Use Cases

Any questions? Feel completely free to contact us

Spatial Data Analytics

Spatial Analytics as a Key Component in Data Products

Modern algorithmic spatial analytics is a relatively new field, though spatial analysis itself has a long history dating back to disease mapping circa 1854. Spatial analytics is now a key component in most data products, whether it’s location-based services or creating strategies mixing offline and online channels. Current implementations of spatial analytics relies on software that can access and merge both internal and external data, integrate specialized algorithms capable of building robust models, and being able to easily include spatial analytics in existing workflows.

Spatial and Geographic Data Analysis

Of particular interest is the ability to analyze geographic data. The number of applications using geographic data is rising rapidly and will continue to become more popular as technology improves. For example, shopping destinations use touch-screen kiosks that recognize your current location and, when prompted, provide the most expedient route to a retail destination based on variable & conditional factors. In another example, geovisualization uses spatial analytics and digital cartography to enable humans to perform geographic data mining in a three and four-dimensional space. As people continue to correlate spatial areas with data, spatial analytics methodologies will continue to play a significant role in data products for years to come.

Using DSS to Discover and Leverage Spatial Analytics Methodologies

Data Science Studio (DSS) is a powerful analytics platform that recognizes the importance of using spatial technology and content in your analytics projects. Some key spatial analytics features in DSS include:

  • Access to Dedicated Geo-Processors: Quickly access dedicated geo-processors when wrangling your data, such as GeoIP, geometric area extraction or centroids, and geo-joins. In addition, Shapefiles can be directly integrated into your workflow.
  • Automatically Generated Maps: Automate calls to geocoding APIs to normalize and augment your data and leverage the best open source technologies in one common platform, such as spatial extensions for databases (Postgis) and specialized R or Python packages/functions. You can even build a map with no code!
  • Visualization: After the data has been cleansed and the models are built, maps can be automatically generated from datasets. DSS is capable of creating rich visualizations that can include both on or offline data. With spatial analytics as a component, your visualizations can take on an even greater sense of utility while facilitating a proactive user experience. Visualized maps are not only fueled by complex data, but are capable of engaging with users via interactive elements, such as slide bars and color-coded filtering (for an example, check out the geographic visualisations in this blog post about student loans in the United States).

In addition to map building, your models can be used to develop your own advanced spatial Web-based applications. Leverage the power of spatial analytics to build out Web applications that are highly accessible, based on real-time data, and engage with your users.