The big list for Decision Analytics

It's not just Data Science, Dashboards, or Machine Learning

Why read this page on decision analytics?

This page provides a comprehensive overview of decision analytics. Links for further reading are provided. Some of the links point to a FrogData repository, so they are available only to FrogData employees. Please post your inputs in the comments section and we will continuously improve this page.

What problems does decision analytics solve?

The first problem for decision analytics is to help determine the best decision, given your current knowledge. The complexity is that:

• when the opportunity for that decision occurs repeatedly, “current knowledge” includes all the expertise of people who work on a decision, and all the data used by those people in determining their decision;

• when the decision is encountered for the first time, you need to create a decision method from scratch.

The second problem is to make decision analytics available as and when needed to make the best decision at every opportunity.

The third problem is to locate opportunities to make better decisions, and to understand the degree to which decisions drive results, as opposed to chance.

What solution does decision analytics provide?

The solution is to build a decision model that includes the expertise of selected people who work on a decision, and all the relevant data used by those people in determining their decision. Once a decision model is made, it can evolve to become better at achieving its goals by changing its algorithm (adding/removing/changing expertise and data elements). It is a better-than-before solution to start with and the basis for continuous improvement.

Decision analytics is used to institutionalize the knowledge and tools needed to make the best decision at every opportunity, and converts decision-making methods into subjects for continuous improvement.

Decision analytics systems provide a systematic way for decision models to be stored, used, and evolved for organizations. For example the FDAP.

Decision Analytics uses some but not all of AI and Analytics. What domains use analytics but are not “decision analytics”? Examples are: speech recognition and translation, image recognition, chatbots, robotics, autonomous driving, drones, chess-playing, medical diagnoses by reading images, gene sequencing, scientific research analyses, etc. In these cases, analytics tools are used for purposes other than supporting decisions about what people and organizations should do.

---

The big list for decision analytics lays out the elements of the solution

1. Making Rational Decisions Systematically

   1. Rational Decisions

      1. What is a rational decision. Goals, levers, options, and decisions. Ref “How to recognize a decision”.

      2. Decision Analysis is a peer-reviewed international journal published by INFORMS dedicated to advancing the theory, application, and teaching of all aspects of decision analysis. The primary focus of the journal is to develop and study operational decision-making methods, drawing on all aspects of decision theory, decision analysis, and behavioral decision theory with the ultimate objective of providing practical guidance for decision makers.

      3. Stafford Beer is known for his work in the fields of operational research and management cybernetics

      4. In the field of management and leadership, we can use “evidence-based practice” for rational decisions. Ref the Center for Evidence-Based Management (CEBMa).

   2. Decide-and-learn (the adaptive decision cycle)

      1. A/B Testing (analysis of randomized experiments), Design of Experiments (DOE), and Natural Experiments

      2. “Plan, Do, Check, Act” or the Shewhart cycle popularized by Dr. W. Edwards Deming; DMAIC (define, measure, analyze, improve, control) used in Six Sigma; and Continuous Improvement (Kaizen)

      3. The OODA loop is the observe–orient–decide–act cycle, developed by military strategist and United States Air Force Colonel John Boyd.

      4. Adaptive Enterprise: creating and leading sense-and-respond organizations, by Stephan H. Haeckel

      5. Decision Cycle, by Rahul Saxena. The decision cycle has a

         decision inventory, a set of decision needs that anchors the cycle to the business need. Decision models, advice delivery, decision analysis, execution analysis, and outcomes analysis are needed in all decide-and-learn cycles and are explicitly defined in the Decision Cycle. Published in "The Analytics Asset." Impact of Emerging Digital Technologies on Leadership in Global Business, edited by Peter A.C. Smith and Tom Cockburn, IGI Global, 2014, pp. 124-149. https://doi.org/10.4018/978-1-4666-6134-9.ch007.

   3. Different kinds of decisions

      1. Organizational decisions: there are shared values (e.g., maximize profit) so the objectives are clear and often measurable, guiding the decision-making and learning processes

      2. Individual decisions: values are individual-specific and vary with time and person, dispersion in outcomes kills time (can be socially costly to differ from a cohort), possible to make decision support models like “in general if you do x the effects are y”. Used for determining medical treatment, buying life insurance, managing investments of time and money, career choices, performance coaching, etc.

         1. Medical treatment analytics, e.g., Stephen Barrager on analyzing cancer treatment: Management Science Guru, Surviving Cancer, Offers Hope to Fellow Sufferers, Doctors and Decision Coaching in Cancer Treatment

         2. Buying Life Insurance plans

      3. Political decisions: where values and objectives are up for debate, e.g., in democratic governance decisions

         1. Law and Order, Police and Judiciary

         2. Economic Strength, Prosperity, and Equity

         3. Defense Strategy and Funding

         4. Happiness, Determination, and Coddling

         5. Representative Republics, Democracy, and other forms of Governance

         6. Voting, Majority-wins, and Multi-winner Methods

         7. Markets, Pricing, and Regulations

   4. Decision Needs and Decision Layers. Decision needs are outlined using methods such as those in the Business Problem (Question) Framing and Analytics Problem Framing steps in the INFORMS Certified Analytics Professional's Job Task Analysis. There are four kinds of decisions:

      1. Network Layer (Strategy) Decisions

         1. Outline the industry landscape using Context Diagrams. The decision-making organization is shown as a box in the center. Other organizations that interact with it are shown in separate boxes, with lines depicting the inflows and outflows of data and materials. Use the SSADM Level 0 (Context Diagram), Porter Five Forces model, Value Networks, Supply Chain, and Demand Chain concepts to build the industry landscape.

         2. What is a strategic decision?

            1. Expand: New market, new manufacturing plant, etc.

            2. Exit, Rebalance, Add/Change Capacity needed or Market addressed

            3. Set boundaries: productivity/employee required, market position, margin, etc.

      2. Capability Layer (Capacity) Decisions

         1. What are capabilities? Drill down one level into the Context Diagrams for the decision-making organization to disaggregate its major functions such as sales, service, manufacturing, etc. Use the APQC Process Classification Framework, the organization chart (the departments or functions in the organization), etc. as a guide. The complexity here is that very large organizations can be structured in three dimensions, such as function (sales, service, manufacturing, etc.), region (such as North America, Europe, Africa, etc.), and industry (where the sales are focused on industries such as Telecom, Banking, Retail, etc.)

         2. What is a capability decision?

            1. Increase or reduce capacity (e.g., hire/fire) in a team.

            2. Add the capability to manufacture or provide a service.

      3. Control Systems Layer (Scheduling) Decisions that set the schedule and assignment of workloads, such as job-scheduling optimization or driver/trip allocation.

      4. Workflow Layer (Dispatch) Decisions that have to be taken by the assignee when assigned a job, usually about when to stop-work (e.g., when the worker encounters a situation that would lead to a bad outcome).

   5. Decision Chains and Dependencies. Decisions are interconnected, and it is useful to trace and model the main interconnections to assure alignment.

      1. Cascading decisions, cascading down (from strategy to capacity to scheduling to workflow) or cascading back up (from workflow to scheduling, etc.)

      2. Sequential decisions (such as assigning truck drivers to loads) where the decisions occur repeatedly and what’s optimal in one cycle can be suboptimal over repeated cycles. Ref the Castle Lab in Princeton University.

   6. Decide-and-learn (the adaptive decision cycle)

      1. A/B Testing (analysis of randomized experiments), Design of Experiments (DOE), and Natural Experiments

      2. “Plan, Do, Check, Act” or the Shewhart cycle popularized by Dr. W. Edwards Deming; DMAIC (define, measure, analyze, improve, control) used in Six Sigma; and Continuous Improvement (Kaizen)

      3. The OODA loop is the observe–orient–decide–act cycle, developed by military strategist and United States Air Force Colonel John Boyd.

      4. Adaptive Enterprise: creating and leading sense-and-respond organizations, by Stephan H. Haeckel

      5. Decision Cycle, by Rahul Saxena. The decision cycle has a

         decision inventory, a set of decision needs that anchors the cycle to the business need. Decision models, advice delivery, decision analysis, execution analysis, and outcomes analysis are needed in all decide-and-learn cycles and are explicitly defined in the Decision Cycle. Published in "The Analytics Asset." Impact of Emerging Digital Technologies on Leadership in Global Business, edited by Peter A.C. Smith and Tom Cockburn, IGI Global, 2014, pp. 124-149. https://doi.org/10.4018/978-1-4666-6134-9.ch007.

   7. Decision Cycle Models: supporting decision needs systematically and adaptively (in a learning loop)

      1. Decision Portfolio Analytics: understanding what decisions are needed, and how they relate to business strategy, operations, and business environment

      2. Decision Cycle Models: techniques for making effective decisions in a continuous improvement loop (a learning loop)

      3. Model to Advice: connecting insights to decisions, providing usable analytics to decision-makers

         1. Decision trees and decision rules

         2. A/B testing

         3. Multi-criteria decision making

         4. Price discovery and auctions

         5. Preference discovery and voting

      4. Advice to Decision: enable decision makers to effectively use the analytics, drive adoption of the analytics

      5. Decision to Execution: analytics to track execution, close gaps, identify best practices, and drive successes

      6. Execution to Outcome: analytics to track outcomes, provide early warning of unworkable strategies, and identify winning strategies

   8. Decision Making Methods for an Individual or a Group

      1. The Role of the Decision Modeler

      2. The Decision Making Method

      3. Set Context

      4. Decision Process

      5. Decision Making Roles

      6. Biases, Emotions, and Bounded Rationality

      7. Managing Irrationality: Removing Bias from Analytics

2. Analytics Systems

   1. Types of Analytics Systems. Systems and market categories will evolve in two tracks: (1) data supply chain and (2) decision cycle system

      1. The “management information system” (MIS) concept debuted in 1959, and evolved into EIS and DSS. It is the root of analytics dashboards.

      2. IBM researchers published the first paper for an “enterprise

         data warehouse” (EDW) in 1988. It caught on, and in the 1990s companies constructed data warehouses (DW). The Data Warehousing Institute (TDWI) was founded in 1995. The “business intelligence” (BI) term was added in the 1990s and the BI/DW terms updated the MIS/EIS terms.

      3. Currently we discern four categories of analytics systems in the market. See “Narrow AI for Decision Intelligence”.

         • 2 types of Data Supply Chain systems: data-pipelines and dashboards

         • 2 types of Decision Cycle Systems: advanced analytics (forecasting, optimization, simulation, decision modeling, etc.) and value realization

   2. Types of Data Sources

      1. Transaction Processing Systems such as ERP, CRM, eCommerce, etc.

      2. Internet of Things, SCADA, PLCs, RFID, GPS, etc. (sensors and actuators)

      3. Social Media

      4. Survey and Voting Tools

      5. Documents, images, video, audio, and other electronic media

      6. Benchmarks and External Data Sources, including stock-market data and other public metrics

      7. Analytical Outputs that serve as Inputs for further analyses

   3. Data Supply Chain

      1. Data Loading with Data Pipelines: fetch, assess, transform, and store. Extract-Transform-Load (ETL) and Extract-Load-Transform (ELT).

         1. Design of Data-to-Report Flows, Data Stores, and Metadata Stores

         2. Build data pipelines with Python and Pandas

         3. Build data pipelines with other technologies such as Spark, Scala, Flink, Pentaho, Talend, DataStage, Kibana, etc.

         4. Design of Data-Enrichment Flows, Data Stores, and Metadata Stores (e.g. Genders, Locations, Colors, Vehicle Year-Make-Model-Trim, etc.)

         5. Design of Data-Quality Flows, Data Stores, and Metadata Stores

      2. Data Storage

         1. Data Store Concepts (Data Warehouses and Marts)

         2. Flatfiles, Relational Databases, Columnar Databases, Graph Databases, Hadoop, and Logical Data Warehouses

      3. Data Quality, Metadata Management, and Data Stewardship

      4. Dashboards, Reports, and Models

         1. Enterprise dashboards

         2. Reports with text, tables, and graphs

         3. Model-driven Reports

   4. Decision Cycle System or “decision factory”

      1. Decision Model Creation, Assessment, and Updates

      2. Decision Model Operations

         1. Analysis to Advice

         2. Advice to Decision

         3. Decision to Execution

         4. Execution to Results

      3. Decision Inventory and Decision System Introspection. Track which decisions have models, and how the models align. This is needed to close gaps in models, to find places where decision models don’t exist, and where decisions are misaligned between different models.

         1. Situation Awareness as a method to monitor the organization’s battlespace, locate hotspots (opportunities and problems), alert the commanders, and help commanders to direct the response.

         2. Autonomous Response (Loitering Munitions) is a method to automatically trigger the best response to a hotspot using the Decision Model operations cycle.

         3. Manual Response provides the workflow, logging, and analytics to assure effective response and learn-from-doing using a shell Decision Cycle that builds up by learning

         4. War Gaming is a method to simulate scenarios that the organization can use to prepare responses in advance of encountering them in the real world. It can also be used to train commanders in Red Teams and Blue Teams.

         5. Battlespace Simulation is used to automatically assess trillions of combinations of variables in the environment and in the organization to locate possible hotspots that can be solved with Decision Modeling, and War Games. It can also be used to train commanders by pitting them against the simulation.

   5. Coordination, sequencing, and timing of Analytics Systems

      1. Event-based (e.g., cronjobs, event buses)

      2. Message-based (e.g., Kafka, MQ)

      3. Frameworks such as AWS Glue and AWS Step Functions

   6. Infrastructure

      1. Servers & Server-less Compute: VMware, Docker, Kubernetes, etc.

      2. Security and Access Control

      3. Storage, Backup, and Restore

3. Analytics Methods and Tools

   1. Analytics Methods

      1. Structure & Relationships Modeling (Boxes and Arrows)

      2. Data Tables (Spreadsheets), Simple Visualizations, and Simple Formulas

      3. Statistics

         1. One-dimensional distributions (histograms)

         2. Measures such as mean, median, mode, etc.

         3. Two-dimensional Scatters, Correlation and Regression

         4. Hypothesis Testing

         5. Time Series and Forecasting

         6. Control Charts, SPC and SQC

         7. Design of Experiments

         8. Machine Learning

         9. Sampling

      4. Simulation

         1. Monte Carlo

         2. Discrete Event Simulation

         3. System Dynamics

         4. Markov Chains and Hidden Markov Models

      5. Optimization and Decision Analysis

         1. Optimization, Transportation, and Assignment

         2. Network Optimization

         3. Sequential decision problems (dynamic programming, stochastic programming, stochastic search, optimal control, simulation-optimization, multiarmed bandit problems and reinforcement learning)

         4. Queuing

         5. Game Theory (e.g., this course by Dr. Vince Knight or this book by Dr. Giacomo Bonanno)

         6. Decision Cycle Modeling

      6. Decision Intelligence Improvement. This is about strengthening the ability to make rational decisions by harnessing methods and data into decision models that are used to generate outcomes that are desired by the user of the Decision Intelligence.

         1. Business Processes (e.g., APQC Process Classification Framework) as a way to extend the process analysis and design techniques at the root of industrial engineering and scale them up to manage at enterprise or multi-enterprise scales (e.g., in a supply chain or in delivery of complex services).

         2. Outcomes, Metrics, and Targets

            1. The APQC Process & Performance Management is an example of how pooled expertise helps to set metrics and benchmarks. Another example is NADA 20 Groups for US Auto Retail.

            2. Enterprise Performance Management (EPM) as a method to define metrics, set goals, measure actuals, alert when any metric is out of control, with the expectation that users will take action to adjust the process so as to get to the goals. The meta-model for such thinking appears to be the Viable Systems Model of Stafford Beer.

            3. The Balanced Scorecard is a framework to determine the metrics to be used.

         3. Quality, Efficiency, and Throughput

            1. Walter Shewhart, Edward Deming, Total Quality Management (TQM) and Kaizen (Continuous Improvement)

            2. In 1984, Eliyahu M. Goldratt and Jeff Cox wrote “The Goal: A Process of Ongoing Improvement” to introduce their Theory of Constraints

            3. Six Sigma

         4. Scheduling and Dispatch

         5. Strategic Planning and Capacity Management

         6. Project Management, PERT, and CPM

         7. Customer Acquisition, Marketing, Sales, and Loyalty

         8. Supply Chain, Inventory, Transportation, Warehousing, Manufacturing, Purchasing, and Distribution Chain

            1. Inventory Replenishment

            2. Inventory Obsolescence or Frozen Capital in Inventory

         9. Service Tickets, Service Projects, Service Commitments, and Asset Health (Uptime, Availability, Reliability, and Value Provided)

         10. Accounting and Finance

             1. In 1912, DuPont explosives salesman Donaldson Brown invented the formulas to understand ROE (return on equity) based on their underlying drivers. This is widely used as the DuPont Model.

         11. Human Resources

      7. Decision Intelligence Reduction. This is about reducing or eliminating the targets’ ability to make decisions by harnessing methods and data into decision models that run processes designed to drive outcomes that are desired by the creator of the Decision Intelligence. This is common in Consumer Analytics, Advertising, eCommerce, and Political Analytics. Uses methods to reduce “friction” so that people slide to an analyst-desired action (such as buying an overpriced product or supporting a candidate) without thinking deeply about the decision, where thinking would slow down or bypass the analyst-desired decision.

         1. Frictionless eCommerce

         2. Nudge technologies in Public Health, Welfare, and other state services

         3. The US Department of Defense “Information Warfare” or the Cognitive Domain Operations (CDO), used by the Chinese Army for psychological warfare in the information era.

      8. Data quality (assess fitness-for-use and resolve)

   2. Analytics Tools (for Analysis, Data Visualization, Dashboards, and Reporting)

      1. MS Excel. A few references: Excel For Statistical Data Analysis, Excel Easy, Use the Analysis ToolPak to perform complex data analysis, Excel For Decision Making, Developing Spreadsheet-Based Decision Support Systems, and Spreadsheet Modelling Best Practice.

      2. Python (with libraries such as pandas, scipy, numpy, etc.) and R

      3. SQL (like MySQL) and NoSQL (like MongoDB)

      4. Tableau, Spotfire, Qlik, Quicksight, PowerBI, etc.

      5. JavaScript, CSS, HTML, D3JS, etc. for reporting & data-visualization

      6. Postman, a platform for building and using APIs

      7. MS Excel Plug-ins for Advanced Analytics, such as Frontline Solvers, @Risk, etc.

      8. Simulation systems such as Arena, Anylogic, Simul8, etc.

      9. System Dynamics modeling tools such as Vensim, Stella, etc.

      10. Simple simulation tools such as Analytica, GoldSim, etc.

      11. Optimization with IBM ILOG CPLEX, Gurobi, etc.

      12. Advanced Analytics modeling systems such as AIMMS, Alteryx, MATLAB, etc.

4. Data Stewardship, Master Data, and Metadata

   1. Data, data dictionaries, privacy, tagging, and categorizations

   2. Master data, lookup tables, and hierarchies

5. Value Management – from problem-assessment to results

6. Making Organizations Smarter

   1. What is an intelligent organization, and how does it become more intelligent?

      1. Realizing the dream of the Intelligent Enterprise

         1. Layer 1 – Focus & Specialization into teams that collaborate to act in concert. It's usual for organizations to have teams in divisional and functional structure. Teams enable focus (on a line-of-business or a region) and specialization (in accounting, sales, service, etc.). This is the foundation for intelligence in organizations. Specialization continues since the beginning of civilization (see The Age of Hyperspecialization by Thomas W. Malone et al) but increased specialization requires greater capacity for integration of the work of specialists.

         2. Layer 2 – Transaction Systems automate business tasks, such as order entry or pick-pack. Automation leads to standardization and control, which makes the work easier to manage. Systems for Customer Relationship Management (CRM), Enterprise Resource Planning (ERP), etc. are commonplace. These systems embed the intelligence of procedures and policies. They usually require human guidance for complex decisions, but can also embed artificial intelligence (AI in the sense of making that decision without recourse to a human) for decisions in the system workflows.

         3. Layer 3 – Analytics Systems collect and process data for decision support. They're useful, but also place demands on money and time.

            1. In 1954, Peter Drucker used the term “management by objectives” (MBO) in his book The Practice of Management.

            2. In 1972, Stafford Beer wrote about the Viable System Model to design and run autonomously intelligent systems in his book Brain of the Firm.

   2. Building intelligence in stages: personal intelligence as do-it-yourself analytics (idea →analysis →decision →execution), “analytics” as a staff function specialized in the analysis stage (usually staffed with statistics and operations research specialists), and “analytics” as a staff function that provides full-lifecycle support in all the stages using decision cycles to coordinate the roles of analysts and decision-makers.

   3. Analytics Culture Maturity

   4. Actionable Analytics

   5. Measure the Value of Analytics

   6. Scaling the decision culture

   7. Lies, Damn Lies, and Analytics

7. Building the Analytics Capability

   1. The Analytics Ecosystem

   2. Placing Analytics Capabilities in the Organization

   3. Analytics Team Skills and Capacity

      1. Data Supply Chain Analyst or Analytics Data Ops (understand and follow the Setup Process and Milestones)

         1. Customer Setup in the Decision System

         2. Data Supply Setup and Configuration

         3. Decision Setup and Configuration

         4. Decision Roles Setup and Configuration

      2. Decision Advisor or Decision Support Analyst

         1. Decision System User Enablement

         2. Decision Advisory Service

            1. Scientific Management by Frederick Winslow Taylor

            2. Management by Objectives, The Balanced Scorecard, Reengineering (Business Processes), etc.

         3. Analysis of the value created, learnings from decision-successes, decision-losses, and customer defections from the decision analytics system

      3. Decision System Integrity Analyst

         1. Decision System Availability, Security, and Reliability

         2. Decision Data Quality, Timeliness, Availability, Security, Privacy, and Reliability

      4. Decision Analyst (for Decision System Design, Test, and Deployment)

         1. Design Analytics Systems, Sub-systems, and Features (understand and follow the Design Guidelines)

         2. Manage the Design-to-Deploy Workflow (understand and follow the Git Standard Operating Procedures)

         3. Test the Systems and Changes

         4. Deploy the Systems and Changes

      5. Data Pipeline Software Engineer

         1. Data Pipelines design, build and test using Python, Pandas, MongoDB, and MySQL

         2. Event-driven Collaborating Intelligent Data Supply Agents

      6. Decision System Software Engineer

         1. Decision Cycle design, build and test using Python, Pandas, MongoDB, MySQL, JavaScript, and CSS

         2. Event-driven Collaborating Intelligent Decision Cycle Agents

      7. Analytics Infrastructure Software Engineer

         1. Analytics Cloud Platform Systems Management (Compute, Storage, Reliability, Security)

         2. Analytics Cloud Platform Cost Management

   4. Analytics Capability of Decision Makers

      1. Transition to using Decision Models and avoid Biases

         1. Grapple with the fact that many outcomes have a large component of chance or dependence on external trends and forces.

         2. Grapple with the fact that many management methods do not result in making better decisions.

         3. Grapple with the fact that data in business systems that should be directly usable for making decision is usually not ready-for-use because it takes care and effort to make data of high quality

         4. Understand that decision models use expertise from external and in-house sources into algorithms that help you to make decisions differently, and require you to be open-minded about using external expertise in making internal decisions

      2. Help to Build and Improve Decision Models

      3. Understand and Manage Data Quality

      4. Drive Pervasive Availability and Maximal Usage of Decision Models

      5. Understand Decision Gaps and the effect of Randomness

      6. Continuous Improvement of Decision Making

   5. Analytics Maturity Model

8. Books related to Decision Analytics

   1. Analytics

      1. Business Analytics by Rahul Saxena & Anand Srinivasan, 2013 at https://link.springer.com/book/10.1007/978-1-4614-6080-0

   2. Statistics

      1. Introduction to Modern Statistics, a website with PDF

   3. Operations Research, Decision Analysis, and Industrial Engineering

      1. Operations Research

         1. Fundamentals of Operations Research by Russell L. Ackoff and Maurice W. Sasieni

         2. Introduction to Operations Research by Frederick S. Hillier & Gerald J. Lieberman

         3. Operations Research by Hamdy A. Taha

         4. Optimization Stories by Martin Grotschel . This is a sweet book on the history of optimization. The first chapter, for example, is on how ancient Chinese mathematicians knew about Gaussian elimination.

         5. A Gentle Introduction to Optimization by B. Guenin, J. Konemann, and L. Tuncel, University of Waterloo, 2014

         6. Numerical Optimization by Jorge Nocedal and Stephen J. Wright, 2014

      2. Decision Analysis

         1. Spreadsheet Modeling & Decision Analysis, Cliff T. Ragsdale (2008)

         2. Decision Modeling by David M. Tulett, Memorial University

         3. Algorithms for Decision Making by Mykel J. Kochenderfer, Tim A. Wheeler, And Kyle H. Wray. MIT Press, 2022

   4. Industrial Engineering and Systems Engineering

      1. Production Systems: Planning, Analysis and Control by James L. Riggs

      2. System Dynamics Modelling and Simulation, by Bilash Kanti Bala, Fatimah Mohamed Arshad, and Kusairi Mohd Noh (2017)

   5. Management and Psychology

      1. The Fifth Discipline: The art and practice of the learning organization by Peter M. Senge (1990)

      2. Adaptive Enterprise: Creating and leading sense-and-respond organizations, by Stephan H. Haeckel (1999)

      3. Thinking, Fast and Slow by Daniel Kahneman (2011)

   6. Accounting, Finance, Economics

   7. Computer Science and Systems Science

      1. Python: widely used for analytics

         1. Free Python Books: https://www.theinsaneapp.com/2021/05/best-free-python-programming-books.html

   8. Data Stewardship

   9. Decision Analytics Systems and Platforms (Information Technology)