RESEARCH & RESOURCES

Going Geo: Augmenting BI with Geospatial Intelligence

Geospatial analytics can boost operational efficiencies, open up new revenue opportunities, improve marketing campaigns, and help with fraud and abuse detection.

Why incorporate geospatial analytics into your business intelligence (BI) practice?

The most obvious -- if insufficient -- answer is: why not? If you're a large organization, after all, you probably already have geographic information systems (GIS) software from Esri, Google Inc., or other providers.

There's a lot more to it, argues David Loshin, a principal with consultancy Knowledge Integrity Inc. Loshin recently addressed the question of geospatial analytics and location intelligence as part of TDWI's "Checklist Report" series.

Loshin's report, Using Location Information for Geospatial Analytics, argues that geospatial analytics can help boost operational efficiencies, open up new revenue opportunities, improve the effectiveness of marketing campaigns, and help with fraud and abuse detection, among other benefits.

"Aside from the typical addition of residential and work addresses to a customer's record, customer profiles can be significantly enhanced using analytical results in two ways," he writes, referring to the idea of using location-dependent characteristics to enhance the overall customer experience, and to the practice of determining location-dependent customer behaviors.

In the first case, Loshin argues, a customer's behaviors -- such as preferred retail location or the locations from which mobile calls originate -- can provide clues to preferences. "These enhancements can be incorporated within a master customer profile so that operational interactions can be optimized to the customer's benefit," Loshin points out.

His second example involves analyzing a customer's location-dependent behaviors with an eye to identifying "geodemographic" characteristics. These characteristics can "help streamline marketing and sales and increase revenues ... [by] customizing Web page offer placements based on general geodemographic customer preferences."

Loshin's report doesn't just make the case for "going geo;" it offers a rapid-fire primer on how to develop the infrastructure and processes required to support geospatial analytics. Although "going geo" can be accomplished in several ways, the most straightforward approach involves using GPS devices -- such as smartphones -- to append geocodes to stored data.

This is far from a silver bullet, Loshin cautions.

"Using GPS-enabled devices [like smartphones] is straightforward, as they automatically generate geocodes in association with events, and those geocodes can be linked directly to stored data," he writes. "Although this method is gaining traction, it cannot be used for the volumes of data that have already been collected and stored in corporate data sets."

The alternative is to enrich existing data with location information. This is a much trickier proposition, Loshin concedes. "This requires more planning, as existing data may not map to any defined standards for address or location information. This suggests a need for location data quality services." Services of this kind typically involve three stages, he explains: first, address parsing and standardization; second, data cleansing and enhancement (in which missing attributes -- such as ZIP codes -- are filled in); and "reverse geocoding," in which "delivery addresses are mapped to geocodes containing latitude and longitude information."

Loshin's complete report also explores the value of linking map-based views to charts, visualizations, and other artifacts. "[I]n an interactive setting, the presentation of geospatial analytical results can be fully integrated with other approaches for visualizing and manipulating analytical results," he writes, stressing that "maps are not just for representing geography. A merchandiser might view a map of a retail store's floor plan with analytic information laid over it representing sales, profitability, and circulation data. Based on the data, the merchandiser can move products and shelves in an effort to raise sales."

Data visualization specialist Bis2 Inc. uses just this approach with its Super Graphics visualizations. Bis2's VizExplorer software is used by several casino properties -- including the Silverton Casino Hotel in Las Vegas -- to study gaming behaviors, identify "hot" and "cold" areas of the casino floor (along with "hot" and "cold" machines), and optimize casino operations.

Loshin's complete report can be downloaded here.

TDWI Membership

Get immediate access to training discounts, video library, BI Teams, Skills, Budget Report, and more

Individual, Student, & Team memberships available.