The Data Quality Analysis API stores each Data Quality Analysis as a Data Quality Analysis object, and you can use the GetDataQualityAnalyses() method to retrieve a list of these objects for a particular Touchstone Project.

Augmentation means adding information about individual properties in your portfolio where data is missing or when confidence in the existing data is low. You can augment building location, property value, and primary and secondary risk characteristics. Primary risk characteristics include building construction, occupancy, year built, height, and gross area. Secondary risk characteristics include roof geometry, roof cover, siding, and foundation type.

An Industry Comparison Summary enables you to benchmark your exposure data against industry data contained in AIR's Industry Exposure Database. This database contains aggregate property information about risk counts, property attributes, and replacement values.

The Score Data diagnostic calculates a Data Quality Score and an Overall Risk Score for individual Locations and for entire portfolios. The scores help you identify high-value exposures that warrant further investigation and augmentation (enhancement). The scores are peril-specific. The impact that missing exposure data has on modeled losses depends on the Location and characteristics of the risk and the peril under consideration. For example, missing construction characteristics have a greater impact on modeled losses in areas in which there is a lot of heterogeneity in the types of construction used and when the scoring methodology is considering a peril for which construction is a key variable.

The Data Quality Score measures the completeness of the exposure data. It quantifies inaccurate and missing primary risk characteristics in the exposure data that can contribute to uncertainty in modeled losses. Ranging from 0-100, a higher data quality score indicates better relative data quality, which can lead to reduced uncertainty. Touchstone calculates data quality scores for each Location in the analysis target and then combines them to produce various aggregate scores, such as for the entire portfolio and for each state. Portfolio-level Data Quality Scores are particularly valuable because they can help you to accomplish the following tasks:

• Communicate portfolio-level data quality to underwriters, brokers, reinsurers, and rating agencies
• Compare exposure data quality in portfolios
• Assess the impact of a Data Quality augmentation
• Monitor data quality enhancement of a portfolio over time

When calculating Data Quality Scores for individual locations, Touchstone considers the availability of known data for the following primary risk characteristics:

• Geocode match level (Relaxed Address or better indicates good quality address information.)
• Building construction code
• Occupancy code
• Year built
• Number of stories

The Data Validation analysis enables you to assess the quality of your exposure data by evaluating your portfolio against a set of completeness rules and reasonability rules. Completeness rules enable you to learn about where information is missing in your exposure data. Reasonability rules help you to determine if the exposure data contains combinations of attributes that typically are not found together. For example, it is not reasonable for a wood frame building to be 10 stories high. It is not reasonable for a reinforced masonry building to have been built prior to 1950. It is not reasonable for a residential family home to be built of light metal.

The Touchstone Data Quality API enables you to integrate Data Quality Analysis results and reports within your applications and workflows. These reports include scoring, validation, benchmarking, and augmentation of your exposure data.

You execute all analysis jobs against an Exposure View, and Touchstone stores the results in a Touchstone result Data Source (Database). To create a new result Data Source, use the SubmitCreateDatabase() method.

The Touchstone Data Quality Analysis API can generate a PDF file that contains a summary of the results of any of the following types of Data Quality Analyses:

• A.M. Best Rating Company
• Augmentation
• Industry Comparison
• Scoring
• Validation