UNIT CODE: GGI 4202

UNIT NAME: SPATIAL BUSINESS

Lecture 01
Introduction
Administrative issues
 Course Assessment
◼ Continuous assessment
 Assignment(s) 5%
 Test(s) 15% 30%
 Practical 10%
◼ Final Exam
 Question 1 30% (Compulsory)
70%
 Q2-Q6 20% Each (Any 2)
◼ Pass mark (40%)
 Teaching style
◼ Set of lectures
◼ Few practical sessions

2
Course Objectives
 Provide students with a good understanding of Spatial Business
Intelligence
 Course Expectations
 Understand the basic concepts and theories of GIScience and
trends of GIS technologies
 Create and manage spatially-enabled business data.
 Use appropriate GIS analysis functions to visualize and analyze
business-related data
 Model business processes using GIS’ advanced analytical
methods
 Design and implement spatially enabled business intelligence
applications

3
Course Outline & References
 Provided

4
Introduction
 Our ability to exploit the massive amounts of complex, disparate data will
never be resolved by the traditional technology we introduce or the common
techniques we attempt to implement.
 Pie charts and other typical graphics fall short of supporting better decision
making.
 There is a growing realization that by adding geographic location to business
data, organizations can dramatically enhance their insights into tabular data
 This context can immediately help users discover new understandings and
more effectively communicate and collaborate using maps as a common
language.
 This geographic aspect has been largely absent from business analytics
solutions, many organizations would like to incorporate it into their
operations.
 This convergence has allowed businesses to transform location data into
valuable insights, solving various use cases such as maximizing store network
efficiency, performing sales forecasts and selecting sites with the right
location characteristics to support a sustainable expansion strategy
5
Introduction
 Our current systems handle the who, what and when, but the where is vastly
underexploited.
 Spatial Business Intelligence is interdisciplinary and comes from the
intersection of three different fields—Business Intelligence, Artificial
Intelligence and Geographic Information Systems technology
 It is an interactive technology that allows you to generate real-time maps and
visualizations, so that you can filter data and see only what matters.
 This makes it easier for one to detect patterns and trends which relate to
your business needs, making your strategic decisions more effective
 Effective BI, therefore, is dependent on the following two capabilities
 Visualization. Interrelationships, specifically those based on geographic data, that might
otherwise be difficult to describe or explain, are often readily understood when visually
presented.
 Spatial Data. Typical BI systems handle the who, what and when, but the where is vastly
underexploited.2 Spatial data, the where of BI, does two things.
 Spatial Business intelligence is guided by the following patterns.

6
Introduction

 Visualization:
 Interact proactively with many different sources of data at once and visualize your results at
any time.
 Having information displayed in an easy-to-visualize way means that you can make decisions
quickly and easily, without having to cipher through files and lists of information
 Analytics
 Use advanced statistical analysis with big data and machine learning techniques to
understand what was previously hidden.
 This information improves your understanding of the environment and its influencers, so
you can make justified business decisions.
 Data
 Gain access to multiple sources of data (e.g. demographic, number of competitors, footfall
traffic…).
 Geoenrichment is a fundamental factor when developing a business strategy; having the
detailed information to target your market is essential to your performance. 7
Introduction: Definitions of terms
 Location intelligence/spatial intelligence
 Process of deriving meaningful insight from geospatial data relationships to solve a
particular problem, it involves layering multiple data sets spatially and/or chronologically,
for easy reference on a map.
 LI tools are designed to turn data into insight for a host of business purposes, such tools
draw on a variety of data sources, such as geographic information systems (GIS), aerial
maps, demographic information and, in some cases, an organization's own database.
 It is the collection and analysis of many sources of geospatial data that are transformed into
strategic insights to solve a variety of business challenges.
 Business Analytics (BA)
 Is the iterative or methodical exploration of an organization's data, with an emphasis on
statistical analysis. It is used by companies that are committed to making data-driven
decisions.
 Data-driven companies treat their data as a corporate asset and actively look for ways to
turn it into a competitive advantage.
 Specific types of business analytics include:
 Descriptive analytics, which tracks key performance indicators (KPIs) to understand
the present state of a business;
 Predictive analytics, which analyzes trend data to assess the likelihood of future
outcomes; and
 Prescriptive analytics, which uses past performance to generate recommendations
about how to handle similar situations in the future
8
Introduction: Definitions of terms
 Differences between BI and BA

 Spatial Business Intelligence:

9
Introduction: Definitions of terms
 Data analytics
 Is the science of analyzing raw data in order to make conclusions about that information.
 Many of the techniques and processes of data analytics have been automated into
mechanical processes and algorithms that work over raw data for human consumption.
 Data analytics techniques can reveal trends and metrics that would otherwise be lost in the
mass of information.
 This information can then be used to optimize processes to increase the overall efficiency of
a business or system.
 The process involved in data analysis involves several different steps
 Determine the data requirements or how the data is grouped.
 Data may be separated by age, demographic, income, or gender. Data values
may be numerical or be divided by category.
 Data Collection, this can be done through a variety of sources such as computers,
online sources, cameras, environmental sources, or through personnel.
 Data organization: the collected data must be organized so it can be analyzed.
 This organization may take place on a spreadsheet or other form of software
that can take statistical data.
 Data cleaning. This means it is scrubbed and checked to ensure there is no duplication
or error, and that it is not incomplete.
 This step helps correct any errors before it goes on to a data analyst to be
analyzed.
10
Introduction: Definitions of terms

 Application Areas
 Energy:
 Spatial analytics is enabling the energy industry to discover patterns and uncover
hidden insights in seconds rather than minutes or hours.
 Transport and logistics companies:
 Be it determining the fastest transportation routes, enabling effective forecasting,
optimizing warehousing processes and stock flows based on the consumption rates of
particular products by locality.
 Real estate and commercial developments:
 Real estate is all about location because of the people served by that location.
 Spatial analytics facilitates research, analysis, and presentation of each prospective
site. It helps in determining optimum sites for development
11
Introduction: Application Areas
 Telecommunications:
 Spatial analytics enables the industry to assess strength of the current infrastructure,
analyze competitor network coverage etc.
 Understanding which locations will provide the best network coverage at the lowest price
possible helps the industry function more effectively.
 Retail and wholesale industry:
 Along with physical store-level detail, spatial analysis is helping the industry to gain
invaluable insights in stock delivery, store management, inventory management, marketing
and sales.
 Healthcare providers:
 Healthcare providers use spatial analytics to see issues from a locational perspective,
leading to more efficient practices and higher standards of patient care.
 Insurance companies:
 Spatial analytics of location-based data, such as crime rates, weather patterns etc. is
enabling insurers to identify high or low risk cases and develop marketing strategies,
policies and pricing models accordingly.
 Finance and banking sector:
 Location data and analytics of customers help banks to carry out effective customer
segmentation and profiling, develop more successful marketing and sales campaigns, tailor
products and services according to the customer base within each region or division and
identify and actively retain and pursue profitable customers.
12
Introduction: Application Areas
 Airports and airlines:
 Airlines use spatial analytics to track flight operations more closely and accurately.
 Airport, meteorological, and fleet data is monitored in real time, and the operations crew
reroute flight paths to optimize fuel and staff costs.
 Education:
 Adding geographical components to student data enable higher education institutions to
develop more effective marketing campaigns, understand better where to put facilities, and
work on research grants..

13