Support for The Weather Company

Transcription

1 IBM Analytics IBM Insurance Information Warehouse Support for The Weather Company

2 2 IBM IIW Support for The Weather Company Introduction IBM Insurance Information Warehouse (IIW) and The Weather Company together provide an essential set of components that address the current and future needs of the analytics landscape for insurance organizations. Weather plays an important role in shaping consumer and commercial decisions to protect their assets and for insurers looking to provide tailored solutions to consumer needs. Major events, including hurricanes, floods and snowstorms, radically impact both individuals and businesses. And localized incidents, such as hailstorms, tornadoes and lightning, pose immediate threats to life, property and other assets. Insurance companies understand the importance of weather data; for years, the industry has incorporated historical weather patterns into its underwriting and pricing models. However, advances in weather science, analytics, geolocation and cloud computing now enable insurance companies to apply weather-related insights in new, innovative ways. Weather data can help insurance companies work more effectively with customers to mitigate weather-related losses, allocate internal resources to better assist customers with post-event support and more effectively manage cash reserves. These advances not only improve operational effectiveness, but also build tighter bonds among customers, agents, brokers and organizations. IBM and The Weather Company are helping companies bring together insights from real-time weather feeds to improve operational performance and decisionmaking around risk assessment, event preparation, loss prevention, and disaster response and recovery. The Weather Company s proprietary forecasting system ingests and processes data from thousands of sources, resulting in approximately 2.2 billion unique forecast points worldwide. It produces more than 15 billion forecasts on average weather days. Combined with IBM s vast portfolio of cloud and mobile assets, unique analytic capabilities and deep industry knowledge, our partnership can help organizations anticipate disruptive events, take early action to mitigate impact and return to normal operations more quickly. A cognitive business uses every opportunity to interact with data to reason, adapt and continuously learn. Essentially, a cognitive business places a premium on making fact-based decisions using data rather than reacting after the fact. Core to this shift is the capability to tap into and synthesize myriad diverse data sets, including weather data, and combining it with business and external data to add context, depth and confidence to every business decision. Combining weather data with traditional business data and rich data from an unprecedented number of Internet of Things (IoT)-enabled systems and devices, in an IIW based data store, has the potential to significantly impact enterprise decision-making.

3 3 IBM IIW Support for The Weather Company Catastrophe Modeling Insurance companies use catastrophe models to gain insight on their exposure to risk over the longer term and help quantify risk and direct their decision making. Catastrophe models have been in widespread use for many decades. They arose out of the severe financial impact on the insurance industry from the aftermath of catastrophic events. For example, Hurricane Andrew in 1992 led to the insolvencies of insurers and reinsurers. The impact of these catastrophic events has highlighted the need to better understand, manage and control the level of risk associated with them. Catastrophe models have evolved over that period to become a part of how insurance organizations view risk from underwriting, pricing, reserving and reinsurance perspectives. When viewing catastrophe losses over time, it can be seen that the level of losses in recent times is greater, possibly due to the increasing value of assets, and the level of insurance penetration and changing demographics. What is more significant is that peak loss years are having a much higher financial impact and are also happening more frequently. Severe catastrophic events such as the earthquake and tsunami in 2011 that devastated north-eastern Japan have heightened the interest in catastrophe modeling and raised concerns about the accuracy/validity of the models. Historically, different catastrophe model providers have evolved different approaches and competencies. Organizations have depended on these models to accurately project their level of risk. However, the variances in their own actual claims experience versus the projections provided by catastrophe model providers has led many to consider capturing a more unified view of risk. In conjunction with this changing industry viewpoint, rating agencies and regulatory changes, such as Solvency II, are mandating greater ownership of results from catastrophe models by insurers and reinsurers. Insurers can now leverage The Weather Company weather datasets and transform how insurers monitor the risks associated with the exposure they support. Catastrophe modelling projects can suffer when ingesting data from a multitude of different source systems, all defining and describing risk exposures, products and risk pricing in variety of different ways. There is a need for a standardized approach to describing elements of risk so different policies, products and risks can be understood and compared in a similar way.

4 4 IBM IIW Support for The Weather Company IIW provides broad coverage in support of catastrophe modeling and reinsurance. IIW catastrophe modeling coverage aims to help insurers and reinsurers understand how to capture the data inputs into, and outputs (results) from, catastrophe loss models in a data warehouse. This involves the identification of the parts of the model that are relevant to this business requirement from reinsurance, policy and exposure data, claims data, weather data sets from The Weather Company, location information and also to identify how the results can be captured. The comprehensive coverage in IIW can help catastrophe modelling projects define products, pricing and risk information in a standardised way, with well-defined and flexible data structures, which can capture data from the simplest of risk characteristics to complex reinsurance treaties.

5 5 IBM IIW Support for The Weather Company Advances in Weather Analytics A great strength of weather data insight is that it can create opportunities across a number of different functions within traditional insurances firms. Several major areas of opportunity exist. Claims In the past, weather-related events often left organizations in a catch-up mode, facing significant increases in call volumes and claims. Further, these unforeseen situations made it difficult to predict exactly where to align field resources, such as adjusters, to rapidly evaluate claims and provide shortterm support to those impacted. Incorporating weather data into operational processes, such as workforce scheduling, third-party contracting and vehicle optimization, can help to decrease the delays associated with managing peak activity and provide assistance to those facing individual losses or business continuity disruptions. At the same time, insurers can integrate weather and social media data, such as Twitter feeds, to assess the reputational risks of inadequate response times. Monitoring the social chatter of weather event victims can identify potential customer concerns and issues, enabling the organization to adjust its resources accordingly. Underwriting Weather insights can help insurers with pricing, underwriting and risk selections. More granular and access to timely weather data allows insurers to make informed underwriting decisions and support a balanced portfolio Altogether, weather disasters cost US insurance companies many billions a year in claims. Data-driven predictive weather insights help insurers mitigate catastrophic scenarios in high-risk areas by using probabilistic weather forecasts as geocoded inputs to policyholder risk profile models. Customer Engagement For insurance companies, the least costly event is the one that never occurs. Insurers can use weather data to identify the potential for a significant weather-related event and notify customers to take action to protect life and property. If weather data predicts a hailstorm, for example, an insurance company could send a text message to warn policyholders in the storm s path of potential damage. That warning would detail the precise location and timing of the expected hailstorm and strongly urge customers to take action, such as moving their cars to covered locations. Similarly, an insurer could recommend that customers move to higher ground or prepare defensive barriers in advance of a storm surge. Companies can personalize and tailor these alerts to:

6 6 IBM IIW Support for The Weather Company Different methods of notifications based on demographics and preferences, such as text messaging, landline phone or in-house monitoring system Actions customers should take, such as removing potential debris hazards before a wind storm, clearing gutters before severe rain events or insulating pipes before rapid freezes The location of critical assets, whether at home or at work After an event, weather data can also assist customer-service professionals by helping them identify customers who need to be contacted. By knowing which policyholders in an affected area may have sustained damages and reaching out to them directly, representatives can quickly ascertain whether individuals have sustained losses and initiate processing. This interaction can assist victims who aren t able to easily access their policy information and, more important, can help to rapidly identify those in need of medical attention or immediate repair services. Pre- and post-event touchpoints with customers provide important information about customer behavior and offer insights into contact preferences, product and service needs and brand image. An insurer can link information, including the number of alerts it sends to a specific device or location or the customer response to the alerts, to other sources of marketing data to obtain a more comprehensive view of the customer. The company can then use this information to develop new products, create crossselling campaigns and even tailor collateral design and development to unique customer segments. Risk Management Weather data can be used with advanced analytics to help insurers better manage financial assets. Traditionally, firms have used long-range forecasts to develop actuarial models that drive more effective product profitability and reinsurance placements, but weather data can also influence short-term financial decisions. The liquidity necessary to support rapid, on-site payments to claimants can also lead to significant cash flow needs for large events. As a result, firms must decide how much cash to set aside to pay claims. Too much in reserve increases the amount of cash on hand, which likely reduces investment income; too little, and the company may need to seek shortterm financing or liquidate longer-term investment assets and incur higher-thanexpected costs of funds. Advanced weather data can help an insurance company better manage its cash positions and determine optimal reserve amounts in advance of a storm. In addition, weather data can play a role in preventing fraudulent claims. Knowing the road conditions at a given time and location, an insurer can improve the accuracy of accident reporting and confirm the presence of hazardous conditions.

7 7 IBM IIW Support for The Weather Company New Business Models One of the most exciting applications of weather-related data is in the field of telematics. Increasingly, insurers are incorporating devices that can monitor driving behavior, and weather data can help further refine the results and offer additional context. For example, knowing that a customer is driving the legal speed limit under clear conditions is very different from realizing that the same driver is moving at that pace through a blizzard. Weather data plays an important role in refining the risk-scoring algorithms that evaluate driver behavior, as well as providing a record of actual conditions for claims investigations. Further, an insurance company can gather a combination of weather, speed and location data from an individual vehicle or others in a connected network. The company can then use that information to alert drivers safely, using a voice prompt or similar technology, when they are approaching poor weather or road conditions. The technology could then help drivers decide whether to modify their speed, change their route or even locate food and lodging alternatives up ahead. Even if drivers choose not to opt-in for realtime traffic alerts, they could still use the information to evaluate options and plan future trips. All of these capabilities will grow increasingly relevant as connected, and even driverless, cars become more prevalent. Freed from the mechanics of operating a vehicle, drivers will be available to select from an array of potential options during a journey.

8 8 IBM IIW Support for The Weather Company The Weather Company Analytics What characteristics are necessary for weather data to power some of these new and emerging capabilities? The data needs to be: Precise and location-specific Many organizations and individuals have access to weather data from various national weather services. While this data may be useful for general predictions, often it doesn t include the level of precision necessary to pinpoint areas where weather is likely to have specific impact. A lack of specificity in forecasting can lead to false-positive alerts that can actually discourage people from taking action. Weather can differ within a square quarterkilometer, and these variations can change how a particular location experiences a weather event. Timely Not only does weather data need to be location-sensitive, it also needs to be refreshed frequently to foster accurate prediction models and insights that are meaningful to users. Small shifts in wind direction, temperature and precipitation can have a significant bearing on where potential damage will occur, so it is critical to refresh the data frequently every five minutes, for example to adjust forecasting models and more accurately predict areas of impact. Integrated Integration of weather data with other data streams creates a rich picture of the environment. The true value of weather data lies not in the data itself, but in its ability to combine with other sources of data to deliver new services and capabilities. Geospatial data together with weather data can provide real-time information about road conditions and potential hazards, as well as route alternatives. Weather and social media data together can provide unique insights into how effectively an insurer is meeting the needs of its customers during a weather event. Insurers can also combine weather data with operational data to help determine if it can muster the resources necessary to service large numbers of claims quickly. Customizable Weather data is most valuable when users can access and apply it flexibly. Customers must be able to easily provide the locations for which they would like to receive weather-related data, as they may be interested in protecting both stationary assets such as a home or a place of business as well as cars, boats and other mobile assets. They may also want to select the type of weather data, customize alert levels and specify family members they would like to be notified. Further, customers may also want to specify how they receive weather data whether it is through a landline, mobile phone, app, text message alert or even on a television. This level of personalization and customization can determine the extent to which individuals will react to weather notifications, influence subsequent behavior and reinforce their relationship with the insurance company.

9 9 IBM IIW Support for The Weather Company IIW Components Business Terms - define industry concepts in plain business language. Analytical Requirements - enable rapid scoping and prototyping of data marts, which provide a subject-specific analytical layer in a data warehouse solution. Supportive Content - provides a method of mapping both external and internal terms from business standards and other requirements to other models. Business Data Model - a logical entity relationship model that represents the essential entities and relationships of the energy and utilities industry. Atomic Warehouse Model - a logical, specialized model that is optimized as a data repository, which can hold long-term history, usually across the entire enterprise. Figure 1. IIW solution components Dimensional Warehouse Model - a logical model that is optimized data repository for supporting reporting needs and analytical queries.

10 10 IBM IIW Support for The Weather Company IIW Support for The Weather Company The Weather Company and IIW can work together to address key components of the new overall analytics landscape. IIW is designed to provide the basis for the data warehouse component that provides the central consolidation point for the different types of data coming into this new analytics landscape. IIW is designed to address the definition both of traditional data warehouses as well as additional unstructured stores, both of which need to be managed in a consistent fashion. IIW is also designed to provide the basis for business issue-specific data marts. The role of the IIW-derived data warehouse as the central consolidation point for data for use across this analytics platform is very complementary with the specific The Weather Company focus on the delivery of advanced weather data. In many cases the data stored centrally in the IIW-derived data warehouse would be complementary with The Weather Company data. The ability to leverage an extensive repository such as an IIW-derived data warehouse: Allows your analytics platform to draw from a rich data set derived from multiple disparate sources to enrich the platform s analytic capabilities Figure 2. Typical Weather Claims Insight architecture Increases your view of the enterprise s data Provides a structure to capture point-in-time weather insights to enrich analytics and decision making throughout the organization

11 11 IBM IIW Support for The Weather Company IIW includes definitions of data structures that can be used to create database objects to hold the data acquired using The Weather Company APIs available in Bluemix. The weather data includes observations (current on demand), forecast or weather alerts can be used for advanced analytics when combined with data from other systems used in the organization, e.g. policy, claims and exposure information. Supportive Content IIW Supportive Content contains structures for support of The Weather Company APIs from Bluemix. A total of almost 400 Supportive Content terms grouped into API specifications and Response Schemas are now available and mapped to IIW Business Terms. 8 API Specifications with 33 different input parameter combinations. 10 Response Schemas which define the results returned from the API calls. - Weather Observation - Weather Forecast - Weather Alert - Weather Almanac (lifestyle related forecasts) The Supportive Content terms for The Weather Company are mapped to the equivalent term in the Business Terms and to the Business Data Model, making it easier to build a data scope for a weather related business requirement using The Weather Company. This complements the existing IIW Supportive Content for catastrophe model open standard specification. This contains the Supportive Content terms that assist with the input and output specifications (financial module insurance loss / financial module insurance structures / financial module programme / ground up losses) of catastrophe modeling systems and is based on the Oasis Loss Modelling Framework. Business Data Model and Atomic & Dimensional Warehouse Model The Business Data model and Atomic Warehouse Model now include Business Overview and Scenario diagrams which illustrate how IIW can support data provided from The Weather Company APIs and can provide a template for a data scope for weather related project. These new business overview and scenario diagrams complement existing Catastrophe Model support. A new Dimensional Warehouse Model Business Scenario diagram provides an illustration of how the Dimensional Warehouse Model can support the data provided from The Weather Company APIs. It identifies the types of dimensions, facts, bridges and outriggers needed to persist the weather company data.

12 12 IBM IIW Support for The Weather Company Analytical Requirements Weather related coverage in IIW includes: Event analysis Flood zone risk concentration analysis Flood risk portfolio analysis Hurricane location analysis Hurricane building structure analysis Loss modeling Annual exceedance probability analysis Loss distribution and vulnerability analysis Occurrence exceedance probability analysis Reinsurance analysis Finite reinsurance decision analysis Project Views Project Views are business subject area views that span across all IIW components with the following functions: Provide predefined business scope of business terms related to the various components of the catastrophe modeling from a data perspective (catastrophe model inputs and results, hazards, exposure data, policy terms including reinsurance and so on) Provide pointers to the parts of the IIW models which would be relevant to a catastrophe model project data scope or to address a particular exposure analysis reporting requirement. Can be extended as required with an organizations specific customizations. Catastrophe Modeling project views contain project views for Catastrophe Modeling Big Data, Exposures, Hazard event data sets, Policy terms and Vulnerability assessments. The Weather Company project view contains all the business terms that have been mapped to The Weather Company supportive content.

13 13 IBM IIW Support for The Weather Company Conclusion As insurers increasingly build similar products that compete against one another in the public marketplace, they will be looking for ways to differentiate their offerings. The ability to take advantage of advances in weather forecasting and advanced analytics and incorporate weather into decision-making processes can provide unique value to insurers and customers alike. Effectively incorporating weather data into a variety of insurance activities can mean the difference between remediation and prevention, and can help to mitigate the impact of events that are truly unpredictable and unavoidable. In short, the effective application of weather data can enable the insurer to offer unique value that centers on risk but improves customer retention and well-being. Weather plays a critical role in many industries. Advances in both weather science and cloud computing have fundamentally changed the paradigm, allowing us to harness more data, scale to meet demands, and be far more precise and accurate in forecasts. As a result, IIW and The Weather Company can transform how businesses understand the impact of weather on their operations, anticipate weather events sooner and take action to optimize those parts of their enterprise impacted by weather allowing more businesses in all sectors to make weather actionable. IIW and The Weather Company together provide a critical set of components needed to address the current and future needs of the analytics landscape for energy and utilities organizations in the areas of data consolidation and advanced weather analytics. A model-driven, extensible data warehouse enables the managed and governed storage of data and provides a home for weather related, as the statement of record for advanced analytics. It also acts as a location for the storage of any weather data created provided by The Weather Company for use by other applications across the enterprise. The use of a data model designed to engage the business user during the initial development phases and the weatherfocused data from The Weather Company enables the likelihood of an extensible data infrastructure that truly meets the needs of the business.

14 Copyright IBM Corporation 2017 IBM Corporation IBM Analytics Route 100 Somers, NY Produced in the United States of America June 2017 IBM, and the IBM logo are trademarks of International Business Machines Corporation in the United States, other countries, or both. The Weather Company is a trademark or registered trademark of TWC Product and Technology, LLC, an IBM Company. Other company, product or service names may be trademarks or service marks of others. A current list of IBM trademarks is available on the web at Copyright and trademark information at. ibm. com/legal/copytrade/shtml. 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 INFORMATION IN THIS DOCUMENT IS PROVID- ED 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 NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided. The client is responsible for ensuring compliance with laws and regulations applicable to it. IBM does not provide legal advice or represent or warrant its services or products will ensure that the client is in compliance with any law or regulation. Please Recycle IMW14944USEN-00