Tag Archives: coverages

How Machine Learning Transforms Insurance

We like our insurance carriers to be risk-averse. So it should come as no surprise they are often last to innovate. Insurers need to feel very comfortable with their risk predictions before making a change. Well, machine learning is writing a new chapter in the old insurance book. There are three key reasons why this is happening now:

  1. New insurtech players are grabbing market share and setting new standards. Traditional carriers have no choice but to follow suit.
  2. Customers are expecting Netflix/Spotify-like personalization, and have no problem changing providers — this trend is expected to grow as we see more millennials maturing out of their parents’ policies.
  3. Getting started with machine learning is becoming VERY easy because of open source frameworks, accelerated hardware, pre-trained models available via APIs, validated algorithms and an explosion of online training.

As with any innovation, it only takes two things for widespread adoption:

  1. Potential to improve business goals.
  2. Ease of establishing pilots.

With time, we see that successful pilots become products. Teams are hired/trained, resources are allocated, business goals gain more “appetite” and models are tweaked.

For P&C carriers. we see the opportunity for improving business goals and easily pilot machine learning in the following areas:

Risk Modeling

Given the complex and behavioral nature of risk factors, machine learning is ideal for predicting risk. The challenge lies in regulatory oversight and the fact that most historic data is still unstructured. This is why we often see machine learning applied to new products such as those using data from IoT sensors in cars (telematics) and home (connected home). But innovative carriers are not limited. They use pre-trained machine learning models to structure their piles of unstructured data: APIs to transcribe coupled with natural language understanding (NLU) extract features from recorded call center calls, handwriting and NLP/NLU tools for written records, leading toward identifying new risk factors using unsupervised learning models.

See also: 4 Ways Machine Learning Can Help  

Underwriting

Carriers can get an actuarial lift even without designing and filing new actuarial models. Using machine learning to better predict risk factors in existing (filed) models. For example, a carrier may have already filed a mileage-based rate-plan for auto insurance but rely on user-reported or less accurate estimates to determine mileage. Machine learning can help predict mileage driven, in a less biased and more accurate way. Similarly, APIs to pre-trained chatbots using lifelike speech and translators can turn website underwriting forms into more engaging and personalized chats that have a good chance to reduce soft fraud.

Claims Handling

Claims handling is a time-intensive task often involving manual labor by claims adjusters onsite. Innovative carriers already have policy holders take pictures and videos of their damaged assets (home, car…) and compare with baseline or similar assets. Carriers could easily leverage existing APIs for image processing, coupled with bot APIs to build a high-precision model, even at the expense of low recall. Compared with having 100% of the book handled manually, a triage bot that automates even a mere 20% of the claims (with high precision) can enable carriers to start with a low-risk service that’s on par with new insurtech players and improve ratios over time. Such a tool can even be leveraged by adjusters, reducing their time and cost.

Coverages

While personalized pricing may be regulator-challenged, personalizing the insurance product offering is expected in this Netflix/Spotify age. As basic coverage is commoditizing, carriers differentiate their products based on riders and value-added services, not to mention full product offerings based on life events. Carriers can (with consent, of course) leverage social media data to tailor and personalize the offering. Similarly, marketing departments can use readily available recommendation algorithms to match and promote content about the benefits of certain riders/value-adds to relevant customers at the relevant time.

Distribution

The world of insurance distribution is growing in complexity. Carriers are struggling with the growing power of intermediaries, and agents are having hard time optimizing their efforts due to lack of predictability of loss commissions. Point-of-sale and affiliation programs are growing, and with them the need for new distribution incentive models. Both traditional and new distribution channels could benefit from machine learning. Brokers, point-of-sale partners and carriers can leverage readily available machine learning models and algorithms designed for retail, to forecast channel premiums. Carriers can grow direct channels without growing headcount, using pre-trained chatbots, NLU and lifelike speech APIs.

See also: Machine Learning: A New Force  

Machine learning is part of our everyday lives. Innovative insurers are now jumping on the ML wagon with an ever-growing ease; which carriers will be left behind?

Outside Looking In

I found myself arguing an extremely silly point with an agency owner at a conference.  Everyone but the agent saw the silliness of his argument.  I explained the point every way imaginable, to no avail.  I could see from the looks on others’ faces, they were tiring of him not getting the point either.  If he had been one of the audience members watching someone else argue, he probably would have seen the errors in his thinking, too.  But, sometimes you just have to be outside looking in to see a point.

As a consultant, I very often find myself facing this type of situation.  The four points below are the most common positions held by agency owners that create immovable and serious roadblocks to their agencies’ success.  If any of these sound familiar to you, take a step outside of the situation and look back in.  You might see your position in a different light.

1.  We must write small accounts because you never know which one will turn into a large account. This commonly expressed position presumes an inability to identify clients with great potential versus those with no potential.  This means agencies believing in this philosophy should write absolutely as many small accounts as possible. 

An average agency abiding by this philosophy has at least 1,000 small accounts and maybe one, over 10 years has grown big.  But let’s say there are two accounts that grow big.  So out of 10,000 renewals, two get big.  Can the agency write enough large accounts to cover the 1,000+ small accounts that soak up huge amounts of time, effort and expense?  If so, this may be a great strategy.  If not, it is time to rethink the agency’s strategy.

2.  We do not use coverage checklists because we might leave something off.  The belief here is that if you don’t have a list, you can’t leave coverages off.  This presumes nothing is left off when a checklist is not used.  So if an insured does not get the correct coverage because the producer does not use a list and the absence of a list means the coverage wasn’t necessary to offer, then by default, the customer could not have needed the coverage and therefore, the uncovered claim is just a figment of their imagination.  Right?  If you believe this, then keep on going without using coverage checklists.

Another perspective is that if the agent does not use a coverage checklist, there is no need to recommend coverages a customer needs.  In other words, if I don’t know the customer needs a coverage, I don’t have a responsibility to offer the coverage.  For a peddler of insurance, this makes perfect sense because peddlers only take orders.  Why pay commissions to peddlers?  Web sites are quite capable of taking orders and issuing policies.

3.  We do not need to hold our producers accountable.  The reasons given for not holding producers accountable are numerous and include that accountability might make them angry.  What is the price of an angry producer?  In some cases, say $500,000 commission producers, not making them angry might be a good strategy.  But is the price reasonable for not making $100,000 producers angry?  An incompetent producer may leave the agency or become a good producer through accountability.  Either way, the agency may find itself way ahead by enforcing accountability.

Other common reasons given are that they are nice guys and that they have never been held accountable so it is unfair to do so now.  That is fair enough.  But to be really fair, if the producers are not held accountable, why hold anyone accountable?  Why hold the customer service representatives (CSRs) accountable?  Why hold new producers accountable?

Another reason given is that by holding them accountable, the ultimate outcome is that they would be fired and the emotional trauma of firing a producer is too much.  That makes sense.  Of course, if you are not going to fire a producer, how can you fire a CSR?  Is their trauma any less?

Then there are the producers that should hold themselves accountable negating the need for management to do so.  How well is that working in your agency?

4.  All agencies have the same value as a multiple of sales or EBITDA.  I am often asked, “How much are agencies worth today?”  This presumes that all agencies are alike, all agencies are commodities and nothing is special about any agency.  Is this correct?  Is there nothing special about your agency?

Let’s assume some common multiple applied to all agencies.  If one agency is losing 10 percent of its commissions annually and another agency is growing by 10 percent, then they should have the same multiple.  The same goes for the agency that has a 25 percent profit margin versus the agency that has a -5 percent profit margin.  Even the agency that has $1,000,000 of extra cash on its balance sheet versus the agency that has spent $500,000 of trust monies will have the same value. 

The question presupposes such material differences do not exist.  It’s like someone is asking, “What’s the value of a 2005 Ford F-150?”  They expect I can look up the blue book, ask how many miles the agency has on it, the condition of the body, and whether it has any extra features.

Quite often, the agency owners who ask this question have problematic agencies and the reason they ask the question this way is because they do not want their problems taken into consideration in the valuation. 

I do not believe any reader likes the logical result of these incredibly common beliefs and practices.  I’m not going to argue these ideas are wrong.  If you share these beliefs, take a step outside and look back in.  Think through the complete concept and if you still believe in it, then go for it 100 percent!