Chapter 2: Data to Insights to Decisions
No description yet. This curated deck is ready for daily study.
Card preview (7)
What are the potential analytics solutions to motor insurance fraud?
-Claim prediction - Member prediction -Application prediction -Payment prediction
What are the key questions required to convert a business problem into an analytics solution?
-What is the business problem? (org not always sure, should be expressed in business terms and have nothing to do with analytics) -What are the goals the business wants to achieve? -How does the business currently work? (situational fluency, understand the business well enough to converse with partners) -In what ways could a predictive data analytics model help to address the business problem? (explore possibilities)
What are the questions involved in evaluating the feasibility of a proposed analytics solution?
-Is the data required by the solution available or could it be made available? -What is the capacity of the business to utilize the insights the analytics solution will provide?
What will claim prediction do?
A model could be built to predict the likelihood that an insurance claim is fraudulent
What will member prediction do?
A model could be built to predict the propensity of a member to commit fraud in the near future
What will application prediction do?
A model could be built to predict, at the point of application, the likelihood that a policy someone has applied for will ultimately result in a fraudulent claim
What will payment prediction do?
A model could be built to predict the amount most likely to be paid out by an insurance company after having investigated a claim