Bridging the Gap: Integrating Bottom-up and Top-down Modelling for Enhanced Predictive Performance in Complex Systems


In the ever-evolving field of data science, the ability to build accurate and robust models that can effectively capture the complexity of real-world systems is crucial for informed decision-making. Two primary approaches, bottom-up and top-down modelling, offer unique advantages and challenges when attempting to understand and predict the behaviour of complex systems such as supply chain networks or ecological systems. This presentation will review these two modelling paradigms and explore innovative methods for combining them, ultimately leading to more powerful data-driven insights.

The session will commence with an overview of the bottom-up and top-down modelling approaches, highlighting their respective strengths and limitations in various data science applications. Attendees will learn how bottom-up modelling focuses on individual components and their interactions, such as modelling individual customer demand in a supply chain, while top-down modelling emphasises the high-level relationships between components to provide a broader perspective, like analysing the overall market trends affecting the supply chain.

Next, we will delve into several strategies for integrating bottom-up and top-down modelling, such as hierarchical modelling, hybrid modelling, and multi-model integration. Attendees will be introduced to practical examples that demonstrate the value of combining these approaches in different data science scenarios.

By attending this presentation, data scientists will gain a deeper understanding of both bottom-up and top-down modelling techniques and learn how to effectively leverage their combined power for improved predictions, increased robustness, and enhanced generalisation. Participants will leave equipped with the knowledge and tools that can unlock new possibilities for understanding complex systems, leading to more meaningful insights from their data.


Gustavo is the esteemed Vice President of Research at Vortexa Ltd., where he has focused on applying statistical modelling and Machine Learning to the energy and freight markets. His research interests span computational neuroscience, medical imaging, and the development of innovative solutions for the energy sector.

Prior to his tenure at Vortexa, Gustavo amassed a wealth of experience in both the academic and professional realms. He has published his research in prestigious international journals and presented his findings at scientific conferences across the globe. Gustavo's dedication to finding optimal solutions for complex business problems is evident in his work.

Gustavo holds an SB and MEng in Computer Science and Electrical Engineering from the Massachusetts Institute of Technology (MIT) and a PhD from the University of Tokyo. As an expert in his field, Gustavo brings a depth of knowledge and experience to ODSC, where attendees can expect to learn from his invaluable insights.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google