Sie sind auf Seite 1von 8

IBM Software White Paper

Insurance

Harnessing the power of big data for insurance

Harnessing the power of big data for insurance

Data is the lifeblood of the insurance industry. To design products, assess risks, set policy prices, protect against fraud and ensure sufficient capital reserves, insurance companies collect extensive data on claims, transactions, demographics, channel usage, geo-location and more. Today, the volume, variety and velocity of data available to insurance companies are increasing rapidly. Social media posts, real-time weather feeds, blogs and customer emails can augment traditional data sources. Like identifying and assembling pieces of a puzzle, accumulating more data even if the veracity of some of it remains uncertaincan help speed the process of finding answers. But insurance companies can capitalize on all this data only if they are well prepared to accommodate unstructured and streaming data from a wide range of internal and external sources. Big datawhich spans traditional and nontraditional data sourcesoffers substantial opportunities for insurance companies. For example, agents can use insights drawn from big data to determine the next best action to retain valued customers and maximize cross- and up-sell opportunities with real-time, personalized offers. Claims analysts and underwriters can run streaming and identity analytics to quickly flag fraud risks and fast-track legitimate claims. Actuaries can improve catastrophe risk modeling, applying analytics to trillions of records to improve pricing and limits while reducing exposure. Big data is becoming an important natural resource for insurance companies. If they can simplify the discovery, extraction and refinement of big data, they can empower users to easily run queries and generate new insights that help transform the business.

Determining the next best action


What if insurance companies could simultaneously improve customer satisfaction, retain valuable policyholders and maximize cross- and up-sell opportunities? To achieve these goals, insurance companies need ways to anticipate customer needs and determine the next best action for each individual customer. Analyzing customer actions or tracking important life events enable a company to offer new types of policies or new levels of coverage that match a customers current or future needs. This allows insurers to create a truly personalized, customer-centric interaction uniquely designed for each individual. For example, a company could offer a discount on bundled auto insurance as a policyholders child nears driving age or recommend a convertible life insurance policy after discovering that the policyholder has been comparing types of policies online. Highly targeted offers can be automatically delivered via any channel, such as mail, email or the web, or provided to agents in real time at the point of customer interaction. Creating personalized offers helps improve customer sentiment and increase profitability as well. Solutions for big data help insurance companies identify the next best action for customers. With the right technologies, companies can extract, integrate and analyze a large volume and variety of data in structured and unstructured formats, ranging from call-center notes and voice recordings to web chats and social media. Through that analysis, they can identify the most valuable customers and better understand their preferences.

IBM Software

Companies can utilize predictive analytics to determine the likelihood that a customer will move to a competitor, and then identify the next best action to retain the customer. Reporting capabilities from business intelligence (BI) solutions can present the targeted offer that the customer is most likely to accept. The insurance organization can deliver the offer in real time, through the most effective channel.

Improving claims fraud detection


Solutions for analyzing big data can play a critical role in addressing the increasing prevalence of claims fraud. Traditionally, fraud is estimated to account for approximately 10 percent of insurance company losses,1 and that percentage is rising. Insurance companies need ways to quickly identify potential fraudulent claims, enhance the efficiency of investigations and prosecutions, and facilitate rapid reporting and visualization to improve ongoing antifraud efforts. At the underwriting stage, insurance companies can employ solutions for big data that scrutinize applicant identities by searching and analyzing large volumes of information rapidly. Companies can determine whether applicantsand people associated with those applicantshave been linked to fraud in the past. Through a review process, companies can avoid fraud by denying applications for disability, health, homeowner or automobile policies with high fraud risks. During claims intake, companies can use solutions designed to collect and analyze streaming data, such as social media posts or geospatial data, to inform investigations and policy decisions. This streaming data can help insurers discover, for example, whether policyholders are being honest about accident details or if services rendered are legitimate. Predictive analytics solutions can help categorize risk and deliver fraud propensity scores to claim intake specialists in real time so they can adjust their line of questioning and route suspicious claims to investigators. For ongoing analysis of fraudulent claims and their impact on the business, companies can use solutions to analyze, report and create visualizations of data patterns.

Increasing cross- and up-sell opportunities with improved segmentation After several years of rapid growth, a large Korean nonlife insurer wanted to boost revenues by improving its competitive position. The company needed to enhance the effectiveness of its large, distributed network of affiliated agents by providing them with the insights and tools to identify opportunities and implement more targeted and relevant cross-selling offers. The company deployed a comprehensive customersegmentation and market-targeting solution built on IBM technology. By applying analytics and predictive modeling to customer account data and transaction histories, the solution enables agents to conduct segmentation based on the probability customers will adopt complementary or higher-value insurance services. By analyzing customers consumption of services, the company can optimize cross-selling strategies, fine-tune marketing messages and deliver targeted offerings. The insurer can more accurately predict which insurance products are the most appropriate for each customer. Offering the right mix of services improves the effectiveness and efficiency of the companys sales force, while the more personalized touch helps agents forge closer bonds with customers, which enhances loyalty.

Harnessing the power of big data for insurance

Enhancing catastrophe risk modeling


Identifying insurance fraud with big data analytics The Insurance Bureau of Canada (IBC) is the national insurance industry association representing Canadas home, car and business insurers. Because investigation of cases of suspected automobile insurance fraud often took several years, the companys investigative services division wanted to accelerate its process. The IBC worked with IBM to conduct a proof of concept (POC) that explored new ways to increase the efficiency of fraud identification. The POC showed how IBM solutions for big data can help identify suspect individuals and flag suspicious claims. IBM solutions also help users visualize relationships and linkages to increase the accuracy and speed of discovering potential fraud. In the POC, more than 233,000 claims from six years were analyzed. The IBM solutions identified more than 2,000 suspected fraudulent claims with a value of CAD41 million. IBM and the IBC estimate that these solutions could save the Ontario automobile insurance industry approximately CAD200 million per year. To learn more about the IBC POC with IBM, visit: ibm.com/software/success/cssdb.nsf/CS/JHUN-8Y4J5A

Analytics solutions designed to handle the volume and variety of data available today also help insurance companies improve catastrophe risk modeling, through which companies determine the exposure of current policies and predict the probable maximum loss (PML) from a catastrophic event. Catastrophe risk modeling is vital for setting policy prices and ensuring there are sufficient reserves available to pay future claims. Solutions designed specifically for big data can help insurance companies accelerate the speed and increase the precision of catastrophe risk modeling. In the past, actuaries were restricted by the inability to run frequent, fast models. Now, companies can use solutions for big data to integrate historical event data, policy conditions, exposure data and reinsurance information. With a powerful data warehouse built for big data, they can analyze trillions of data rows and rapidly deliver results that underwriters can use to price policies by street address, proximity to fire stations or other granular parameters, rather than simply by city or state. A big dataenabled solution allows pricing models to be updated more often than a few times a year, and specific risk analysis can be determined in minutes rather than hours. A solution built to analyze streaming data enables companies to capture and analyze real-time weather and disaster data that might affect losses. Predictive modeling solutions can help companies anticipate those losses before disasters strike or as events unfold. Insurers gain the ability to model losses at the policy level, calculating the effect of a new policy on the portfolio while it is being quoted.

IBM Software

Addressing big data challenges with the IBM big data platform
Before realizing the benefits of big data, many companies must overcome technical hurdles. They need solutions that integrate, cleanse and analyze a large volume and variety of dataincluding both the structured data from claims and online transactions, and the unstructured data from customer correspondence, agent notes and voicemails. They need solutions that analyze streaming datafrom social media posts to weather feedsto quickly gauge customer preferences, discover fraudulent activity and prepare for a flood of claims. Solutions for big data must enable insurance companies to apply predictive analytics to large data volumes, run ad hoc queries and visualize patterns efficiently. The IBM big data platform is a broad portfolio of solutions and capabilities that can help insurance companies determine the next best action for customers, improve fraud detection, enhance catastrophe risk modeling and more. The platformbased approach allows companies to start with one capability and add others as demands change. Integration with existing systems makes it simple for insurance companies to quickly benefit from analyzing big data while working with traditional data sources. Platform capabilities are pre-integrated with one another and with associated IBM technologies, helping accelerate the time-to-value as insurers expand their big data environments (see Figure 1).

Solutions
Analytics and decision management

IBM big data platform


Visualization and discovery Application development Systems management

Accelerators
Hadoop system Stream computing Data warehouse

Information integration and governance Big data infrastructure

Figure 1: The IBM big data platform offers an array of integrated capabilities
to address the tremendous volume, variety and velocity of big data.

Harnessing the power of big data for insurance

Improving profitability by reducing losses and increasing pricing accuracy A large global property casualty insurance company wanted to accelerate catastrophe risk modeling in order to improve underwriting decisions and determine when to cap exposures in its portfolio. The current modeling environment was too slow and unable to handle the large-scale data volumes that the company wanted to analyze. The goal was to run multiple scenarios and model losses in hours, but the current environment required up to 16 weeks to acquire data, model losses, perform analytics and take actions. As a result, the company was able to conduct analysis only three or four times per year. A proof of concept demonstrated that the company could improve performance by 100 times, accelerating query execution from three minutes to less than three seconds. As a result, the company decided to implement IBM solutions for big data. The company can now run multiple catastrophe risk models every month instead of just three or four times per year. Once data is refreshed, the company can create what-if scenarios in hours rather than weeks. With a better and faster understanding of exposures and probable maximum losses, the company is able to take action sooner to change loss reserves and optimize its portfolio.

Enterprise-class Apache Hadoop: Building on the opensource Hadoop software framework with unique IBM innovations, IBM InfoSphere BigInsights helps insurance companies collect, process, analyze and manage a large volume and variety of data. Companies can ingest and analyze structured and unstructured data, including various social media posts that may provide key insights into customer preferences and future behaviors. InfoSphere BigInsights also helps integrate information from a range of discrete sources, from claims data to call-center recordings. Stream computing: IBM InfoSphere Streams enables companies to continuously capture, analyze and cleanse data in motion to facilitate real-time decision making. Analyzing streaming data provides important opportunities for improving customer service, fraud prevention and catastrophe risk modeling. For example, insurance companies can stream and cleanse social media posts to better understand customer preferences or discover potential fraudulent activity. Companies can integrate real-time weather and disaster data to formulate more accurate, up-to-the-minute catastrophe risk models. Workload-optimized data warehousing: IBM PureData System for Analytics, powered by IBM Netezza technology, is an integrated data warehouse appliance that enables insurance companies to conduct deep, complex analytics on large-scale data volumes while simplifying management. With an innovative, asymmetric, massively parallel processing architecture, PureData System for Analytics can rapidly analyze petabytes of information, enabling insurance companies to explore more variables and patterns, and deliver results quickly. Like InfoSphere BigInsights, PureData System for Analytics enables companies to expand analysis to more data types, including structured and unstructured data, and bring together data from multiple sources. By providing a single, integrated appliance, PureData System for Analytics can be up and running in just 24 hours.

IBM Software

Discovery, visualization and reporting: IBM InfoSphere Data Explorer provides secure, federated navigation and discovery across a broad range of applications, data sources and file types to help users find key information rapidly. IBM Cognos business intelligence and financial performance management software provides the reporting and visualization capabilities that help turn data analytics into meaningful, actionable insights.

Data quality: IBM software such as IBM InfoSphere Information Server, IBM InfoSphere DataStage and IBM InfoSphere QualityStage plays a key role in helping insurance companies correctly identify customers, match records, integrate data, control customer data and improve data quality. Predictive analytics: Easily integrated with the IBM platform for big data, IBM SPSS predictive analytics software can provide insights into future customer behaviors, the impact of events and policy decisions, or the likelihood of fraud. For example, companies can use SPSS to categorize risk and deliver fraud propensity scores to intake specialists in order to thwart fraud.

IBM big data platform at a glance InfoSphere BigInsights provides an integrated solution for analyzing hundreds of terabytes, petabytes or more of raw data derived from an ever-growing variety of sources. InfoSphere Streams provides a state-of-the-art computing platform that can help companies turn burgeoning, fastmoving volumes and varieties of data into actionable information and business insights. InfoSphere Data Explorer provides federated discovery, search and navigation over a broad range of data sources to help organizations get started quickly with big data initiatives and gain more value from their information. Robust IBM data warehouse software and integrated systems help simplify and accelerate the delivery of insights derived from your data. IBM PureData System for Analytics is a high-performance, scalable, massively parallel system that enables clients to gain deep insight from their data and perform analytics on enormous data volumes. IBM PureData System for Operational Analyticspart of the IBM PureSystems familyis an expert integrated data system designed and optimized specifically for the demands of an operational analytics workload.

Serving customers, preventing fraud and reducing uncertainty


IBM solutions for big data offer insurers valuable capabilities for enhancing customer service, identifying fraud and improving pricing. With enhanced information insight, companies develop a greater understanding of customer needs, better anticipate behaviors and deliver targeted offers in real time at the point of contact. They can rapidly prevent, predict, detect and investigate potentially fraudulent claims and enhance the efficiency of ongoing antifraud efforts. IBM solutions for big data can help improve the performance and speed of catastrophe risk modeling to increase the precision of policy pricing, optimize reinsurance placement and determine when to cap a book of business based on risk. With the IBM big data platform, insurance companies are better equipped to harness big data to develop a more customer-centric enterprise, reduce risks and sustain a competitive edge.

For more information


To learn more about how IBM solutions can help insurance companies capitalize on big data, please contact your IBM representative or IBM Business Partner, or visit:
ibm.com/big-data/insurance
Copyright IBM Corporation 2013 IBM Corporation Software Group Route 100 Somers, NY 10589 Produced in the United States of America March 2013 IBM, the IBM logo, ibm.com, BigInsights, Cognos, DataStage, InfoSphere, PureData, PureSystems, QualityStage and SPSS are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the web at Copyright and trademark information at ibm.com/legal/ copytrade.shtml Netezza is a trademark or registered trademark of IBM International Group B.V., an IBM Company. This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates. The performance data and client examples cited are presented for illustrative purposes only. Actual performance results may vary depending on specific configurations and operating conditions. THE INFORMATION IN THIS DOCUMENT IS PROVIDED AS IS WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NONINFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.
1

Insurance Fraud, Insurance Information Institute, March 2013, www.iii.org/issues_updates/insurance-fraud.html Please Recycle

IMW14672-USEN-00

Das könnte Ihnen auch gefallen