Detecting Fraud With An Insurance Data Warehouse

We all pay for the cost of crime, and preventing it is much more appealing for insurers than accounting for it after the fact. Insurance losses related to crime and abuse are factored into companies’ rates as a cost of doing business.

Relatively few instances of fraud affect the balance of the companies’ customers. Insurers have implemented sophisticated and powerful computer systems to try to accurately identify the losses as soon as possible after they happen, and factor them into their rates through timely accounting of the losses of those few.

Recovery of the losses after the fact does not happen as quickly as the loss itself, since new rates must cycle through the natural course of business as new policies occur and old ones are renewed; and you don’t just add in the real costs; they have to be factored into the rates carefully, after considering competitive and shareholder concerns as well. Powerful actuarial resources are in place to forecast and predict the necessary reserves to protect the insurer against these few potential losses from crime and abuse. This is really a form of accounting for crime that is expected to happen. What about preventing it before it happens? A recent study revealed that 10-15 percent of insurance premiums fund the North American $40 billion insurance fraud tab, not including the accompanying investigation expenses and legal fees.

Fraudulent claims are not only very expensive; they are also one of the most frustrating and aggravating elements of the insurance industry. Conventional wisdom in the industry states that 10 to 20 percent of all indemnity is fraudulent. The percentage of claims, which are detected or denied ranges from 1 to 5 percent, suggesting improvements are to be gained. This gain heads straight for the profit line of the insurer’s balance sheet. For many of the major insurers this gain means millions to hundreds of millions of profit not being pursued. Even a small improvement of a few percentage points is significant, and the potential for improvement is much greater.

Reducing or controlling this significant amount is worthy of proactive investment by insurers. Just as public law enforcement agencies continually search for tools and techniques to help them prevent crime, Special Investigative or Security Units of insurers can also use a helping hand. Tools are important, and the raw material is under their noses. In addition to currently available external industry claims databases, insurers have a very powerful resource within their own computer data centers, their own operating data.

For many insurers, fraud investigation is handled in a responsive and reactive manner.  When claims administrators are suspicious of a claim, they inform their supervisor. The supervisor reviews the information, and if the supervisor feels the claim warrants investigation, it is forwarded to the SIU or Security Unit, The investigative/security unit reviews the information to determine whether to accept the claim for investigation. The investigators have at their disposal specialized investigative techniques and artificial intelligence software products to perform their research.

However, this inspection is focused on specific individual cases or on a small number of claims. Any proactive initiative is completely dependent on the experience or inquisitiveness of the person initially processing the claim(s). Fraudulent intentions are difficult to detect on individual basis, unless blatant. Trending insights are not available. Dormant exposures are not visible, Abusive patterns are not obvious.

On the other hand, timely and easy access to enterprise operational data, which is integrated and complete, will enable the fight against fraud to be powerful and more effective. An Insurance Data Warehouse, which contains organized detailed historical data, will provide fraud fighters with a very powerful weapon.

Uncovering fraudulent claims requires extensive data gathering and analysis. Often the information is difficult and time-consuming to obtain. It has to be manipulated into an environment that accommodates an analytical process – a data warehouse. Further, the information is time sensitive in many cases, and there is the need to acquire it in an efficient manner. There needs to be sensitivity to the confidentiality of the data collection process, and this is difficult in the environment currently in place in most organizations.

Finally, the investigation & security staff has a requirement to ask their questions and receive answers in a timely manner, while they are in the midst of a certain thought process. It is a heuristic process. Answers lead to more questions, and so on. How can a data warehouse help fight fraudulent claims or exposures? The ability to identify or detect an investigative path and to follow this path is a primary benefit. Let’s explore some examples.

Automobile Insurance:

As automobile insurance premiums represent over $9OB in the United States, insurance fraud is a particular problem for auto insurers. Fraudulent claims present themselves in various forms like:

  • The staged accident
  • Paper property
  • The inflated claim
  • Multiple coverage for the same vehicle
  • The disguised claim

The current reaction capability of investigators limits them to pursuing after the fact or evaluating the situation in isolation. The ability to apply the lessons and profiles gained from other policies is very difficult or nonexistent. However, with an integrated data warehouse which is easily accessible, easy to use, and flexible enough for ad-hoc querying, fraud investigators can activate a proactive approach to combating these costly claims through earlier identification and prevention. Such a data warehouse would typically contain:

  • Complete policy data of all policies (active and inactive) in one common database
  • Complete claims details (active and closed) for 36 to 60 months
  • Sales agent compensation
  • Industry enhancement data

In a recent exercise, a major P&C insurer gained an ability to explore its own data integrated in such a data warehouse. In the first step, the insurance professionals were asked to produce a list of policyholders who made claims over a particular amount within the last two years in a specific State. Then, the investigators asked for the results to be grouped by Vehicle Identification Number (VIN). What they observed was alarming to them; there were multiple situations, several thousand vehicles, where multiple active policies were covering a common VIN. Armed with such information, the insurers’ SIU went into action and ultimately saved the insurer millions of dollars in repossessed claims or unnecessary exposures.

Then the investigators looked for claims for recently insured high-priced vehicles involved in rear-end collisions with older vehicles, a favorite scenario for staged accidents. As well, they uncovered several cases where they had paid a loss for stolen, non-recovered cars, which were now insured by another of their companies, in some cases by the original owner.

With such an integrated data warehouse, this exercise was completed in half a day where previously it was impossible or required weeks of efforts involving SIU and information technology resources. In this way the company took a major leap forward, from rationalizing buried rate increases, to cutting their losses and increasing their competitive edge. This project, which cost almost nothing, was completed in months and returned millions within a matter of one month of utilization.

Insurers have experts on claims processing and experts on the investigation of fraud, but no experts on the detection of fraud in this sense. Investigative expertise and experience combined with flexible and timely access to enterprise wide operating detail arm insurers with proactive fraud fighting capability. A rapidly constructed enterprise insurance data warehouse will provide insurers with a proactive ability to keep claims costs down for a strategic ability to price their products more profitably and competitively. This same data warehouse can also service other needs of insurers, like product development and target marketing for even stronger market position.

FAQ – Data View: what is a Data View?

An end-user client asked, “What’s a data view?”.

“It’s like an Ipod playlist for databases”, I said.

Just as you can listen to all of your music or group selections for different listening preferences, you can do the same with data elements you may need for different purposes.

Each grouping of data is called a Data View

FAQ – How do I send Harold questions?

Please ask your questions by an email or comment. If you know me just call. I’ll also post my answers within one or more FAQ subcategories, which can be searched within this site.

I’m happy to answer any question about (to list a few):

  • Business Intelligence
  • Customer Relationship Management
  • Data Architecture and Design
  • Data Integration, ETL, and Design
  • Data & Data Quality
  • Data Mining
  • Data Marts
  • Data Models – Conceptual, Logical, Physical, Semantic, Dimensional
  • Data Warehousing
  • Information Architecture and Design
  • Master Data Management and Data Governance
  • Organization Roles & Responsibilities
  • Projects and Plans
  • Relational Concepts and Databases
  • Techniques, Templates, and Tools

FAQ – Categories: Why is a new Post Category not listed on my Blog page?

Categories may be created at the Parent (main) level or as a subordinate to one or more Parents (Child Level).

A Category will only be displayed in the Category list when one or more postings are linked to the Category.

Monday Morning Marketing

Imagine a time when all the computer power you need for high performance , direct Multi-Channel  Marketing is in place; a powerful database computer; three years’ worth of high quality detailed customer and transaction data extracted from several operational systems – scrubbed, matched, and consistent; workstations configured with the latest software tools for customer behavior analysis and visualization; networks established connecting your desktop directly to the data you need for spontaneous assessment and decision-making.

It’s Monday morning, the system is turned on – go.

What exactly would you do on Monday morning when the system is turned on for you? If your answer is simply “Direct Marketing” and/or “Database Marketing” it will be very difficult for you to justify the cost of the new system, or demonstrate an ROI within a reasonable time-frame.

Just as buying a new car requires you to decide where you drive it, and how you want to use it, the same is true for the acquisition of any Direct Marketing technologies. You must define how you will use them, and for what specific purposes.

Information Technology (IT) departments are expected to deliver the day’s operational data processing requirements and now they are faced with an ever-growing problem of fitting in a long list of demands for time-intensive information processing.

Data processing requirements can be clearly defined in advance because they are predictable, mirroring day-to-day business processes. Changes to data processing requirements are identified, planned, and implemented. Data processing operations are tightly scheduled and controlled.

Information processing requirements on the other hand, are much more impromptu and spontaneous. They don’t necessarily mirror the business operation and they are very difficult to predict in advance. Information processing is highly dependent on both the data, and the experience of the person who looks at it.

Information processing requirements are highly variable and are difficult to implement with conventional data processing techniques and technologies. To do so imposes severe limitations on the value of the data and the effectiveness of one’s decision-making process.

For example, it is very common when designing a new application system to include the design of several reports. In effect, the IT department asks you to define then what you want to see in the future. When you finally receive what you thought you wanted, the report is less than effective for most of the problems you want to solve. It is this problem most managers face now.

If instead, the IT department understood you how you will use the data, they would better prepare and organize it to give you the flexibility to access it and visualize it in any way appropriate – on-demand.

For direct multi-channel spontaneous database marketing, or any analytical use of databases for decision support purposes, it is critically important to accurately define how the database will be used – so you can establish a specific decision support undertaking which has value, can be accomplished quickly, and can be measured.

Define and Assess Specific Initiatives

Many projects that identify the cost of a direct Multi-Channel Marketing system are unable to quantify and predict its true value. Without a definition of specific needs, it is not possible to quantify a business case or outline the actual data requirements. Since the IT department doesn’t really know exactly what data you need to solve specific problems, they try to give it all to you. As you can imagine, providing all the data in an easily accessible form requires something new – a data warehouse.

Without specific needs defined for how the system will be used that first Monday morning, the technology acquisition for a data warehouse environment may be excessive compared to the actual ROI; it may take longer than necessary to implement and benefit, or it may not meet the end-users’ expectations since too much data can be overwhelming to deal with.

An Information Architect trained to identify and qualify business and user requirements for Decision Support and Business Intelligence applications like Direct Multi-Channel Database Marketing, can facilitate a working session to develop, elicit and express clear, tangible requirements.

These requirements are related to information needs which can be supported by data which already exists within current operational systems. The session will also confirm the value (by initiative) of an effective and focused decision support information warehouse.

This kind of program is designed to assist groups in quickly and collectively assessing and identifying specific business initiatives.

Business Case Development

A facilitated program such as this, focuses on building a business case for the listed business initiatives; a business case based on reduced costs and increased revenues, enabled by eliminating time spent in data collection and reconciliation, improving the decision-making process, or targeting the right customers or products for specific promotions.

Facilitated Workshop with Users

A focused one day workshop identifies a prioritized list of issues, assumptions, values, and initiatives affecting any area of interest. The information gathered in the session is solicited through group interactions and forms the basis for a laying out a road map which is produced to document the session and communicate recommendations and action items.

This first critical step, has not only proved to be the most effective way to evaluate program ideas and business initiatives, it has also been identified to be the most important factor used by organizations to accelerate the shift to a new way of doing business and evaluating results.

In the commercial and even the public sector environment a variety of initiatives could be undertaken immediately which would result in a near-term pay back, and these are identified and appraised during the facilitated workshop.

Data Requirements

Many projects focus on providing all the data to all the users without considering its use. It is imperative however, to associate specific data with the business initiatives to be undertaken. The data has to be available and may need to be transformed into a useful and flexible state. The value of the data has to be defined otherwise there is no need to store it. The value has to be measurable so benefit of its use can be accurately measured and determined and adjustments can be made.

Goal Oriented

It has been my experience that plans which are undertaken to implement a generalized direct marketing database facility often do not deliver the expected value compared to the committed investment.

On the other hand, an evolutionary approach which implements only those portions of the database needed for specific planned initiatives can be accomplished very quickly and will consistently deliver measurable results to your business units that surpass the projected benefits. Companies often use a portion of the incremental revenues from their initial programs to fund the extensions to their systems.


Examples of the benefits achieved by others using a program of facilitated workshops for example, are

  • Financial Returns or cost reductions accelerated – dramatic improvement in approval time-frames for policy and marketing program decisions
  • Accurate identification of problems and opportunities – shift in the focus from reporting an event to understanding the event
  • Confidence in decision-making – political and economic basis determined for product reforms from actual experience to-date, thus avoiding discrepancies between actual and system-reported values in management reporting
  • More rapid consensus of opinions – avoidance of organizational information conflicts due to elimination of multiple and inconsistent data
  • Focused goals with measurement objectives – effective analysis of objective and outcome planning
  • Dramatic reduction in measurement effort – to consolidate and refine data for analysis and planning
  • Consolidation and consistency for Security – fraud detection
  • Consistency for reporting – consolidation all related sources of detailed data for pre-defined and ad hoc queries – both simple and complex
  • Demographic and Psychographic analysis – development of profiles, and identification of individual customers and their transactions, combination, and patterns of use; definition of programs based on actual lifestyle, and demographic information

Contributors and Time frame

The facilitated workshop is a focused session which is led by an experienced facilitator. As well, industry consultants may supplement your group of business contributors. In order to maintain its focus on near-term, high valued solutions to current business issues and opportunities, representatives from your IT department should also participate. Their role is to comment on the availability of data required by the proposed solutions.

A session can be conducted within one day, followed by the review, approval, and publication of the group’s findings, recommendations and action plans.

Success through 3 Stages

A facilitated workshop is the first of a three stage process for realizing an identified business initiative into production.

Stage 2 focuses on implementing a pilot project. The scope of the pilot involves processes for data collection, data management, system management and information delivery. The focus is on specific business initiatives, identified by the initial workshop, with measured rates of return. The pilot is utilized by a core group of end-users to test the effectiveness of the business initiatives and the application of the data warehouse. This develops a high degree of end-user confidence leading to self-sufficiency for data access. Effectively, the first implementation should be focused enough to be completed within 90 days.

Stage 3 focuses on implementing a full production solution. At this point there is collective business user and business management buy-in. The business initiative will have been fully tested, and most significantly, the organization will be fully aware of the benefits.

Stage 1
  • Facilitated Workshop
  • Business case for initiatives
  • Data identification
Stage 2
  • Pilot project
Stage 3
  • Implementation into production

With this approach, when that first Monday morning finally does roll around and the system is turned on, you’ll know exactly what it is you are going to do, how you will benefit, and how to measure the benefit. Most important is the self-confidence you will have to use the system in new and creative ways to improve the way you do business.

Information Architect

People ask what I do, and the answer varies depending whether I’m at a party, on an elevator, or flying cross-country. (Don’t worry if you’re next to me on a plane … 95% of the time I say I’m a Contract Computer Guy and fall asleep.)

I’m actually an Information Architect, and depending on the need of an assignment, sometimes I actually get hired to do that job.

An Information Architect is a senior role in an organization, integrating views of

  • customer/client data management, and account servicing,
  • product management,
  • territory management,
  • consolidated Management Reporting, and
  • Corporate communication

across all lines of Business; facilitating consistent, accurate and unified management information – for discovery, analysis, presentation, communication, collaboration, and reporting for internal and external purposes.

The Information Architect creates and maintains the Enterprise Information Architecture, and communicates the Information Architecture in the context of where business processes create or use various classes of data and how Information is shared.

This enables an organization to better leverage information to deliver business value, improve operational efficiency, promote transparency and provide business insight.

The Information Architect facilitates the definition of data ownership (responsibility and accountability for information and data quality), and its attribution to the business as well as gaining agreement on Enterprise wide common definitions for key indicative and demographic data elements (name, address, metrics and key performance indicators, etc.). This work leads to reference data standards enterprise-wide.

The role requires with a broad range of architectural, technological and organizational experience and often influences business transition programs. The Information Architect provides working project guidance for tactical design decisions, as well as overall design and data standards. This is a conceptual and high level design role. The Information Architect functions as a member of a multidisciplinary team and is not responsible for program plans or working on an isolated individual assignment.

Vision – The Information Architect needs to be able to have an end-to-end vision, and to see how a conceptual design will translate into one or more functioning systems; how the Data will flow through the successive stages involved. He (or she) needs to understand the importance of Data Governance, including Master Data Management, Meta Data, and Data Dictionaries.

Turning Information Anxiety to Information Advantage™

A previous assignment was completed at month-end December 2008, and while looking for a new one, I discovered many potential clients were actually doing well during the very rough times of Q1 2009. They were pushing ahead below the media radar, while others obviously had issues. The funny thing is, whether doing well or struggling with business, people were struggling through the media blitz, suffering from …. information anxiety!!!

I came up with a new personal theme that year of 2009, and since then have been leading a drive, related to what I’ve been doing for more than 30-years … and decided to give it a name,

Turning Information Anxiety to Information Advantage™ !!!

Information anxiety afflicts personal, corporate, and public endeavors and crosses all borders and boundaries. While there’s no magic pill for information anxiety, there are many ways to quickly alleviate the symptoms, then permanently resolve problems that fuel it. Stamping out information anxiety is my current obsession as a Data and Information Architect.

I wish you all the best …. and when you suspect you, a loved-one, friend, or colleague is suffering from information anxiety, whether from personal angles, access to data, corporate or competitive information or other forms, please let me know. I’m available now and onward to help you and/or your colleagues.