969. https://doi.org/10.1080/00207543.2019.1598599
Koppel, S., & Chang, S. (2021). MDAIC – a Six Sigma5implementation strategy5in big data
environments.5International Journal of Lean Six Sigma,512(2), 432–449.
https://doi.org/10.1108/IJLSS-12-2019-01235
Uluskan, M. (2019). Analysis of Lean Six Sigma tools from a multidimensional
perspective.5Total Quality Management & Business Excellence,530(9–10), 1167–1188.
https://doi.org/10.1080/14783363.2017.13601345
Vashishth, A., Chakraborty, A., & Antony, J. (2019). Lean Six Sigma5in financial
services5industry: A systematic review and agenda for future research.5Total Quality
Management & Business Excellence,530(3–4), 447–465.
https://doi.org/10.1080/14783363.2017.13088205
Zwetsloot,5I. M., Kuiper, A.,5Akkerhuis, T. S., & de Koning, H. (2018).5Lean Six Sigma meets
data science:5Integrating two approaches based on three case studies. Quality
Engineering, 30(3), 419–431. https://doi.org/10.1080/08982112.2018.14348925
Powered by TCPDF (www.tcpdf.org)
