2016 has become the starting block of the InsurTech movement. Innovation is leading the effort to create new technology for the business insurance. CEOs, Sr. V.P.s, Directors, Managers, Supervisors, and line level professionals are hoping that the emerging technology will improve customer satisfaction, increase sales in the marketplace, and streamline and reduce the costs of processing claims. A valuable asset to your business process is the ability to identify patterns in your data (internal first, and then external data), which will then allow you to have better insight and decision making. Remember: Right Data, at the Right Time, to the Right Person, for the Right Decision. Artificial intelligence (A.I.), or machine learning, can leverage the knowledge and skills of your team into automated computing processes thereby reducing the amount of time in gathering data, organizing the data, analyzing the data, and then present it in a clear and concise view for timely decisions.

Lessons Learned

Imagine your claims representative missing the patterns of an organized enterprise preying on your claims system. What about the nefarious individual masking questionable activities in the policy application (life, property and casualty, workers’ compensation, automobile)? How can you gain a clear vision of the future trends in litigation issues of claims (residential and commercial, non-standard automobile, workers’ compensation, life and indemnity, disability, etc.) What about a district attorney’s office bringing a three year, highly sophisticated, $120 million healthcare fraud case to trial with the need to analyze mountains of documents and evidence for trial? Advanced analytics with machine learning is key to answering these questions. Understanding how and where A.I. can be deployed in your analytics and business processes might appear to be a daunting task, but it is not with the proper strategy.

A.I. Defined for Insurance

The following technologies are the foundation of a robust advanced analytics platform:

• Knowledge Engineering: Basically, knowledge engineering is utilized to analyze data, models, and business rules (heuristics) into applications to solve complex problems which human beings have done for some time. Remember, the goal is to automate the process of gathering and analyzing data much more efficiently and quickly. For example, ICD 9 and 10 codes in medical records; pharmaceutical codes for medications and narcotics; weather patterns; commercial and residential building registers, or the national death register. Reducing the time spent on gathering routine information can lead to better decision making by your staff, and reduce costs.
• Natural Language Processing: NLP is utilized to understand the meaning of words in conversations, both audio and written text. NLP combined with machine learning will allow you to discover patterns within your claims and underwriting data streams, and build powerful predictive models. For example, initial claim forms (FNOL, CMS1500, State workers’ compensation forms, etc.); claim investigation notes and reports; social media posts (mainstream media and public records); medical billings and reports.
• Machine Learning: Tools, techniques, and algorithms are the bedrock of machine learning and critical in identifying patterns in your data. Machine learning is key in deploying advanced analytics for your underwriting, claims, and marketing operations. Connecting the silos of information is critical in the predictive analysis of your business process.
• Image Analysis: Image analysis basically identifies objects, locations, events, and individuals in photographs and video. Imagine the possibilities of receiving a live video stream of an area just destroyed in a catastrophic weather event or firestorm. What about photographs of vehicles used over and over in multiple false claims (each time masking the true identification of the vehicle, both VIN and license plate)? A robust image analysis solution can help validate genuine claims, and stop the fraudulent ones before a payment is issued.
• Sensory Perception: The Internet of Things (IoT), which is really Data of Things, will grow exponentially due to smart phones, smart devices (i.e., the smart home). It is estimated that by 2020, each person will have several devices connected together with the IoT. This is a significant amount of data that can be gleaned and analyzed in the business of insurance and risk management. The sensory data needs to have the right context for meaningful analysis. Advanced analytics is key to make sense of the IoT.

The True Value of A.I. for Insurance

Earlier this year I was honored to speak at the Silicon Valley Insurance Accelerator Q3 Symposium on A.I. for claims. One of the attendees asked a great question: “Will A.I. replace the human in the claims process?” The short answer is; No! Many laws and regulations governing the business of insurance would need to be modified, and or created. The true value of A.I. in the claims, marketing, and underwriting processes is the automation of mundane tasks. It is estimated that agents spend 80 percent of their time gathering data on a prospective customer, 10 percent on administrative tasks, and 10 percent of the time on analyzing the potential risk of the new business. Claims personnel mirror the same percentages. If you automate the data gathering, the organization of it, and then apply specific advanced analytics to your business process, success will follow. You can lower the adjusted loss expenses claims (ALE), reduce the time currently expended in gathering and data, and streamline your business process.

Next month, we will introduce the concept of connecting the senses used in the human interaction for the business of insurance. Cognitive computing begins with connecting basic senses to A.I.

Seasons greetings and happy holidays from the Infinilytics team!