note: This article is by Dr Sambit Sahu, a manager
and senior research scientist at the IBM
His current research focuses on Cloud and Big Data analytics for Telco and Smarter Cities.
service providers are rich in Big
Data, especially those that offer telephony, TV and Internet services –
better known as the triple play. Telcos want to monetize that data but it's
extremely challenging to derive meaningful, actionable analytics due to the
complexities of correlation, prediction, and the massive volumes of different
this need I, along with other data scientists at IBM Research, am exploring
ways to perform these complex analytics, so that telcos can get new customer
insights that they can turn into new business models and services.
going to demonstrate this analytics tech at Mobile
World Congress in Barcelona,
a lot of information at their fingertips: the kind of programming customers
watch and subscribe to, when they watch, as well as location and movement data
that are embedded in transaction data records and signaling information between
devices and towers.
all of this data is noisy. In order to correlate space-and-time data
successfully, we're using sophisticated machine learning and data mining-based
spatio-temporal analytics to make sense of different data sources -- including
an enhanced profile of a customer that could predict what their behavior might
be in the future.
location unlocks the ability to build context about a customer's current
location and also correlate it with information already known about the
customer. For example, understanding context can infer intent: will this
customer like this brand; make a trip out of town soon; buy tickets to a
specific sporting event; take public transport versus a car trip? Add to this,
knowledge of a customer’s social media network usage, and you can build a near-360 degree picture of him or her and predict future
team is putting these analytics to work in two use cases.
Mobile World Congress Demo
IBM will demo a use
case at Mobile World Congress, showcasing how to create targeted IPTV
adver-tisements campaigns based on enriched customer profiles. The solution
uses advanced analytics algorithms to correlate & analyze IPTV channel
viewing history, location & movement data, and web browsing information
to better understand customer's preferences, lifestyle, predicted locations
and in turn match a viewer with the most relevant campaigns.
the first, the analytics platform is being used to create targeted Internet
Protocol Television (IPTV) advertisements based on a customer's profile. So, instead of every TV watcher
seeing the same ad at the same time, during the same program, opt-in
participants would see tailored advertisements that best match their profiles.
Even individual family members would see different advertising based on knowing
who is at home via cell phone location data, in conjunction with what
programming they’re watching and their specific profile attributes.
use case, seeks to explore hyper-local targeted advertisements that will be
delivered to mobile phones. In this use case, targeted advertisements and
coupons will be delivered to a customer based on a better understanding of
their profile, as well as current and predicted locations.
customer who follows a certain celebrity on Facebook who recently launched a
new fragrance. And the customer is also determined to be a fashion-forward
consumer, based on IPTV viewing. The analytics platform will now predict when
this customer is going shopping at a local mall, and offer a promotion on the
celebrity’s fragrance sold by a cosmetics store in the mall. More importantly,
by predicting the customer’s location, the offer is not sent based on current
location – when often times it’s too late to act on an offer.
this analytics platform can form a foundation of meaningful and enriched
profiles about their customers that in turn allows them to offer more
personalized programming and services, while also creating new business
opportunities and innovative services built around a variety of location-based
you’re watching your favorite sport you might be grateful to see a timely
commercial that helps you book a resort for that ski trip you’ve just been
Labels: analytics, big data, mobile world congress, telco