loading
The latest thinking and expert insights into the insurance industry.
26 March 2018
  |  
profile-img

Leveraging Artificial Intelligence for Automatic Image Analysis

Insurance companies consume terabytes of information every day in the form of digital data. Valuable data is being provided by more and more sources. All this data quickly paints a reliable picture of a risk or a submitted claim. By doing this it possible to filter out unwanted risks and fraudulent claims. State-of-the-art technology is required to process this influx of information and convert it into applicable knowledge and insights. This requires for intelligent software capable of processing information quickly, learning independently, drawing smart conclusions, and making recommendations. Similar to a human, but then smarter and more efficient. We’re talking about artificial intelligence (AI).

3 types of Artificial Intelligence (AI)

leveraging-artificial-intelligence-for-automatic-image-analysis

We can identify roughly three types of artificial intelligence. The first benefits everyone and is known as ‘general’ AI. Examples of this type of AI include natural language processing, facial recognition, and augmented reality. In the latter, the physical world is overlaid with elements from the virtual world. We use elements of general AI to support specific process in the other two forms of AI.

The second form is called product-based AI. It involves product with specific tasks. Just think about systems designed to identify and deactivate computer viruses, spam filters, and programs that detect fraud patterns. The latter is extremely valuable to us. If we feed AI with information about fraud cases, the better it becomes at this specific task. AI systems learn by doing and by drawing on feedback from many different users.

The third type of AI is custom or domain-specific AI. In short, AI that is trained for usage in a specific niche. An example from the insurance sector is AI that was trained to identify fraud patterns. Straight-Through Processing (STP) was integrated, aswell as the characteristics of a single insurance company: the specific products, target groups, distribution channels, and claims processes. This allows us to determine how AI can best be integrated into the business operations of an individual insurance company.

AI and Image Analysis

Combining all three types of AI often leads to the best results; for instance, using Artificial Intelligence to analyse images in an STP environment while simultaneously checking for fraud. Insurance companies receive huge amounts of visual material. This is used to illustrate claims and support the claims process (e.g. determining the legitimacy of a claim). The photos are submitted by policyholders or thirth parties to illustrate damage (e.g. car damage) or as evidence that lost or stolen items were indeed in the possession of the owner (e.g. jewellery, clothing, or cameras).

Claim Assessment

Leveraging-Artificial-Intelligence-for-Automatic-Image-Analysis

In order to optimize the use of photographs, it must be determined that the right photos were submitted and that the damaged object was photographed from every angle. It’s also important to determine that the object in the photo is indeed the insured object; that older damage is not being included in the claim; and that the photo has not been used before, downloaded from the internet, or photoshopped. The next step is to determine the damage and the costs of repairing the damage. Is the car a total loss? How bad is the fire damage? Are there any visible indications of fraud?

These analyses can be made with the help of the three AI types listed above. General AI is trained with millions of images to identify general objects like cars, windows, buildings, etc. The huge quantity of data and the impressive computational power means these analyses are carried out at lightning speed and with great accuracy.

Product-based AI is trained using specific claims (e.g. glass damage) to determine the amount of damage and to identify potential fraud.

Training AI

As a final step, AI can also be trained with various machine learning algorithms in the specific application domain; in this case, the process used by the relevant insurance company. Combining these three types of AI ensures smooth and efficient claims processing. The longer AI is used and the more data and feedback it receives the better and faster it will work. This will speed up the claims assessment process. And it may even lead to a fully automated process in some cases, such as STP. An added benefit is that fraudulent claims are filtered out more efficiently.

In addition to image analytics, there are dozens of AI types currently available and under development. Insurance companies can use these technologies to improve and streamline their risk analysis and fraud identification processes. In the coming period I will elaborate on this subject using some of our fraud prevention cases as an example.

Learn more about the future of Straight Through Processing (STP)

Contact us

Cookie and Privacy Policy

1. Introduction

When you use this website, FRISS may collect information about your use of the website and the content offered. We believe it is important to handle your (personal) data with due care and confidentiality. When processing your personal data, we comply with the General Data Protection Regulation (Algemene Verordening Gegevensbescherming) and Article 11.7a of the Telecommunications Act (Telecommunicatiewet).

1.1.  Controller

The controller of the processing of personal data is:

FRISS Fraudebestrijding B.V.
Orteliuslaan 15
3528 BA
Utrecht

This processing of personal data is registered with the Dutch Data Protection Authority (Autoriteit Persoonsgegevens) in The Hague under reporting number m00004997.

1.2.  Purposes of data processing

There are several places on our website where you can fill in your (personal) data. We will explain the purposes of the various instances of data processing below.

Filling in the contact form or sending an e-mail

If you fill in the contact form on our website or send us an e-mail, we will only use the (personal) data you provide for the purpose or purposes for which you filled in the contact form or sent the e-mail.

Download form

If you download files on our website (such as e-books, whitepapers or reports), we will use the (personal) data you provide for one or more of the following purposes:

  • for the execution of an agreement, for example to send you the e-book, whitepaper or report you have chosen;
  • for the formation of an agreement, for example by contacting you by telephone or in writing.

Newsletter

If you fill in the application form for the newsletter on our website, your (personal) data will be used to send you the newsletter. Each newsletter contains a hyperlink at the bottom of the message that you can use to unsubscribe.

In addition to the personal data you provide to FRISS yourself, FRISS may collect, record and process additional (personal) data if you use the (web) services of FRISS. This concerns the following personal data:

  • data from the used equipment, such as a unique device ID, version of the operating system and settings of the device you use to access a service;
  • information about the use of a service, such as the time at which you use the service and the type of service that is used;
  • location details from your device or derived from your IP address that is provided to us when you use a particular service;
  • data available from external sources. We may receive information about you from public or commercially available sources.

1.3.  Provision of (personal) data to third parties

Your (personal) data will never be provided to third parties without your permission, unless we have an obligation to do so pursuant to legislation or regulations or you have given permission for this.

1.4.  Security of data

FRISS respects your privacy and ensures that personal data are handled confidentially and with the utmost care. All processed (personal) data is stored exclusively in secure databases. These databases are only accessible to employees of FRISS, to the extent that this access is required by virtue of their position. FRISS makes every effort to secure these systems against loss and/or any form of unlawful use or processing.

1.5.  Inspection, correction and deletion of data and the right to object

You can view your data that is processed by FRISS at any time and free of charge and, if you so wish, modify this data or have it deleted. You can also object to receiving information about products, services or content of FRISS. If you wish to make use of one of these options, you can send an e-mail to the Data Protection Officer of FRISS via privacy@friss.eu or write to the following address:

FRISS | fraud, risk & compliance
Attn. Data Protection Officer
Orteliuslaan 15
3528 BA Utrecht.

2. Cookies

When using this website, information about your use of these services and other websites may be collected by or on behalf of FRISS, for example by means of cookies.

A cookie is a small file that is sent along with pages of a website and stored by your browser on the hard disk of your computer. We use cookies to remember settings and preferences. You can disable these cookies via your browser.

2.1.  The purposes for which FRISS uses cookies

On our website we use cookies for the following purposes:

  • for statistical purposes, in order to analyse the use of FRISS websites. This allows us to keep track of the number of visitors and see which parts of our website are popular. We use Google Analytics in order to track and consult these statistics. On this website you can find explanations about all cookies that may be placed by Google;
  • for what is known as ‘targeting’ purposes, if you have used the download form. By targeting we mean building a profile of you based on your surfing behaviour on our website, after which we may contact you by telephone or e-mail based on the interests you have shown in order to offer you FRISS services that you may be interested in. We use HubSpot in order to track and consult these statistics. On this website you can find explanations about all cookies that may be placed by HubSpot;

3. Changes to this Cookie and Privacy Statement

FRISS may make changes to this Cookie and Privacy Statement. All modifications will be published on this page. We advise you to consult this Cookie and Privacy Statement regularly, so that you are always aware of the content of the current Cookie and Privacy Statement.

 

Subscribe