Marketing a new product or service is getting more complex
every year with the proliferation of digital channels, shrinking
attention span for consumers and businesses alike and lack
of trust in all direct advertising messages. Marketing
professionals estimated that over 26% of the marketing
budget would be lost as a result of poor strategic planning
and/or incorrect channel focus.
Cost of developing new products and services escalates every
year, with each new drug costing the pharmaceutical industry
over 2.6 Billion US dollars. Marketing to the hubs of influence
works very well - 92% of the marketers who used influencer
marketing found it effective. Influencer marketing shows up in
all spheres of life from buying a Coach purse for your
daughter because her favorite YouTube personality carries it
or switching to a new cholesterol or blood pressure
management drug because your trusted cardiologist
recommended it over the current one due to higher efficacy.
The main challenge for the marketers is finding these hubs of
influence, understanding the community attached to each hub
and prioritizing the marketing activities to effectively launch
the new product or service through the hubs.
Traditional Solutions Are missing the Mark
Finding hubs of influence on the social media channels (Instagram,
YouTube, Twitter, Facebook etc.) is well understood and there are a
plethora of tools that can identify the hubs, characterize the
communities or audience attached to each hub and rate the relative
value of each community for consumer product marketing.
more complex products such as new pharmaceutical drugs (for e.g.
PCSK9 inhibitor cholesterol drug), equipment (for e.g. higher
resolution X-Ray or MRI) or healthcare treatments (for e.g. TAVR,
the minimally invasive heart valve replacement treatment),
identifying hubs of influencers among physicians and other
healthcare providers requires deep analysis of patient claims data
to uncover the referral relationships. Traditional analytics solutions
built on relational databases require expensive joins among large
tables containing prescriber, claims and patient data. It can take
hours, sometimes days to complete the database joins and that
makes traditional analytics solutions unsuitable for this type of
Why TigerGraph, a Native Parallel Graph Database for Product & Service Marketing?
Uncover Referral Relationships with Deep Link Analytics
Uncovering referral relationships is a lot easier in
Tigergraph, as the patient, prescriber and claims data is
pre-connected in the graph database. Consider the
example, where Dr. Douglas Thomas, a general
practitioner sees a patient, p1003 on Sept 8, 2017, for shortness of breath symptom resulting in the claim
c10005. The same patient, p1003 sees Dr. Helen Su, an
interventional cardiologist (surgeon) on Sept 20 for
Cardiac Catheterization or Angiography (claim c10030)
and again on Sept 23 for the Angioplasty operation
TigerGraph visually shows all of these
claims connected with the patient and the prescribers in
the GraphStudio so that data analysts can understand
the relationship intuitively.
TigerGraph also links them based on a time window to
deduce referral relationship. In this example, the claims
occurring within four weeks are considered for
establishing a referral relationship. It takes four hops or
steps for traversing from the referring physician, Dr.
Douglas Thomas to the referred physician, Dr. Helen Su
via relevant claims identifying 3 common patients, p1003,
p1004 and p1005 over the month of August and
September. A referral edge or relationship is established
between Dr. Douglas Thomas and Dr. Helen Su and the
relationship edge carries important information such as
the number of patients referred, healthcare condition
groups related to the referred patients. The prescription
claim data can be added in, to provide specific drugs for
Cardiac care that are frequently prescribed by both
physicians. Armed with these insights, pharmaceutical
companies producing the cardiac care medication and
the medical equipment manufacturers producing
stents and other products for the cardiac surgery can
market those products to Dr. Douglas Thomas and his
referral network including Dr. Helen Su for the San
Jose healthcare market.
Ranking the Influence by Hubs with Graph Algorithms
After establishing the referral relationships among
influencers or trusted product or service providers (such
as prescribers or doctors in case of pharmaceutical and
healthcare industry), next step involves identifying the
most influential hubs driving most activity such as
healthcare claims for a specific condition such as cardiac
care or diabetes management). Graph algorithm,
PageRank is often used for this purpose. Consider the
example, where Dr. Douglas Thomas, the general
practitioner is driving referrals for cardiac care issues to
three surgeons - Dr. Helen Su, Dr.
Rick Summers, Dr.
Zane Adams and two cardiologists - Dr. Henry Chang
and Dr. Neil Patel. Dr. Don Kirk is another physician in
the area, driving referrals to two surgeons - Dr. Helen Su
& Dr. Rick Summers and one cardiologist - Dr. Larry Ko.
Graph Algorithm, PageRank creates a unique ranking for
each physician and Dr. Douglas Thomas with the
PageRank of 3.9 is the most influential physician driving
referrals for cardiac care in the area. Dr. Don Kirk is the
second most influential physician with PageRank of 2.5.
Community Detection Around the Most Influential Hubs
After identifying and ranking the hubs for their influence with
PageRank, the final step in the product and service marketing
driven by influencers is to identify the community around each hub and evaluate the market opportunity to determine the
relative importance of each community. TigerGraph’s open
source graph algorithm library includes the community
detection algorithm to identify communities around each hub.
Consider the example where there are three communities of
connected prescribers and patients identified for East San
Jose for treating cardiovascular disease and providing
preventive care with medicines to manage hypertension.
Community id 70163044 is for Dr. Douglas Thomas, Dr. Don
Kirk, and their referral physician network and their patients.
TigerGraph’s high performance SQL-like graph query
language, GSQL is used to aggregate the spend across all
claims for the community that is related to the cardiovascular
disease, along with insurance payouts as well as the out of
pocket cost for patients. Total spend along with insurance
payouts and out of pocket cost is calculated for the
hypertension medication prescriptions. Armed with these
insights, pharmaceutical companies producing the
hypertension medication and the medical equipment
manufacturers producing stents and other products
for the cardiac surgery can prioritize visits to the most
influential hubs in communities with the maximum
spend on those products or services in the east San
Jose healthcare market. This delivers the new
innovations in medicine as well as healthcare
instruments and procedures to the community that is
likely to benefit most from it while delivering maximum
revenue uplift for the producers of these products and