Story of Neighborhoods

Market Opportunity for Neighborhood Services

The Factle Map Co. plans to build a neighborhood data set for enterprise service companies. The initial goal is market neighborhood map data of 15,000 neighborhoods for the largest 250 US cities with the street level accuracy (1-meter resolution). The firm’s core competency is its expertise in neighborhood data acquisition for which the founder has three patents pending. By producing a high-quality data -- which it is hoped to be adapted by major companies including the largest search engine firms (Google, Yahoo, and Microsoft) and the top real estate companies -- the firm’s Neighborhood Map Project wants to set an industry standard that would be difficult to dislodge by competitor.

Neighborhood map production was originally undertaken by Bernt Wahl and a team of 15 paid interns (mostly UC Berkeley students) who worked with advisers in the Summer of 2005. As the need for neighborhood mapping expanded the project, sought starting in late 2005, the assistance of a GIS expert in the University of Malaya, Richard Dorall, and who in early 2006 guided 9 interns, all of them graduates in Geography from the University of Malaya, to improve on the spatial accuracy, and to expand the city and metropolitan area coverage, of the original neighborhoods data set developed by the UC Berkeley-based team.

Market Needs

Today companies are using server science technology to better target customers and enhance services. One effective method is to target specific customers based on demographic information. This trend is expected to triple by the end of the decade. It is expected that about 30% of Internet search will be based on local content. One method to find a user’s location is to map an IP Address to a specific region or location. This accuracy however is limited; it is dependent on the ISP’s ability to pinpoint a user.

Internet technology allows consumers to easily access information enabling them to become more sophisticated shoppers. Market driven service companies can gain considerable insights into customers by observing their online shopping patterns. One emerging phenomenon is the demand by consumers for more targeted data that can provide relevant focused information. In many market segments the Internet is replacing traditional storefront service business with transaction sites. In web markets, service providers are beginning to offer increased personalization by targeting consumers’ specific interests for desired services. To target more effectively location based services, providers need more granular data, that can be organized in a meaningfully way, that can direct consumers to specific locations. 

Current demographic data is based on census data groupings. For instance, home and real estate information are segmented by city, zip code or census block groups. Census block groups are based population fixed-quantity units that vary in sizes from individual city blocks to large tracts of rural land.  Arbitrarily combining census block units severely diminishes the potential benefit of attribute consistency and trends within the grouping. This limitation is also found in zip code divisions, dependent on the length of mail delivery routes. 

Neighborhood datasets can provide a meaningful granularity for understanding locally correlated attributes, and are a significant improvement over the current system of granular units.  Neighborhood data intelligently identify groups that identify with each other, providing partitions that embody the strong associations between neighbors as well as the consistency of demographics within neighborhoods.  With the more granular and localized data, consumers will be able to obtain content that is more meaningful to them.  For example, they will be able to locate the nearest coffee shop, the school district which their house belongs to or the crime rate within their neighborhood within seconds.  As for the businesses, besides providing useful content to their customers, as in the case with online real estate markets and search markets, they will also be able to use the data to identify the lifestyle and consumer behavior characteristics of their best customers, and then find more people just like them and reach everyone with the highest impact at the lowest cost.  Identifying and targeting specific customer groups can help businesses minimize unnecessary advertising costs and make more efficient decisions.

Neighborhood Demographic Data

Public Health: Diseases can be tracked and clustered by neighborhoods. Health agencies looking to create local branches can use this as a starting point to strategically place sites that will be most effective and cost efficient. Researchers may also be able to deduce more information about illnesses if they are provided information regarding the original source of the disease and population information for those particular neighborhoods.

Crime Statistics: Criminal incidents can be tracked and grouped thus reflecting the level of safety within a neighborhood. Law enforcement agencies will be able to more effectively distribute its resources to areas with higher chance of criminal activity. 

Politics: Applications such as neighborhood targeted polling can be achieved. Political campaigns can be presented more effectively to communities that are interested as opposed to general spamming to a mixed audience. This technology will create an automated system to select districts by neighborhoods and reduce gerrymandering of political boundaries.

Demographics Research: Changes over time of different neighborhoods will allow analysts to predict future trends and gain valuable marketing data. Corporations can track their consumer performance and strategically target areas that have high interest in their product or service. Location based advertising and population growth data are only a few examples of what these demographics can offer.