How Can Location Intelligence Help Identify Affordable Housing Development Opportunities

The real estate adage “location, location, location” is as relevant today as it has ever been, encapsulating the essence of what makes a property valuable. Traditionally, the real estate market has leaned heavily on local knowledge to decipher urban patterns, historical trends, and the subtle distinctions between neighborhoods and their surrounding environments. This method, while grounded in time-honored practices, often faces challenges to grasp broader market dynamics, conduct extensive comparisons and identify hidden market potentials.

In the realm of affordable housing, the identification of development opportunities has largely been guided by policy-driven initiatives and practical considerations. Without a clear comparison across larger geography, many affordable housing projects may not align with the best interests of those they are intended to serve.

Location intelligence has the advantage of collectively analyzing these patterns and opportunities at a much larger scale, due to the availability of abundant and diverse spatial data. According to Carto, “Location Intelligence is the methodology of deriving insights from location data to answer spatial questions.” With this wealth of data at our fingertips, we can now try to ask and answer the spatial questions – Where are the most suitable sites for affordable housing development? And how can we identify them with location intelligence?

Before diving into details, it’s crucial to note that underlying this technical exploration is a broader dialogue about incorporating values and policy choices into machine learning models to balance fairness and efficiency. Location intelligence should be seen as an advisory presence, rather than the one to dictate decisions.

More is More: Layering Up Information

In an era where data is more abundant than ever, the challenge often lies not in obtaining data, but in identifying which data is most pertinent to our goals. This is especially true in the context of affordable housing development, where the right data can illuminate the most viable opportunities for creating impactful, sustainable housing solutions. For affordable housing development, several key data types are critical in evaluating the potential of a location within both its built environment and social context.

Neighborhood Characteristics

Socioeconomic Indicators: Data from sources such as the American Community Survey provide invaluable insights into income, poverty, education, age demographics, and household types. Other data sources cover features such as business footprints that help depict a multifaceted picture of a neighborhood. This information is crucial for identifying areas where affordable housing is most needed, ensuring that development efforts are both strategic and impactful.

Housing Characteristics: Attributes like building types and available amenities play a significant role in determining a location’s suitability for affordable housing projects. These characteristics help developers understand the existing housing stock and identify gaps that new developments could fill.

Built Environment and Public Space: Characteristics of the built environment, including its walkability, green spaces, and urban canopy coverage, contribute significantly to its desirability and sustainability. These factors not only affect the quality of life and cost of living for potential residents but also the long-term viability of housing solutions.


Amenities Proximity: The accessibility of essential services such as schools, grocery stores, healthcare facilities, and parking directly impacts the quality of life for residents. Proximity to these amenities is a key consideration in the planning of affordable housing.

Transportation Access: Efficient, reliable access to public transport is a cornerstone of sustainable urban development, enabling residents to connect with employment, education, and other critical services.

Temporal Correlation

Development Trajectory: Analyzing how a community changes over time adds a dynamic layer to our understanding of neighborhood characteristics. By examining trends in socioeconomic indicators, housing characteristics, and built environment factors, developers can forecast future scenarios and plan accordingly.

Historical Outcomes: Historical data on affordable housing developments, such as the Low-Income Housing Tax Credit and other programs, provides a foundation for analyzing past outcomes and refining future strategies.


Advertisements and Comments: The use of natural language processing to analyze advertising language and online commentary, such as on platforms like Zillow, offers insights into public perceptions of housing and neighborhoods. This data can reveal public perceptions, preferences and biases that may influence the desirability of certain areas for affordable housing.

Policies and Regulations: Zoning laws and regulations, including those that promote or require affordable housing (like inclusionary zoning in New York City), have a profound impact on development decisions. Understanding these legal frameworks is essential for navigating the complexities of affordable housing development.

Less is More: Distilling Information

Based on these data, multiple statistical models enable deeper understandings of complex data, guiding the strategic planning and execution of housing initiatives with precision and foresight.

Predictive Models

Predictive models, most commonly refer to regression models, are at the forefront of leveraging historical data to forecast future trends in real estate and urban development. By analyzing patterns in demographic shifts, housing demand, economic trends, and environmental changes, these models can predict where affordable housing will be most needed in the future. For example, predictive models can identify potential gentrification areas, enabling interventions that preserve affordability for existing residents while accommodating new development.

Decision Making Models

Models like decision trees and random forests can help streamline decision-making in affordable housing development. Decision trees break complex choices into simpler, binary options, aiding in assessing factors like location and cost. Random forests, built by aggregating multiple decision trees, enhance prediction reliability and handle complex datasets effectively. This approach enables more strategic, data-driven decisions, identifying prime locations and predicting demand for affordable housing, thereby optimizing development strategies with precision.

Clustering Algorithms

Clustering algorithms efficiently helps identify patterns and similarities in large datasets, highlighting potential affordable housing sites by grouping areas with common features like socioeconomic status, accessibility, and infrastructure. This method optimizes resource allocation and planning, pinpointing areas with high potential for impact and identifying underserved communities to ensure equitable distribution of affordable housing

Utilization: Location Intelligence on the Rise

Affordable housing has long been a critical field for public private partnership. Policymakers and urban planners are tasked with steering and encouraging equitable and efficient affordable housing development to effectively deliver it to vulnerable populations. Similarly, developers, whether driven by profit or not, must grasp the available incentives and market dynamics to ensure their projects are financially sustainable over the long term. Thus, identifying optimal sites for these projects is essential, as it directly influences their success and sustainability.

In the public sector, these advanced analytical tools offer policymakers a robust framework for understanding the intricate dynamics of urban development and housing needs. By identifying patterns and trends in housing demand, socioeconomic shifts, and urban growth, policymakers can make data-driven decisions that promote the sustainability and accessibility of affordable housing. For instance, the use of scoring systems implemented in Charlotte, NC enables authorities to evaluate and prioritize projects based on a comprehensive set of criteria including proximity, accessibility, change, and diversity. By layering up these spatial data, the system helps to ensure that developments align with broader urban planning goals and meet the community’s needs.

In the private sector, commercial real estate developers and consulting firms have consistently utilized market data to pinpoint trends and uncover hidden spatial and locational values. Capital Markets Quants, created by Jones Lang LaSalle (JLL), synthesizes data from more than 1.25 million property transactions across various countries spanning the last two decades. This platform aims to forecast future space demand, spotlight development opportunities, and refine portfolio management. As both a public good and a real estate product, affordable housing can benefit from these proven location intelligence tools. By integrating additional layers of data, these models can be fine-tuned to prioritize social benefits alongside economic viability, ensuring that affordable housing projects meet both market and community needs effectively.

Data is powerful and insightful. Utilizing location intelligence to identify areas with potential for affordable housing development is an exploratory approach that leverages data to spot patterns, forecast trends, and unearth opportunities. Unlike unsupervised machine learning, this method is highly guided by human decisions aiming at achieving a balance between equitability, efficiency, and sustainability. The pursuit of affordable housing is challenging and prolonged, hopefully, location intelligence is offering a new approach to clear the way forward.


This content is part of Econsult Solutions’ thought leadership initiative, ESI Center for the Future of Cities, which brings together experts in urban economics, policy, and strategy to craft new evidence-based research on the most important issues facing cities around the world, and to provide consulting services for public and private sector organizations working in urban settings.


Yihan Zhang, Analyst | [email protected]

Yihan Zhang is an analyst at ESI. She graduated from the University of Pennsylvania in 2023 with a Master’s in City Planning with a concentration in Public and Private Development. Yihan’s interest lies in understanding the public and private forces behind urban development, especially in housing and redevelopment projects. Her previous work experience includes housing policy research, urban design, market analysis and software programming for sustainability analysis.


Share This