The increasing availability of location-based data, plus the growing capabilities of AI and ML, provides an optimal opportunity for companies to capitalize on location-based data science for a competitive edge. However, across the board, companies are challenged with finding an effective strategy for organizing, consistently enriching, and analyzing location data across the enterprise – and as a result, are experiencing a wide variety of challenges.
Join this on-demand session to learn how customers are developing data analytics strategies to enable the widespread consumption of location data to solve customer acquisition, customer satisfaction, and network optimization challenges.
3. has never mattered more.
Where to place micro and
macro networks and
rationalizing network
investment
4. Operationalizing
Location Data and
Data Science to Gain a
Competitive Edge in
Telecommunications
4
Are you building in the
right place?
Are you marketing
to and servicing the
right people?
Does your potential
new subscriber qualify
for a given service?
7. Challenges for Data
Science
Massive Scale
• Building Footprints: Availablefor
100M+US properties
• Property Attributes:Across3000US
counties
• People Data:Thousandsof
Demographic Attributes
Unique Data
Types
• Addresses, Lat/Lon,Shapes,Lines,
Formats
• Difficult to join different Formats
and Data Types with
accuracy
• Datatypes mustbe modified tobe
used in
MLalgorithms
Geospatial
Calculations
• ComputationallyIntenseto Join
and Enrich SpatialDataat
Scale
• Enrichingwithroutingandcatchment
is critical,buthighlytime consuming
8. Location data prep slows data science
Forbes, Mar 23, 2016
“Cleaning Big Data: Most Time-Consuming, Least Enjoyable Data Science Task, Survey Says”
3%
60%
19%
9%
4%
5%
What data
scientists spend
the most
time doing
Building data sets
Cleaning and organizing
data
Collecting data sets
Mining data for patterns
Refining algorithms
Other
Data
preparation
accounts for 79%
of the work of data
scientists
9. Messy Data => Time + Risk +
Inefficiency
LocationisComplex:Addresses,Lat/Long,Shapes,Lines,Formats
• Data Scientists are not typicallyused to these data types
• Difficult to join different Formats and DataTypes with accuracy
LackofReliable, Robust 3rdpartydata
• Theavailability and quality of data varies greatly country-to-country
• Timeto evaluatedata is onerous
Rapid Changes in properties,businesses andgeo-characteristics
• Keeping a consistent, updated record is crucialfor business decisions
ComputationallyIntenseto Join and Enrich SpatialDataatScale
• Enrichingand adding variables from spatial data is critical, but highlytime consuming
“For every
minute spent
in organizing,
an hour is
earned.”
-Benjamin Franklin
Inventor, Statesman, Insurer
10. A location-centric approach to MDM
puts network providers in control.
03.
Analyze
Apply Data Science
at scale to gain a
competitive advantage.
02.
Enrich
Leverage trusted ID to join
massive amounts of your own
and 3rd party data sources .
01.
Organize
Assign a trusted ID
that is unique and
persistent to each address.
16. In-depth view of consumers
$£€
Household
Number of people, marital
status
Ages, genders, ethnicities
Health
Education
Home
Housing type and tenure
Location
Mortgage and insurance
Neighborhood
Natural hazards
Telco coverage
Corporate
Customer
Sales and costs
Contacts
Preferences
Pre-defined segmentation
Geodemographic based
Affluence
Lifestyle
Socioeconomic
Economics
Income, disposable
income
Purchasing power
Spend by category
Employment, unemployment
Individual
Name, Age, Income,
Education, Profession
Social Affinities and
Interests
Contact Information
17. In-depth view of businesses
$£€
Business opportunity
Population demographics
Local summary
Consumer segmentation
Local economics
Location
Geocoded
Location name
Accessibility
Neighborhood
Natural hazards
Telco coverage
Corporate
Ownership
Brands
Legal entity
Trading names
Business demographics
Employment count
Years in business
Business type
Business financials
Economics
Income, disposable
income
Purchasing power
Spend by category
Employment, unemployment
There are two reasons for this. The first is technical. The wavelengths that operate as part of the 5G specification, especially in the ultra-dense 30-100GB range, are more attenuated by physical obstructions. As a result. Microcell placement needs closer proximity between devices in order for 5G to deliver on its expected network speeds.
For the millimeter waves in the ultra-dense spectrum, this requires attention to physical realities – building material, distance from cell, knowledge of what people will do with the improved bandwidth, even the weather, as rain can interfere with wave transmission.
You’re going to have more frequent handoffs as a result. And each handoff is a potential lost call or delayed signal.
ABI Research just noted in their Reality Check on the 2019 Mobile World Congress that “everyone” agrees” that antennas are key to successful 5G deployment. In addition, despite some vendor claims that existing base stations can be upgraded to 5G, it’s far more likely still be deployed as an overlay, as existing stations will still be utilized for 4G.
When it comes to getting this all to work, location, knowing where to place a cell and how much bandwidth to supply, will be how Telcos gain a strategic advantage in the new world of 5G.
There’s a shift here between writing in the third person to writing in the second person. Why?
Two reasons: first, it’s useful in challenger to have a tone that isn’t abstracted, and it’s impossible to talk about the state of the industry entirely in the second person. So state of the industry is third person, impact on person being pitched to is second person. Second, it’s a technique called interpellation – it works by describing the subject position that the writer/speaker/salesperson wants the audience to see itself in. The simplest way of doing it is selective use of second person. I don’t recommend it for a blog post, but it works well as a technique for a pitch or keynote (the latter depends somewhat on audience).
As a result, the question of where to place towers and how to structure macro and micro cells, and to assign data, has never mattered more.
The building of infrastructure, like the laying of fiber optic cable, or the placing of 5G cells, will determine signal strength and separate the products and service that matter from those that don’t.
In effect, 5G transforms a tactical issue into a primary strategic concern. If you’re still treating location intelligence as a tactical issue, or as an operational concern, you’re doing 4G thinking in a 5G world.
Every TELCO is going to be making huge investments in infrastructure. You’re going to make those investments. The question is whether you’re going to make the right ones. The answer to that will depend on three things: are you building in the right place, are you marketing to and servicing the right people, and are you properly provisioning the service?
It doesn’t take much to figure out what happens if it goes wrong. You build in the wrong place and a building interferes with your signal, and you lose customers.
You don’t understand your audience and how they use their devices, and as a result you don’t have enough bandwidth in the right spot, or you have too much where you don’t need it. You lose money.
You provision poorly and waste a 200-300 dollars every time you send a crew out to see why a wireless signal isn’t working inside a home as advertised. You lose customers and money—one service call at a time.
Again…the issue with using second person seems accusatory. It’s the wrong tone.
I’m happy to turn this over to the wisdom of the committee. I absolutely understand the concern here. On the other hand, rational drowning is the moment in challenger when it pays to be a bit more confrontational.
If you can take all that information and integrate it together, then you can build a digital twin before you invest in the build-out; you can create a simulation that can validate or modify strategy and inform execution.
You can learn, and adapt, without wasting funds on bad builds or the wrong audience.
[---- Solution / Marketing ----]
That superior understanding of your customers helps you identify who to market these new services to, who can afford them, who wants them, even who thinks they need them. It can target growth in areas or populations in IoT or new streaming services. It can look at city zoning, economic development data, school locations, and so much more.
Data scientists face several key challenges using Location Data that can minimize its usefulness.
Scale: With high resolution images, IoT data, mobile trace data, data sets that involve spatial and spatiotemporal data can easily be in the tera-to-petabyte range, making them challenging to manipulate and extract useful insights from.
Unique and Complex Data Types: Few data scientists have a background in GIS or the data typical of that system and are unused to handling raster or vector data types, dealing with pixels/voxels, or the metadata structures associated. Further, many statistical models and machine learning techniques do not natively understand these data types, and they must be modified for use.
Geospatial Calculations: Routing and catchment data provide and intuitive foundation for planning, however they are compute-intensive operations.
We have off the shelf data (footprints, POIs, boundaries, etc.) available to quickly enrich your addresses. This is enabled by the pbKey feature within MLD and the fact that we have pbKeys on our enrichment data.
Enriched address provide more context and serve as a better starting point for business operations/challenges/analytics/etc. that appear on the right side of this slide.
Device IDs
Signal strength
Predicted coverage
Data consumption by device
Average monthly bill
Competitive fiber
Modeling Project:
Predict where to extend fiber to buildings in an area – here is an aerial view of a county in Texas where a telco is looking to understand the best buildings to connect to their fiber lines.
Add in the existing fiber … [next slide]
And now add in the buildings that the company has already invested in connecting to fiber (fiber lit buildings)
[next slide]
(You’ll see the fiber lit buildings show up in red)
… now we have an overview of all of the assets:
cell towers (signal strength, directionality), homes that are already successfully connected to fiber, as well as existing fiber lines.
For a predictive analytics/data science/ML projects, this information is only useful if it has gone through the correct transformations and formatting.
For this project, we append… [next slide]
Consumer data
Property/other data
Including: distance and routing calculations for each property in the area (lit AND unlit) to the fiber and cell towers
All of these are added as variables/features/columns to the addresses in the area. Now we have TIDY data, in rows and columns, and in the format that we need for modeling!
For the modeling:
In this case, we are training a Neural Network to understand what makes a location “good” by feeding it all of the data and calculated variables from the known fiber lit buildings.
A neural network is comprised of layers of nodes (3 in this case) and learns to map inputs (the building information) to outputs (should we invest in making this a fiber lit building?).
We first reduce the dimensions of the data set by employing recursive feature elimination, whereby only the most relevant columns (variables, characteristics) from the training data (known fiber buildings) are taken as they have the most predictive power in getting to the target value.
We then feed the information through the neural net, and use that trained model to take in new locations and score them based on the network’s prediction of whether this building is likely to be a successful fiber-lit investment. We can then take that information and place it back into a mapping scenario [next slide] …
(Slide from before with just current assets, to reorient viewer)
And we can see that the conservative estimate for which buildings to expand to next is shown in green. This is also a good logical check to the model – by placing the locations back on the map we can get an intuition for what might have been an important factor for the decision to invest in expansion (proximity to fiber, local neighborhood characteristics, building types).
NOTE to PAUL: you can also show the less conservative predictions – they are the next 2 slides, basically just a cost/benefit analysis of “if I increase my investment, where might I go next”, but not really necessary for what you are talking about? Up to you.