I. INTRODUCTION

In today's fast-paced and complex business environment, organizations need to find new ways to optimize their operations and stay ahead of the competition. Technology and innovation are key drivers of this transformation, and they require new management methods to leverage their potential. The convergence of Lean, Six Sigma, and AI technologies like Machine Learning and Big Data Analytics promises to revolutionize the way we approach strategy execution and propel organizations into a new era of operational excellence [1].

LSS aims at a capability level of 3.4 defects per million opportunities. Many businesses have attempted to implement LSS, but not everyone has succeeded in improving the business processes to achieve expected outcomes. [9]

The potential to integrate Lean Manufacturing to Industry 4.0 has been debated [3], and, more specifically, Lean Six Sigma has been investigated in its applications to accelerate the process of extracting key insights from Big Data, and how Big Data processing can help to innovate and cast a new light on the projects requiring the use of Lean Six Sigma [3].

In the context of Big Data Analytics, the law of large numbers is critical for understanding the selection of training datasets, test datasets, and in the evaluation of model skill. It supports the intuition that the sample becomes more representative of the population as its size is increased.

For instance, if we collect more data, our sample of data will be more representative of the problem domain. As the size of the sample increases, the mean value of the sample will better approximate the mean or expected value in the population. As the sample size goes to infinity, the sample mean will converge to the population mean.

Analysis of massive data generated by IR4.0 technologies can't be done with usual Six Sigma statistical techniques. A more advanced Data Analytics algorithms and advanced statistical Machine Learning (ML) Models would produce more valuable information to support optimal decision making. New ML tools will not replace good LSS tools like DMAIC, PDCA, Pareto or fishbone diagrams, but will enhance them with more accurate inferential methods. Basic data mining techniques such as clustering, association, prediction, classification and process mining help organizations reach correct and optimal decisions at various stages of LSS projects.

Lean Six Sigma and Big Data Analytics are two complementary approaches that can enhance each other's capabilities and outcomes. Lean Six Sigma is a methodology that focuses on eliminating waste and variation in processes, while Big Data Analytics is a term that refers to the collection, analysis, and use of large and complex data sets. By combining Lean Six Sigma and Big Data Analytics, organizations can achieve powerful integration of data-driven insights and process improvement techniques. This can lead to improved quality, efficiency, innovation, and customer satisfaction.

Big Data Analytics can enhance Lean Six Sigma by providing tools for data analysis, process optimization, voice of customer, anomaly detection, predictive maintenance and more. Also, it can help to automate some of the tasks that are repetitive or tedious for humans, such as data collection, measurement and reporting [3].

However, such AI technologies also poses some challenges for Lean Six Sigma practitioners. For example, AI may require new skills and competencies to understand and interpret the results of machine learning models. AI may also introduce new sources of variation or bias that need to be identified and controlled [3].

The synergy between Lean, Six Sigma, and Big Data Analytics manifests itself in several ways, some of which are listed below [1]:

1. Enhanced Decision-Making: With AI's ability to process vast amounts of data and identify patterns,

organizations can make more informed decisions that align with Lean and Six Sigma principles. For instance, AI can help interpret trends in data and identify outliers, enabling targeted improvements to eliminate waste and reduce variation.

1. Predictive Analytics and Scenario Planning: AI-driven predictive analytics can empower organizations to foresee potential issues and address them proactively. By leveraging AI in scenario planning, organizations can develop a playbook of potential issues and pre-planned responses, ensuring they are prepared for any eventuality.

2. Continuous Improvement: By integrating AI into Lean and Six Sigma initiatives, organizations can create a continuous improvement loop that constantly refines processes and performance.

II. LSS METHODOLOGIES

Lean Six Sigma methodologies are designed to eliminate waste, bottlenecks, and achieve total customer satisfaction. They combine the principles of lean manufacturing/lean enterprise and Six Sigma to optimize processes and improve quality [2].

Some of the techniques and tools used to implement Lean Six Sigma methodologies include:

1. Kanban: Workflow management practices, such as work visualization and limited work in progress,

which maximize efficiency and promote continuous improvement [3].

1. Kaizen: Practices that engage employees and promote a work environment that emphasizes self-development and ongoing improvement [3].

2. Value Stream Mapping: Analyze places to eliminate waste and optimize process steps [3].

3. DMAIC: A data-driven five-phase problem-solving framework to six sigma projects. DMAIC is an acronym for five interconnected phases: Define, Measure, Analyze, Improve, and Control [3] [6].

4. DMADV: A five-phase framework for designing new products or processes that stands for Define, Measure, Analyze, Design, and Verify [3].

Lean Six Sigma methodologies (Table 1) follow a data-driven approach that relies on statistical analysis and measurement to identify root causes of problems and implement solutions. They also focus on delivering value to customers by understanding their needs and expectations. Approximately $95\mathrm{\%}$ of LSS projects follow to improve quality so-called define-measure-analyze-improve-control (DMAIC) approach [2].

DMAIC has proven to be one of the most effective problem-solving methods used up to now, because it forces the teams to heavily utilize the data [2]. Table 2 lists the DMAIC approach steps and sample activities. Table 3 lists all the tools utilized in the DMAIC five steps of which AI models are part of.

Characteristics	Methodologies
	Lean	Six Sigma	Lean Six Sigma	Kaizen
Scope	Eliminating unwanted activities	Reducing variance	Waste elimination and variation reduction	Small and incremental changes
Objective	Reduction in workflow time	Process standardisation	Process standardisation and waste reduction	Incremental continuous improvements
Use of information technology tools	Very high	Very high	Very high	Intermediate
Relying on data in decisions making	High	High	High	High
Change method	One time	Incremental	Continuing	Continuing incremental
Associated risk levels	High	Moderate	Moderate	Moderate

Phase	Descriptions	Sample activities
Define	Define the purpose and scope of the six sigma project	Define why the project should be done
		Define the targets, goals and scopes of project
		Define the customer requirements
Measure	Measure to determine the current situation	Select the output characteristics
		Assess the performance specifications
		Establish the initial process capability
Analyze	Analyze and determine the actual causes for process improvement	Analyze the current process performance
		Monitor the potential Critical to Process (CTP)
		Analyze what resources will be needed for improvement
Improve	Improve the process by eliminating wasteful causes, removing the problem or reducing the effects of the problem	Improve idea
		Identify optimal operating conditions
		Eliminate wastes
Control	Control the improved process performance	Determine the process capability for CTPs
		Implement the process controls
		Document what you have learned

	Define	Measure	Analyze	Improve	Control	Design	Verify
Statistics	Descriptive	Descriptive, Tally chart, Z-test, Confidence intervals, Predictive	Correlation, T-test, Chi-square test, F-test, Hypothesis tests, ANOVA, Histogram, Predictive	Hypothesis tests, Multivariate Analysis		Descriptive, Predictive	Correlation, Causality
Quality Tools	Brain storming, NGT, Pareto analysis, Matrix diagram, QFD, FMEA, SIPOC, Prioritization matrix, Fishbone analysis,	Pareto analysis, Process sigma	SPC	TRIZ, DOE	FMEA, Control diagram, Standardization, SPC	QFD, DOE
Data Mining1			Association Rules, Clustering, Classification	Prediction		Market Basket Analysis, Association Rules
Big Data	Text Mining, Video Mining		Machine Learning, Decision Trees, Text Mining, Video Mining, Artificial Intelligence	Machine Learning, Artificial Intelligence	Machine Learning, Artificial Intelligence		Machine Learning, Artificial Intelligence
Process Mining	Process Discovery	Conformance checking	Process Discovery, Conformance checking	Flow diagrams, Enhancement	Flow diagrams, Conformance checking		Graphing, Visualization

III. AI: BIG DATA ANALYTICS

Data is created constantly, and at an ever-increasing rate. Mobile phones, social media, imaging technologies to determine a medical diagnosis- all these and more create new data, and that must be stored somewhere for some purpose. Devices and sensors automatically generate diagnostic information that needs to be stored and processed in real time. Merely keeping up with this huge influx of data is difficult, but substantially more challenging is analyzing vast amounts of it, especially when it does not conform to traditional notions of data structure, to identify meaningful patterns and extract useful information. These challenges of the data deluge present the opportunity to transform business, government, science, and everyday life.

Big data analytics is the process of using advanced techniques and tools to analyze large and complex datasets and extract useful information from them.

The Big Data trend is generating an enormous amount of information from many new sources. This data deluge requires advanced analytics and new market players to take advantage of these opportunities and new market dynamics. [10]

Some of the Big Data types include:

1. Structured Data: This is data that has a predefined format and can be easily stored and processed in databases or spreadsheets. Examples of structured data are customer records, sales transactions, sensor readings, etc.

2. Unstructured Data: This is data that has no fixed format and is often text-based or multimedia. Examples of unstructured data are emails, social media posts, videos, images, audio files, etc.

3. Semi-Structured Data: This is data that has some elements of structure but also contains unstructured components. Examples of semi-structured data are XML files, JSON files, web logs, etc. Chart 2 below presents a depiction of data evolution and the rise of Big Data Sources.

Chart 2: Data Evolution and the Rise of Big Data Sources [10]

Big Data Analytics process follows a five lifecycle phases. Here is a brief overview of the main phases:

• Phase 1- Discovery: In Phase 1, the team learns the business domain, including relevant history such as whether the organization or business unit has attempted similar projects in the past from which they can learn. The team assesses the resources available to support the project in terms of people, technology, time, and data. Important activities in this phase include framing the business problem as an analytics challenge that can be addressed in subsequent phases and formulating initial hypotheses (IHs) to test and begin learning the data.
• Phase 2- Data Preparation: Phase 2 requires the presence of an analytic sandbox, in which the team can work with data and perform analytics for the duration of the project. The team needs to execute extract, load, and transform (ELT) or extract, transform and load (ETL) to get data into the sandbox. The ELT and ETL are sometimes abbreviated as ETLT. Data should be transformed in the ETLT process so the team can work with it and analyze it. In this phase, the team also needs to familiarize itself with the data thoroughly and take steps to condition the data
• Phase 3- Model Planning: Phase 3 is model planning, where the team determines the methods, techniques, and workflow it intends to follow for the subsequent model building phase. The team explores the data to learn about the relationships between variables and subsequently selects key variables and the most suitable models.
• Phase 4- Model Building: In Phase 4, the team develops datasets for testing, training, and production purposes. In addition, in this phase the team builds and executes models based on the work done in the model planning phase. The team also considers whether its existing tools will suffice for running the models, or if it will need a more robust environment for executing models and workflows (for example, fast hardware and parallel processing, if applicable).
• Phase 5- Communicate Results: In Phase 5, the team, in collaboration with major stakeholders, determines if the results of the project are a success or a failure based on the criteria developed in Phase 1. The team should identify key findings, quantify the business value, and develop a narrative to summarize and convey findings to stakeholders.
• Phase 6- Operationalize: In Phase 6, the team delivers final reports, briefings, code, and technical documents. In addition, the team may run a pilot project to implement the models in a production environment.

IV. AI: MACHINE LEARNING (ML)

Machine learning is a branch of artificial intelligence (AI) that enables machines to learn from data and improve their performance without explicit programming [2]. Machine learning can be used to analyze big data and refine operations by identifying patterns, trends, anomalies, and correlations [3].

The machine learning model takes the featured data, as inputs, and examines them against a supervised machine learning approach or cluster them in unsupervised approach. The model then labels the input and recommends an action against each activity.

Lean Six Sigma can benefit from Machine Learning/Big Data Analytics by using it to:

• Enhance forecasting and decision making by using variance models and statistical analysis algorithms.
• Automate routine tasks and optimize workflows by using robotic process automation (RPA) and natural language processing (NLP).
• Improve customer satisfaction and loyalty by using sentiment analysis and recommendation systems.
• Consolidate critical success factors and best practices by using classification and clustering algorithms.

Machine learning/ Big Data Analytics can also benefit from Lean Six Sigma by using it to:

• Define clear objectives and metrics for machine learning projects by using DMAIC frameworks.
• Measure and monitor the performance of machine learning models by using control charts and dashboards.
• Analyze and improve the quality of data and models by using value stream mapping and root cause analysis.

Machine learning analytical methods are utilized to analyze big data and produce results. The output of machine learning models is the result of applying a trained algorithm to a given data set. Machine learning models are used to recognize patterns in data or make predictions based on the learned information. A machine learning model is defined as the mathematical representation of the real-world processes that are approximated by the algorithm. Different types of machine learning models are suited for different tasks, such as classification, regression, clustering, or recommendation. Some examples of machine learning models are support vector machines, decision trees, neural networks, and k-means clustering. These models are utilized during Big Data Analytics phase 3, model planning. Big data is fed into machine learning algorithms to analyze and for predicting output results. Big Data Analytics and Machine Learning are complementary fields that work together to teach machines how to recognize patterns in complex datasets and make valuable predictions.

Chart 1: A Simplified Representation of Common Machine Learning Algorithms

V. THE SYNERGY: INTEGRATED APPROACH

The presence of synergies between Lean Management Tools and Big Data Analytics is evident and therefore, the combination of Lean Management Tools and Big Data Analytics will bring significant benefits to the organizations. [5]

DMAIC and other process improvement methodologies greatly benefit from statistical methods of which Big Data helps providing accurate prediction close to the intended results.

In an integrated approach, Big Data Analytics can be used to train models on large datasets. The law of large numbers supports this by ensuring that as we collect more data, our sample becomes more representative of the population and our model's accuracy improves. These accurate models can be utilized at various stages of LSS projects.

DMAIC and other process improvement framework constituents can be categorized into the following phases: Process Discovery, Process Behavior Measurement/Prediction, Process Improvement and Process Optimization. In each phase various Big Data Analytics algorithms can be utilized to increase the quality/ accuracy of the phase outcome bringing the aim of reaching 3.4 defects per million. The table below lists the recommended ML/Big Data Analytics algorithms to each phase of LSS project.

Table 4

Phase	DMAIC Phase	Data Analytics Life Cycle	Tools/Algorithms
Process Discovery	Design	DiscoveryData PreparationModel Planning	SQLExploratory Data Analysis EDAData VisualizationData WranglingOutliers DetectionCorrelation & Regression ModelsPrediction based on History
Process Behavior Measurement/Prediction	Measure	Model Design & Building	Support Vector Machine (SVC)ClusteringAssociation RuleRegressionDecision TreeNaïve Bayes ClassifierTime Series AnalysisText Analysis
	Analyze
Process Improvement	Improve	Communicate Results	Data VisualizationExplanatory GraphsScatterplotHeatmapMapsQuality Control Charts
Process Optimization	Control	Operationalize	Linear ProgrammingNetwork ModelsDecision TreesSimulation, Monte Carlo, Next-Event Approach

Data Analytics life cycle phases can be mapped into LSS projects and accordingly utilize the available advanced tools to increase the quality/ accuracy of each LSS phase output.

VI. CONCLUSION

The aim of this paper was to present a comprehensive overview of how Lean Six Sigma and Big Data Analytics can be integrated to enhance the quality decision making process. Lean Six Sigma is a quality improvement methodology that focuses on reducing variation and waste in processes, while Big Data Analytics is the process of applying advanced techniques to analyze large and diverse datasets that contain various types of data. In the context of industry 4.0, where massive amounts of data are generated and available, traditional data analysis techniques used in Lean Six Sigma projects may not be adequate. Therefore, by combining both methodologies, quality projects can benefit from more effective and efficient decisions for quality problems. This paper proposed a framework for aligning or synthesizing the different stages of both methodologies, and suggested some algorithms and techniques that can be used in each stage. However, this paper did not provide detailed explanations of these algorithms and techniques, nor did it illustrate their applications with real-world case studies. These could be topics for future research or papers that could further enrich the subject and demonstrate its practical value.

ACKNOWLEDGMENT

The author extends his appreciation of Saudi Aramco and its management in specific "Tariq A. Turairi" for his support and encouragement to publish technical papers.