How are you using analytics in your Insurance company? How are your competitors?

New data and technology is driving the re-invigoration of Analytic models and creating new one to one customer models in Insurance. Telematics provides insurance companies with more information to assure the competence and risk of your driving style. The easy and readily available information about flood zones has already disrupted the insurance market.

Such data is allowing new incumbents to focus on less risky properties, segmenting and “stealing” customers from the larger insurers; to challenging Insurance policy advisers about the state of mutuality.


Analytics in insurance is undergoing a paradigm shift from reporting and dashboards to advanced analytics, which uses the knowledge captured in the historic data of the past to predict and optimize the future. Insurance analytics can be employed to detect and prevent fraudulent claims, to optimize the perfect mix for a product by identifying the attributes that targeted customer segment most desired in a product, opportunities of cross sell, customers satisfaction level, Customer’s profitability etc.

Some of the areas where insurance companies have successfully used analytics are :

  1. General Liability Claims: Predictive models can be used to predict propensity of claimant to require and hire legal for the settlement of claims. This can help the insurance company to control the percentage of cases going to court, saving cost and operational time.
  2. Subrogation analysis: Subrogation refers to an insurance company seeking reimbursement from the person or entity legally responsible for an accident after the insurer has paid out money on behalf of its insured. Predictive Modelling can help the insurance companies to identify missed recoveries associated with payments.
  3. Severity analysis: Predictive modeling is used to rank the claim on the basis of financial and customer service impact. Timely treatment and proactive intervention can help the insurance company to optimize the usage of resources, thus minimize the cost as well as can maximize the customer experience.
  4. Application Fraud Detection Algorithms: Early Identification of fraud at the application level itself will help the insurance companies to reduce the number of fraud claims and save huge amount of money.
  5. Litigation Cost and Cycle Time Analysis: Insurance companies often employ external legal help to resolve litigation. Usually they use the judgmental factor for assigning claim to external legal firm. Predictive Models can help the insurance companies to devise more comprehensive business rule to assign a litigated claim to outside legal counsel team.

…. and so many more….

These are all beyond the more usual and typical CRM and consumer analytics that you see in many industries:

  • Customer Response Modelling
  • Market Mix Modelling
  • Campaign Management
  • Cross-sell and Up-sell Analytics
  • Loyalty Management and Customer Lifetime Values (LTV) Analysis
  • Collection Analytics and Delinquency Modelling
  • Churn Prediction and Retention Modelling
  • Renewal of Lapse Policies