Validate your Big Data Business use case before you implement

One of the key best practice for successful implementation of Big Data Analytics solution is to validate the business use case for Big Data. It will help organization with 2 important aspects for successful implementation:

1. Keeping the scope limited to help work with limited data set within Big data context

2. Help measure the success of solution that address key business problem

In case the same data set addresses multiple use cases, organization may need to prioritize their use case and apply iterative and phased approach. It’s the theory of getting biggest bang for the buck, tactical and strategic.

While there are extensive industry specific use cases, here are some of the use cases for handy reference.

Retail/Consumer Use Cases

  • Merchandizing and market basket analysis.
  • Campaign management and customer loyalty programs.
  • Supply-chain management and analytics.
  • Event- and behavior-based targeting.
  • Market and consumer segmentations

Financial Services Use Cases

  • Compliance and regulatory reporting
  • Risk analysis and management
  • Fraud detection and security analytics
  • CRM and customer loyalty programs
  • Credit risk, scoring and analysis
  • High speed Arbitrage trading
  • Trade surveillance
  • Abnormal trading pattern analysis

Web & Digital Media Services Use Cases

  • Large-scale clickstream analytics
  • Ad targeting, analysis, forecasting and optimization
  • Abuse and click-fraud prevention
  • Social graph analysis and profile segmentation
  • Campaign management and loyalty programs

Health & Life Sciences Use Cases

  • Clinical Trials Data Analysis
  • Disease Pattern Analysis
  • Campaign and sales program optimization
  • Patient care quality and program analysis
  • Medical Device and Pharma Supply-chain management
  • Drug discovery and development analysis

Telecommunications Use Cases

  • Revenue assurance and price optimization
  • Customer churn prevention
  • Campaign management and customer loyalty
  • Call Detail Record (CDR) analysis
  • Network performance and optimization
  • Mobile User Location analysis

Government Use Cases

  • Fraud detection
  • Threat detection
  • Cybersecurity
  • Compliance and regulatory analysis

New Application Use Cases

  • Online Dating
  • Social Gaming

Fraud Use-Cases

  • Credit and debit payment card fraud;
  • Deposit account fraud;
  • Technical fraud and bad debt;
  • Healthcare fraud;
  • Medicaid and Medicare fraud;
  • Property and Casualty (P&C) insurance fraud,
  • Workers’ compensation fraud.

E-Commerce Use-Cases

  • Cross-Channel Analytics
  • Event Analytics
  • Recommendation Engines using Predictive Analytics
  • Right Offer at the Right time
  • Next Best Offer or Next Best Action (Ebay, Netflix, Amazon and Others)

Big Data Use-Cases in Healthcare – Provider, Payer and Care Management

In this part, we will discuss use cases specific to Healthcare industry. In general, Healthcare industry has been late adopter of technology compared to other industry verticals – Banking and Finance, Retail and Insurance. As per McKinsey report on Big Data June 2011, “…if US health care could use big data creatively and effectively to drive efficiency and quality, we estimate that the potential value from data in the sector could be more than $300 billion in value every year, two-thirds of which would be in the form of reducing national health care expenditures by about 8 percent…”.

Some of the key use cases for Provider industry are:

a. Reduce Medicaid Re-admissions – One of the major cost of Medicaid is readmission costs due to lack of sufficient follow ups and proactive engagement with patients. These follow-up appointments and tests are often only documented as free-text in patients’ hospital discharge summaries and notes. These unstructured data can be mined using text analytics and timely alerts can be sent, appointments can be scheduled, education materials can be dispatched. This proactive engagement can potentially reduce readmission rates by over 30%.

b. Patient Monitoring – Inpatient, Out-Patient, Emergency Visits, Intensive Care Units…

With rapid progress in technology, sensors are embedded in your weighing scales, glucose devices, wheel chairs, patient beds, XRay machines. All these large streams of data generated in real-time can provide real insights into patient health and behavior. This will improve the accuracy of information and significantly reduce the cost of healthcare providers. It will also significantly enhance patient experience at healthcare facility by providing proactive risk monitoring, improved quality of care and personalized attention. Big Data can enable CEP – complex event processing providing real-time insights to doctors and nurses in control room.

c. Preventive care for ACO

One of the key ACO goals is to provide preventive care to its members. The Disease identification and Risk Stratification will be very crucial business function. Managing real-time feeds coming in from HIE from Pharmacists, Providers and Payers will be key information to apply risk stratification and predictive modeling techniques. In the past, companies were limited to historical claims and HRA/Survey data but with HIE, the whole dynamic to data availability for health analytics has changed. Big Data tools can significantly enhance the speed of processing and data mining.

d. Provider Sentiment Analysis 

With social media growing at rapid pace, members are sharing their experience about providers through social channels – Facebook, Twitter, and other media. These experiences through comments, twitter feeds, blogs, surveys can be mined for gaining rich insights about quality of services.

e. Epidemiology

Through HIE, most of the providers, payers and pharmacists will be connected through network in few months to come. These will allow hospitals and health agencies to track disease outbreaks, patterns and trends in health issues across geography allowing determination of source and containment plans.

f. Patient care quality and program analysis

Natural with growth of data and insight into new information, comes the challenge to process these voluminous and variety of information to produce metrics and KPIs for Patient care quality and program. Big data provides the architecture, tools and techniques that will allow to process TB and Petabytes of data to provide deep health care analytics capabilities to its stakeholders.

Some of the key use cases for Payer industryare

a. Clinical Data analysis for improved predictable outcomes

Payer/Health Plans and Insurance companies can significantly reduce cost of care by reducing readmission, improved outcomes and proactive patient monitoring. There is a huge amount of existing clinical data that resides within organization and myriads of unstructured data coming at rapid space, Big data will be candidate to process these complex events and data to provide clinical insights to payer organization. Some of the areas that can be immediately addressed by Big data solutions:

  • Longitudinal analysis of care across patients and diagnoses; time sequencing
  • Cluster Analysis around influencers on treatment, physicians, therapist; patient social relationships
  • Analyze clinical notes (multi-structured data); no longer limited by dimensional sentiment of a relational database
  • Analyze click stream data and clinical outcomes; look for patterns/ trends to quality of care delivered.
  • Clinical outcomes can be integrated with financial information to understand performance

b. Claims Fraud Detection

Although no precise dollar amount can be determined, some authorities contend that insurance fraud constitutes a $100-billion-a-year problem. The United States Government Accountability Office (GAO) estimates that $1 out of every $7 spent on Medicare is lost to fraud. Some of the fraud examples are:

  • Billing for services, procedures, and/or supplies that were not provided.
  • Misrepresentation of what was provided; when it was provided; the condition or diagnosis; the charges involved; and/or the identity of the provider recipient.
  • Providing unnecessary services or ordering unnecessary tests
  • Billing separately for procedures that normally are covered by a single fee.
  • Charging more than once for the same service.
  • Upcoding: Charging for a more complex service than was performed. This usually involves billing for longer or more complex office visits
  • Miscoding: Using a code number that does not apply to the procedure.
  • Kickbacks: Receiving payment or other benefit for making a referral.

With Health Information Exchanges playing a pivotal role in real-time information sharing, Payer organization will have the power of information to proactively detect frauds using Pattern Analysis, Graph Analysis of cohort networks, social media insights.

c. Member Engagement

Like any industry, Payer organization like Health Insurance companies are battling to win member business. Companies are monitoring members, prospects behavior on their websites and social media.

d. Payer Sentiment Analysis 

Similar to Provider sentiment analysis, members are sharing their experience about insurance benefits, customer service experience through social channels – Facebook, Twitter, and other media. These experiences through comments, twitter feeds, blogs, surveys can be mined for gaining rich insights to improve quality of services.

e. Call Center Analysis

Payer organizations are capturing information from Call Center using call recording. These call records provide valuable information to

  • staffing model – by demographic preferences, hours of services
  • member feedback using voice pattern and recognition
  • member experience using metrics – Average speed to answer, abandonment rate, dropped calls, unable to reach member

Finally, few of the use cases for Care Management – Disease Management, Utilization Management and Behavioral Health Management industry are:

a. Disease Identification and Risk Stratification

Care management companies constantly collect data from various sources – claims, prior authorizations, biometrics screening, health risk assessment and survey data. Disease ID and Risk Stratification is key function that helps organization with limited resources to focus on top 5-10% of high risk population that takes 60-80% of medical cost. Processing through 10′s of years of historical information added with realtime information from various sources adds a huge complexity and processing challenges. Big data can alleviate such challenges by not only providing accessibility to  unstructured data but also providing the robustness and speed of processing.

b. Member Sentiment Analysis 

With social media growing at rapid pace, members are sharing their experience about providers through social channels – Facebook, Twitter, and other media. These experiences through comments, twitter feeds, blogs, surveys can be mined for gaining rich insights about quality of services.

c. Member care quality and program analysis

Natural with growth of data and insight into new information, comes the challenge to process these voluminous and variety of information to produce metrics and KPIs for Member care quality and program. Big data provides the architecture, tools and techniques that will allow to process TB and Petabytes of data to provide deep health care analytics capabilities to its stakeholders.

While these are just few of the generic use cases in Healthcare industry, there are a lot of unique use cases specific to your line of business, organization and department. I will reiterate again that assessing and prioritizing the business use case for Big data based on value is key to its success and will have significant impact on your organization in years to come. Think Big, start Small!