GIS as a Data Science Framework
Date: September 17, 2018
Posted by:

Situation Overview

With the world being more interconnected than ever before, maps and geolocation data have become commonplace. Yet, the data on its own isn’t that easy to comprehend unless it is visualized, something that’s made possible via specialized plots. These plots involve maps and enable the end-user to understand the data better and pinpoint potential signals that may exist in the data at hand.

Problems Involved

As the amount of the relevant data for this sort of applications grows exponentially, it is very difficult to process it efficiently, even if the visualization part is fairly straight-forward. After all, the geolocation data starts adding value when combined with other data streams, since on its own it doesn’t reveal that much. As sensor data stemming from IoT devices becomes more readily available, the whole data landscape becomes even more challenging, making the distillation of the corresponding datasets a non-trivial issue.

Implications of Said Problems

As a result, geo-tagged data points carrying various signals related to people or any other entity whose spatial attributes are of value, are too difficult to process properly, especially in cases where optimization needs to take place. The latter is often tied to applications like logistics, though other kind of applications could be used too, such as disaster-relief initiatives (e.g. for the victims of hurricanes) and resource exploration projects (e.g. for figuring out potential oil drilling endeavors).

Proposed Solutions

Geographic Information Systems, or GIS for short, are often employed for this sort of situation, as they provide a practical framework for tackling any data analytics problems involving this kind of data. Even though it’s been traditionally more of a programming endeavor (with Java being the predominant language employed), lately it has become an important factor in the data science realm as the problems related to GIS have grown in scale and complexity. As a result, a modern GIS involves a great deal of modeling with AI oftentimes playing an important role too, mainly due to the large amounts of data involved, particularly when it comes to the optimization aspects of the problems at hand.

Next Steps

Data Science Partnership (DSP) is atop technologies like this one, as well as many other aspects of data science. So, DSP can help you fill that gap of GIS expertise in your organization, by providing you with the right human resources, contract-based or in-house, able to undertake the implementation of such a system. Moreover, its internal consulting team can provide you with guidance in this technologies, while training for both C-level and teams, is also a possibility. Feel free to contact us at to learn more about how DSP can help your organization take advantage of this promising data science framework.

Share with...

Zacharias Voulgaris

Zach is the Chief Technical Officer at Data Science Partnership. He studied Production Engineering and Management at the Technical University of Crete, shifted to Computer Science through a Masters in Information Systems & Technology (City University of London), and then to Data Science through a PhD on Machine Learning (University of London). He has worked at Georgia Tech as a Research Fellow, at an e-marketing startup in Cyprus as an SEO manager, and as a Data Scientist in both Elavon (GA) and G2 (WA). He also was a Program Manager at Microsoft, on a data analytics pipeline for Bing.


Leave a Reply

Your email address will not be published. Required fields are marked *