OUR INNOVATIONS
At Aretian, we're building a new scientific theory of cities. We bring together cutting-edge techniques in the fields of data analytics, complexity science, and network theory-driven machine learning to produce high-resolution digital models of cities. These models enable us to study cities more closely than ever before - and to share fresh insights with the community leaders who are planning, designing, and developing the cities of tomorrow.
​
We believe in the power of analytical methods to reveal new insights into how cities work. Yet cities are social spaces where people live and work and where politics and private businesses drive change. To capture this richness, we cultivate a team with broad perspectives, ranging from engineering, data science, and architecture to anthropology, public policy, and urban planning.
TECHNOLOGY
Aretian's analytics technologies are the next generation of tools for urban development and design. With advanced data science at the heart of every project, Aretian's technology reveals patterns that traditional methods cannot see.
​
Our technology combines theoretical frameworks from five disciplines:
​
​
COMPLEXITY SCIENCE
Complexity science provides a scientific method for studying the dynamics of complex systems. It helps us understand how many small components of a large system interface with one another, how many individual actions can lead to a collective behavior of the entire system, and how the system builds relationships with its physical environment.
​
NETWORK THEORY
Network theory defines data as nodes and connections to visualize the structure of a complex system. When applied through techniques like combinatorial optimization and statistical analysis, this theory can identify valuable features of a system, such as the optimal location for a component, the nature of the relationships between parts, and how robust or fragile a network is.
​
MACHINE LEARNING
Machine learning is a way of designing algorithms that learn to predict the outputs of a system through iterative data processing. By comparing baseline conditions in different cities, this type of modeling enables us to reliably identify the expected outcomes of a design intervention and accelerate our understanding of urban systems.
​
AGENT BASED MODELING
Agent based modeling is a type of bottom-up analysis that models behavior at the individual level to shed light on the complex system dynamics that emerge over time. In our human-centered design work, agent based modeling allows us to discover the nature of inter-dependencies between individuals and components of a system and identify the governing equations that describe global patterns.
SYSTEM DYNAMICS MODELING
System dynamic modeling uses mathematical equations to model the behavior flows of a system. This kind of modeling enables us to test the practical limits of the dynamics that govern a system and help us understand the non-linear effects of feedback loops that can either balance or destabilize the entire system. We use this kind of scenario analysis to pressure test potential solutions.