Amit Capstone Project - Analytics in Insurance

The property and casualty (P&C) insurance industry is further along in using advanced analytics in not only to improve the risk selection but also offer customers the new products. For example, a growing number of auto insurers now offer usage-based insurance products that use technology to monitor driving behavior and reward good driving with a discount. Tech-savvy Millennials in particular, find these products appealing and believe usage-based insurance is a much better approach for policy underwriting than the traditional methods, such as credit scores.

Fraud:

1 out of 10 insurance claims is fraudulent. Most fraud solutions on the market today are rules-based. Unfortunately, it is too easy for fraudsters to manipulate and get around the rules. Predictive analysis, on the other hand, uses a combination of rules, modeling, text mining, database searches and exception reporting to identify fraud sooner and more effectively at each stage of the claims’ cycle.

Subrogation:

Opportunities for subro often get lost in the sheer volume of data – most of it in the form of police records, adjuster notes and medical records. Text analytics searches through this unstructured data to find phrases that typically indicate a subro case. By pinpointing subro opportunities earlier, one can maximize loss recovery while reducing the loss expenses.

continue …….

Settlement:

To lower costs and ensure fairness, insurers often implement fast-track processes that settle claims instantly. But settling a claim on-the-fly can be costly if one overpay.By analyzing claims and claim histories, one can optimize the limits for instant payouts. Analytics can also shorten the claim’s cycle times for higher customer satisfaction and reduced labor costs. It also ensures significant savings on things such as rental cars for auto repair claims.

Loss reserve:

When a claim is first reported, it is nearly impossible to predict its size and duration. But accurate loss reserving and claims forecasting is essential, especially in long-tail claims like liability and worker's compensation. Analytics can more accurately calculate loss reserve by comparing a loss with similar claims.

continue …….

Activity:

It makes sense to put your more experienced adjusters on the most complex claims. But claims are usually assigned based on limited data – resulting in high reassignment rates that affect the claim duration, settlement amounts and ultimately, the customer experience. Data mining techniques cluster and group loss characteristics to score, prioritize and assign claims to the most appropriate adjuster based on experience and loss type. In some cases, claims can even be automatically adjudicated and settled.

continue …….

Litigation:

A significant portion of the company’s loss adjustment expense ratio goes to defending the disputed claims. Insurers can use analytics to calculate a litigation propensity score to determine which claims are more likely to result in litigation. one can then assign those claims to more senior adjusters who are more likely to be able to settle the claims sooner and for lower amounts.

Why make analytics a part of your claims processing? Because as insurance becomes a commodity, it becomes more important for carriers to differentiate themselves. Adding analytics to the claims life cycle can deliver a measurable ROI with cost savings. Just a 1% improvement in the loss ratio for a $1 billion insurer is worth more than $7 million on the bottom line.

We’ve talked about what makes big data ‘Big’ and how access to SO much data can leave us feeling overwhelmed!! But when data analytics are divided into these four categories, understanding what is possible for your agency becomes much more manageable and time-friendly.

Through descriptive, diagnostic, predictive and prescriptive analytics methodologies, insurance firms can use all the data available to them and in turn, make their business more efficient while providing better care for their customers. Let's take a look at what each type of analytics mean and, more importantly, how each can help independent agents and its carriers, and the insurance industry as a whole.

• Descriptive Analytics and Insurance
• Diagnostic Analytics and Insurance
• Predictive Analytics and Insurance
• Prescriptive Analytics and Insurance

continue …….

Descriptive Analytics and Insurance

Descriptive analytics consist of any results capable of being analyzed and synthesized to further benefit a business such as page views and web activity, social interactions, blog mentions and more. According to the Information Week, more than 80 percent of the analytics business deal with, are descriptive and this is where the insurance carriers start in their analytics journey. Here is the video which is data focused and does a great job showing off Progressive’s big data capabilities.

Diagnostic Analytics and Insurance

Once insurance companies find the raw data that powers descriptive analytics, the next evolution in the analytics journey is turning those into diagnostic analytics. This means examining the data to answer the “why”. A common form of diagnostic analytics is ‘regression analysis’, which can be used to estimate the relationships among variables, drill-down analysis to discover a cause, and deep data mining to discover correlations.

continue ……

Predictive Analytics and Insurance

Predictive analytics find their power in their ability to maximize efficiency. Customers are happier when greeted by tailored, custom experiences. Employees are happier when they can provide customers with better service. Additionally, they help the insurance companies save money by predicting future events and saving more time to plan accordingly. Seeing the ‘what’ and the ‘why’ provided by descriptive analytics and diagnostic analytics allow the insurance carriers to anticipate trends and pivot so they are well-prepared.

continue ……

Prescriptive Analytics and Insurance

By using all the above-mentioned forms of analytics to better understand their customers, the likelihood of actions, and the ramifications for those specific events, insurance companies can use prescriptive analytics to optimize their strategies and improve their businesses. Prescriptive analytics recommend one or more courses of action which can be measured and refined based on the results. Prescriptive analytics are always evolving but are of crucial importance to put the rest of the work a company has done gathering and organizing data to its optimal use. An example of how prescriptive analytics are used in the healthcare industry is when providers measure clinically obese patients and then use risk factors for conditions such as high cholesterol and diabetes to determine where to focus the treatment.

Although life insurers are still in the early days of realizing the full potential of both big data and predictive analytics, many have their eyes on the prize and are taking aggressive steps to move-forward. Commitment will be as important as technology. The most successful companies will attract and retain the right people, develop an integrated strategy across business functions and invest wisely in reliable technology.