> For the complete documentation index, see [llms.txt](https://docs.alphageo.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.alphageo.ai/macro-suite/location-dynamism-signals-us-only/net-gravity-score-ngs.md). # Net Gravity Score (NGS) ## Overview AlphaGeo’s **Net Gravity Score (NGS)** is a proprietary census tract-level migration index that measures how strongly a place is positioned to attract or lose residents. By combining three independent layers – structural fundamentals, real-time local sentiment, and spatial spill-over effects – it captures migration pressure in a way that is more timely and realistic than lagging population counts or single-variable proxies. The result is a clearer signal of where local growth or decline may emerge next. NGS helps users understand not just where migration conditions are strong or weak today, but where changing fundamentals, public perception, and proximate location dynamics may begin to reshape population trends, housing demand, and market momentum. The proprietary layers make NGS both diagnostic and explanatory, revealing why people move. ## Our approach The migration literature shows that residential mobility is shaped by the interaction of economic opportunity, affordability, place reputation, and geographic proximity, rather than by any single factor in isolation. NGS translates this multi-causal view of migration into a census tract-level composite score built from three layers: structural conditions, local sentiment, and spatial influence. The final score is defined as:

NGS Score = Structural Score + α · Sentiment Score + β · Spatial Influence

where the structural score captures measurable push and pull conditions within the census tract, sentiment score captures county-level local reputation and momentum, and spatial influence captures the average structural attractiveness of immediate neighboring tracts. The parameters *α* and *β* control the contribution of sentiment and spatial influence to the final composite score. ​Together, these layers produce a census tract-level migration signal that is multi-dimensional, spatially aware, and more responsive to emerging change than conventional migration measures. #### Structural Layer The structural layer is the backbone of the NGS score, split into push and pull factors. Eighteen structural variables in total feed into this layer, chosen after correlation analysis to avoid redundant signaling. This breadth distinguishes NGS from single-metric approaches. The full set of variables is detailed in the table below.
Every push and pull variable rolls up into this one equation, giving each tract a measurable structural score.

Structural Score = Pull Score - Push Score

The structural layer serves as the measurable, data-driven foundation of NGS, providing the statistical base that is then enhanced by the sentiment and spatial layers. #### Sentiment Layer The sentiment layer models how media coverage shapes a location's reputation in real time with respect to economic, safety, climate and other factors. The layer runs in four steps: local news is collected through Google News RSS, scored by a Large Language Model on a -1 to +1 scale, aggregated to a county-level sentiment score, and applied uniformly to all tracts within that county.
The sentiment layer captures momentum and reputation, sometimes ahead of the structural numbers. It is both integrated into the Net Gravity Score (NGS) and available as a *standalone proprietary dataset.* #### Spatial Layer The spatial layer reflects the fact that no census tract moves in isolation. A tract's score is adjusted based on the performance of its immediate neighbors, since growth or decline often spills across tract boundaries. Neighboring-tract influence is calculated as the average structural score of adjacent tracts identified through queen contiguity, then added to the final score using an empirically calibrated spatial weight.
#### National Gravity Score: Combining the Layers The three layers are combined into a single composite Net Gravity Score (NGS) for each census tract. Each layer contributes something distinct: structural gives the measurable fundamentals, sentiment gives real-time perception, and spatial accounts for how growth and decline spill across neighboring areas.
The NGS score is not a black box. Each tract's score can be traced back to its structural drivers, sentiment signal, and spatial context, allowing users to diagnose whether a tract is being pushed down by local conditions, pulled up by attractive features, strengthened by positive sentiment, or influenced by nearby areas. This makes NGS useful not only for ranking places, but also for understanding what is driving each score. ## Product features * **Geographic coverage:** United States * **Spatial unit:** Census Tract * **Model structure:** Structural factors + sentiment + spatial spillover * **Structural inputs:** More than 15 variables across economics, climate, health, education, infrastructure, and investment * **Sentiment source:** County-level sentiment derived from local news coverage * **Date range:** 2026 ## Core outputs The dataset includes five core outputs: * **Net Gravity Score:** Composite gravitational score per tract * **Net Gravity Rank:** Percentile ranking across all tracts * **Structural Score:** Underlying tract-level push-pull score * **Sentiment Score:** Local news-based reputation and momentum signal * **Factor decomposition:** Key drivers behind each tract's push or pull profile ## Interpreting the forecast The key field is **Net Gravity Score** * **Positive values** mean the tract is more likely to attract residents * **Values near zero** mean overall migration conditions are relatively balanced * **Negative values** mean the tract faces stronger out-migration pressure NGS is designed to be unpacked: a tract's score can be traced back to opportunity and investment, affordability or climate strain, sentiment, or the pull of its neighbors. ## Use cases * Market analysis and site selection * Real estate and investment screening * Institutional investment and portfolio risk * Policy and economic development * Within-county equity analysis * Factor decomposition and attribution * Risk monitoring --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.alphageo.ai/macro-suite/location-dynamism-signals-us-only/net-gravity-score-ngs.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.