The recent webinar presented by Hesham Mahmoud, an experienced professional in the fields of multinational corporations, academia, and the United Nations, focused on the intersection of Machine Learning (AI) and System Dynamics. This post summarizes the webinar’s key points, including the Q&A session, offering insights into how these two methodologies can be effectively integrated.

Presenter Background:

Hesham Mahmoud, currently a Junior Lecturer and Machine Learning Researcher at Radboud University, brings a wealth of experience from his roles in various sectors, including his tenure at the Food and Agriculture Organization of the United Nations. His expertise in Economics and Political Economics, combined with his professional experience, provides a unique perspective on the application of Machine Learning in System Dynamics.

Webinar Summary:

1. Defining the Relationship between AI, Machine Learning, and System Dynamics: Mahmoud began by delineating the distinctions and connections between AI, Machine Learning, and System Dynamics. He emphasized the potential of Machine Learning to enhance the analytical capabilities in System Dynamics, moving beyond the traditional view of AI as a complex and opaque field.

2. Addressing Bias and Ensuring Objectivity: The webinar highlighted the challenge of bias in Machine Learning algorithms. Mahmoud discussed the importance of feature selection and the role of human oversight in ensuring that machine-learning models are as objective and unbiased as possible.

3. Data Challenges in Machine Learning: Mahmoud pointed out that both the scarcity and abundance of data present challenges in Machine Learning. He stressed the importance of careful decision-making in feature selection to avoid introducing biases into the models.

4. Complementarity of Machine Learning and System Dynamics: The discussion underscored how Machine Learning could uncover patterns in data that might not be immediately apparent in System Dynamics models, while System Dynamics can provide a human-centric approach to guide Machine Learning analyses.

5. Practical Applications in Healthcare: The webinar touched on the application of these methods in healthcare, demonstrating how combining Machine Learning with System Dynamics could enhance predictive models in medical systems.

Key Points from the Q&A:

• Machine Learning as a Complement to System Dynamics: Mahmoud clarified that Machine Learning should be seen as a complementary tool to System Dynamics, not as a replacement. He emphasized its utility in providing data-driven insights that can inform and refine System Dynamics models.

• Bias Mitigation in Combined Approaches: In response to concerns about bias, Mahmoud discussed how integrating Machine Learning with System Dynamics could help mitigate biases from both fields. He suggested that the triangulation of data-driven insights and System Dynamics models could lead to more balanced and objective outcomes.

• Ethical Considerations in Model Design: Mahmoud acknowledged the importance of ethical considerations in the design and application of Machine Learning models, especially when used in conjunction with System Dynamics. He stressed the need for ethical frameworks to guide decision-making in these integrated approaches.

• Technical Aspects of Integration: Addressing the technicalities, Mahmoud mentioned the availability of tools and packages in programming languages like R, which facilitate the integration of traditional System Dynamics models with Machine Learning techniques.

This webinar provided a comprehensive overview of how Machine Learning can be integrated with System Dynamics to enhance model accuracy and objectivity. The key takeaway is that these two methodologies, when combined, can offer a more robust approach to understanding and solving complex problems, particularly in fields like healthcare. The Q&A session further reinforced the idea that Machine Learning and System Dynamics are not competing but are complementary tools that, when used together, can lead to more effective and ethical outcomes.

This session is organized and led by MINDS – the student-led System Dynamics Association at the University of Bergen in Norway.

Watch the recording below

About the Speaker

“”The recent webinar hosted by the System Dynamics Society featured Linda Booth Sweeney and Philip Ramsey, offering an overview of the world of systems thinking and its application in education and storytelling. Linda, an accomplished educator and author, shared her journey in integrating systems thinking into various educational materials and books. Philip Ramsey, an author and senior lecturer at Massey University, New Zealand, discussed his Billy Bonk and Frankel series, aimed at teaching systems thinking to children.

Linda Booth Sweeney: Bridging Systems Thinking and Storytelling

Linda emphasized the importance of early exposure to systems thinking, noting that it can become a habitual way of thinking if introduced at a young age. Her approach involves using simple, yet powerful, questions to encourage children to visualize and discuss the connections in the world around them. She introduced her new book, “Apart Together,” which aims to cultivate systems literacy, a growth mindset, and resilience in children.

Key Takeaways from Linda’s Presentation:

Early Systems Thinking: Linda highlighted the necessity of introducing systems thinking to children, potentially preventing the fragmentation of knowledge as they grow older.

Curious About Connections: She introduced her methodology involving three questions – “What’s happening here?”, “What if this is connected to that?”, and “What caused what to change?” – to help children visualize and think about systems.

Access the free companion guide when you subscribe to the “Curious About Connections” Newsletter here.

Practical Implementation: Linda shared how her methodology and book can be utilized in various everyday scenarios, from family discussions to classroom settings, to instill a sense of curiosity and interconnectedness in children.

Philip Ramsey: Storytelling with Systems Thinking

Philip Ramsey’s part of the webinar focused on his Billy Bonk and Frankel series, republished recently with the help of the System Dynamics Society. These books are designed to teach systems thinking to children around age 10. He emphasized the role of storytelling in making complex concepts accessible and engaging for young minds.

Key Insights from Philip’s Presentation:

Targeted Age Group: Philip’s books are primarily aimed at children around 9-11 years old, making them a suitable tool for educators and parents to introduce systems thinking at a slightly more advanced level.

The Power of Storytelling: He underscored storytelling as an effective method to communicate systems thinking concepts, making them relatable and easier to understand for children.

Series Development: The Billy Bonk and Frankel series were developed to not only entertain but also educate children, demonstrating the practical application of systems thinking in various scenarios.

The webinar with Linda Booth Sweeney and Philip Ramsey was an enlightening exploration of systems thinking through storytelling. Linda’s approach of simple questioning to induce systems thinking in young children and Philip’s use of storytelling to teach more complex systems concepts to older children present a framework for educators and parents. These methods can be instrumental in fostering an early understanding and appreciation of systems thinking, shaping a more aware and connected generation.

Watch the recording below

About the Speakers

Philip Ramsey is the author of the Billibonk and Frankl series, jungle-based fables aimed at teaching children systems thinking through fascinating animal adventures. Phil is a Senior lecturer at Massey University in New Zealand, where he teaches Organizational Learning, Leadership, and Teamwork. He also works as a Director of Incite Learning, a consulting company that mainly works with schools, helping school leaders apply Organizational Learning concepts to solve tough problems.

Dennis Sherwood, a stalwart in the consulting industry, recently presented a webinar that peeled back the curtain on the not-so-glamorous aspect of consulting—client dissatisfaction. With over 20 years under his belt and roles in prestigious firms like Deloitte and Goldman Sachs, Dennis brought a wealth of experience to the discussion, centered around a challenging government project that spanned a decade.

The Struggle for Educational Reform: Dennis dove into the intricacies of a flawed examination grading system he audited, which affected countless students’ futures. Despite his comprehensive analysis and solution-oriented approach, he encountered stiff resistance from the powers that be, illuminating the daunting task consultants often face when their findings and client expectations don’t align.

Advocacy in the Face of Resistance: His unwavering commitment to rectify the grading system, even after being turned away, highlights a consultant’s duty to pursue the truth and advocate for change. Dennis’s call to action rallied lawyers, educators, and policymakers to join the fight for transparency and fairness in education.

The Takeaway: Dennis Sherwood’s “Navigating Client Dissatisfaction” session is a testament to the perseverance needed in consultancy, especially when advocating for societal change against entrenched systems. For those inspired by his dedication, Dennis remains open to dialogue and can be reached for further insight at dennis@silverbulletmachine.com

Watch the recording below

Whoops, this recording is available for members and ticket purchasers only. Please login to verify. If you’re not a member, purchase a membership here. You can also buy a ticket to watch the recording here.

Resources

About the Speaker

We had the opportunity to delve into the world of business model simulations with industry experts Kim Warren, founder of Strategy Dynamics, and Martin Lycko, Customer Success Manager at Silico, this webinar provided invaluable insights into strategic planning and operational management using System Dynamics.

The concept of a “Digital Twin” is a dynamic virtual model of a business or part of a business. The transformative potential of digital twins lies in their capacity to closely mirror actual performance and predict the evolution of broader systemic influences. Lycko highlighted Silico’s role in implementing effective digital twin architectures that can significantly improve organizational performance.

The participants were walked through examples where System Dynamics and digital twins had been leveraged to optimize business performance and drive competitive advantage. These examples underscored the expansive scope and adaptability of these business tools, validating their efficacy and viability.

In a rapidly evolving business landscape, the utilization of System Dynamics and Digital Twins presents a compelling approach to strategy and operational management. This enlightening webinar underscored the importance of these tools in enabling organizations to better understand their systems, optimize their performance, and drive competitive advantage. As we look to the future, it’s clear that these innovative models will play an increasingly vital role in business planning and strategy.

Related Courses

Dynamic Business Modeling

An online course that guides you in creating a quantified, simulated “digital twin” of your business, highlighting inter-dependencies and feedback points.

Society members get a 20% discount

Read More

Strategy Dynamics for Leaders

An online course that will teach you how to build strategic plans with a digital twin of your business or challenge. Based on rock-solid strategy dynamics frameworks, you will have full confidence that your plans and decisions will achieve your performance targets.

Society members get a 20% discount

Read More

Watch the recording below

Whoops, this recording is available for members and ticket purchasers only. Please login to verify. If you’re not a member, purchase a membership here. You can also buy a ticket to watch the recording here.

Resources

About the Speakers

System Dynamics is a powerful approach to understanding complex systems in various fields, such as public health, ecology, and economics. Prof. Jim Duggan, an expert in applying System Dynamics and data science methods to public health, recently hosted a webinar on System Dynamics Modeling with R. In this session, Prof. Duggan provided insights into R’s capabilities for data analysis, visualization, and manipulation, as well as building and running Ordinary Differential Equation (ODE) models. Additionally, he discussed using R’s Shiny framework for creating interactive web apps and the prospect of forming a joint digital science tools group for R and Python users.

Exploring R’s Capabilities

Prof. Duggan showcased R’s potential by introducing packages such as ggplot2 and dplyr for data manipulation and visualization, deSolve for building models, and Tidyverse for data analysis. Moreover, he demonstrated creating interactive web apps using the Shiny package.

Visualizing Data with ggplot2 and GGCloud2

Ggplot2, a library from the Tidyverse, enables users to create graphs in R. Prof. Duggan demonstrated creating scatter plots with different visual properties, such as color, using the ggplot function with specific arguments. He also highlighted GGCloud2 as a flexible visualization tool that adds a fourth dimension to a plot using the facetwrap function.

Tidying Data in R

Prof. Duggan emphasized the importance of tidying data for easier processing in R. He showcased the use of pivot_longer for converting wide data into a tidy data format and dplyr as a powerful package for summarizing data. Techniques like grouping, summarizing, and data transformation can be performed using Tidyverse tools.

Building and Running ODE Models

R can be used to build and run ODE models, as Prof. Duggan demonstrated by defining stocks using vectors and generating models automatically with the deSolve package. He also discussed how Markov Chain Monte Carlo (MCMC) can be used to calibrate data using System Dynamics models, helping to find parameters from a dataset.

Interactive Web Apps with Shiny

Shiny, R’s framework for creating interactive web apps, was another key focus of the webinar. Prof. Duggan explained how Shiny’s reactive programming automatically updates outputs based on input changes, requiring minimal HTML, CSS, and JavaScript knowledge. The server function links inputs to outputs and generates new graphs based on input changes.

Conclusion

Prof. Jim Duggan’s webinar on System Dynamics Modeling with R provided valuable insights into the capabilities of R for data analysis, visualization, manipulation, and ODE model building. The session was an excellent resource for those interested in exploring R’s applications in System Dynamics and data science.

Watch the recording for more!

Watch the recording below

Whoops, this recording is available for members and ticket purchasers only. Please login to verify. If you’re not a member, purchase a membership here. You can also buy a ticket to watch the recording here.

Resources

About the Speakers