Discussion Questions:1.What are some ways that data mining could be used to detect fraud in health insuranceclaims?2.How could private insurance companies and public government agencies collaborate tocombat insurance fraud?What types of business skills would be necessary to define the rules for and analyze theresults from data mining?What business processes are necessary to complement the IS component of data mining?3.4. 1. Case Study #1: Combating Insurance Fraud with Data Mining and AnalyticsAbout 3% of the $2 trillion spent on health care in the United States is wasted on fraud everyyear. Insurers recover only a fraction of that $68 billion, but the information systems they use tospot suspicious claims are improving dramatically. Data mining and analytics are their mostimportant weapons. They arm the insurer's special investigative units with information aboutpotentially fraudulent billing patterns buried in millions of legitimate claims, spotting unusualtrends that no human being working alone could ever see.Health Care Service Corp. (HCSC), for example, implemented a fraud detection system thatdrew on software from IBM and SAS, and it paid off almost immediately. An allergist in Illinoiswas submitting fraudulent bills, but the individual amounts were never high enough to triggerany suspicion. Something was amiss, however, and the system helped senior investigator, MonePetsod, find it. Petsod drew a comparative analytics that showed what other allergists werecharging for the same procedures. "It was so different" she said of the Illinois practitioner'sbilling history, and that finding helped uncover the $800,000 scam.Fraud detection systems rely partly on rules developed by human beings, and partly on patternsand trends that the analytic engines detect. A key step is to spot fraud before any claim is paid,because it is much easier to deny payment than to recover funds that have already been paid out.The time window is short, however, given pressures on payers to reimburse quickly. Forexample, Medicare acknowledges paying almost $50 billion per year in questionable claims, afigure that is much higher than the private sector's fraudulent claims rate. Government agents goafter scammers once they see a pattern of abuse, but if the money is already paid, it is difficult torecover. Fraud detection systems, on the other hand, can operate quickly enough to catchsuspicious claims before they are paid.Although data mining and analytics are potent weapons, it takes time for insurance companyinvestigators to understand them and use them wisely. At HCSC, for example, the analysts mustwork closely with investigators to apply human judgment as they create new rules and followdata leads. Ôngoing training is essential, especially because the fraudsters continue to launchnovel and increasingly complex schemes, changing their tactics to stay a step or two ahead.Knowing when, where, and how to drill down into the data to see meaningful patterns is a skillthat agents must learn. But the investigators who master these skills will be able to combine theirown experience and judgment with an immensely powerful information system to help reducehealth care costs for everyone.

Question

Discussion Questions:1.What are some ways that data mining could be used to detect fraud in health insuranceclaims?2.How could private insurance companies and public government agencies collaborate tocombat insurance fraud?What types of business skills would be necessary to define the rules for and analyze theresults from data mining?What business processes are necessary to complement the IS component of data mining?3.4. 1. Case Study #1: Combating Insurance Fraud with Data Mining and AnalyticsAbout 3% of the $2 trillion spent on health care in the United States is wasted on fraud everyyear. Insurers recover only a fraction of that $68 billion, but the information systems they use tospot suspicious claims are improving dramatically. Data mining and analytics are their mostimportant weapons. They arm the insurer's special investigative units with information aboutpotentially fraudulent billing patterns buried in millions of legitimate claims, spotting unusualtrends that no human being working alone could ever see.Health Care Service Corp. (HCSC), for example, implemented a fraud detection system thatdrew on software from IBM and SAS, and it paid off almost immediately. An allergist in Illinoiswas submitting fraudulent bills, but the individual amounts were never high enough to triggerany suspicion. Something was amiss, however, and the system helped senior investigator, MonePetsod, find it. Petsod drew a comparative analytics that showed what other allergists werecharging for the same procedures. &#34;It was so different&#34; she said of the Illinois practitioner'sbilling history, and that finding helped uncover the $800,000 scam.Fraud detection systems rely partly on rules developed by human beings, and partly on patternsand trends that the analytic engines detect. A key step is to spot fraud before any claim is paid,because it is much easier to deny payment than to recover funds that have already been paid out.The time window is short, however, given pressures on payers to reimburse quickly. Forexample, Medicare acknowledges paying almost $50 billion per year in questionable claims, afigure that is much higher than the private sector's fraudulent claims rate. Government agents goafter scammers once they see a pattern of abuse, but if the money is already paid, it is difficult torecover. Fraud detection systems, on the other hand, can operate quickly enough to catchsuspicious claims before they are paid.Although data mining and analytics are potent weapons, it takes time for insurance companyinvestigators to understand them and use them wisely. At HCSC, for example, the analysts mustwork closely with investigators to apply human judgment as they create new rules and followdata leads. Ôngoing training is essential, especially because the fraudsters continue to launchnovel and increasingly complex schemes, changing their tactics to stay a step or two ahead.Knowing when, where, and how to drill down into the data to see meaningful patterns is a skillthat agents must learn. But the investigators who master these skills will be able to combine theirown experience and judgment with an immensely powerful information system to help reducehealth care costs for everyone.

Accepted Answer

Note: “Since you have posted a question with multiple sub-parts, we will solve first three sub-parts…