Claims:We Claim:
1) System and method for fraud detection in insurance by using artificial intelligence technology is comprising of components such as;
a) Fraud detection web application;
b) Electronic device with active internet connection;
c) Insurance Database – This database has all the records of insurance customers; and
d) Backend server – All data related to all insurer of insurance company is stored on server.
2) The system claimed in claim 1, analyses historical data of insurers.
3) The system claimed in claim 1, checks set of patterns of data of insurers.
4) The system claimed in claim 1, reduces counterfeit of claims.
, Description:Field of the invention:
The present invention is related generally to the insurance sector, and more particularly to system and method for fraud detection in insurance sector by using artificial intelligence technology.
Background of the invention:
Fraud in insurance is an illegal activity done by either buyer or seller for an insurance contract. It occurs when a seller or buyer makes false insurance claims in order to get benefits or compensation to which they are not entitled in real. It can be done by various type, but basically it is a serious crime in all jurisdictions.
In simple words, insurance fraud is an act committed to defraud an insurance process. When a claimant attempts to get some advantages or benefit which they are not entitled to or in other case an insurer knowingly refuses some benefit which is due, is considered as fraud. It is generally related to money.
The anti-fraud technology is common in among insurers. It reduces chance of frauds. But still it is not 100% fraud proof. Though most of insurers used it, still insurance sector experienced loss of money due to fraud.
There are a few systems having fraud detection features inventions, which are patented, are listed below.
US patent application US7813944B1 by Ho Ming Luk, Pamela E. Coates, Arati S. Deo, Sean M. Downs, Benjamin A. Friesen, Craig A. Nies, Anu K. Pathria discloses Detection of insurance premium fraud or abuse using a predictive software system. Detection of insurance premium fraud is provided by a predictive model, which uses derived variables to assess the likelihood of fraud for each policy. The predictive model produces a score, which is a measure of the likelihood of premium fraud or abuse. The predictive model is included in a system that accepts policies to be considered for scoring, selects which policies are appropriate for scoring, stores data about the policies in a database, uses the data to derive variables for the model, and processes and outputs the model scores and related information. A rule-based analysis, which detects specific inconsistencies in the data that are indicative of premium fraud, may also be part of the system. The model scores and red-flag indicators from the rule-based analysis may be further processed to provide customized output for users.
PCT patent application WO2016210122A1 by Shrinivas SHIKHARE discloses Insurance fraud detection and prevention system. A computer-implemented method and system for detecting possible occurrences of fraud in insurance claim data is disclosed. Historical claims data is obtained over a period of time for an insurance company. The fraud frequency rate and percentage loss rate for the insurance company are calculated. The fraud frequency rate and percentage loss rate for the insurance company are compared to insurance industry benchmarks for the fraud frequency rate and the percentage loss rate. Based on the comparison to the industry benchmarks, the computer system determines whether to perform predictive modeling analysis if the insurance company is within a first range of the benchmarks, to perform statistical analysis on the claim data if the insurance company is below the first range of the benchmarks or perform forensic analysis if the insurance company is above the first range of the benchmarks. Statistical analysis, predictive modeling or forensic analysis are then performed based on the benchmarks to determine possible occurrences of fraud within the insurance claim data.
US patent application US20110246229A1 by Debra Pacha discloses System and Method for Detecting Healthcare Insurance Fraud. A system and method for detecting healthcare insurance fraud is disclosed. The method includes creating a database containing source data related to at least one healthcare claim submitted for reimbursement, selecting data from the database to compare to a set of rules using an audit module, and comparing the selected data to the set of rules using the audit module. The method also includes using the audit module to automatically identify suspected fraudulent data when the selected data violates at least one rule of the set of rules and using the audit module to flag the fraudulent data. In addition, the method includes using the audit module to generate a report illustrating patterns of irregularities within the source data to visually identify the fraudulent data displayed within the source data by user-friendly graphs and charts, and generating at least one automated statement for display to identify the at least one rule of the set of rules that was violated by the selected data using a documentation module.
US patent application US20070294104A1 by Carmeli Boaz, James H. Kaufman, David C. Spellmeyer discloses System, Method, and Means, to Detect and Prevent Fraudulent Medical Insurance Claims. The invention provides a method for detecting and preventing fraudulent medical insurance claims comprising storing identifying information and medical transaction histories on a portable device and on a server. The portable device is presented by a valid patient user to an authorized medical care provider. Medical transaction histories stored transaction histories are detected from the portable device and server. Medical transactions histories stored on the device are compared with those stored on the server. When the transaction histories on each device do not match, potential fraudulent medical insurance claims are detected.
Though the prior art patents disclose Detection of insurance premium fraud or abuse using a predictive software system, Insurance fraud detection and prevention system, System and Method for Detecting Healthcare Insurance Fraud and System, Method, and Means, to Detect and Prevent Fraudulent Medical Insurance Claims, they do not give any perfect solution for fraud detection system for insurance sector.
Artificial intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The term may also be applied to any machine that exhibits traits associated with a human mind such as learning and problem-solving.
Object of the invention:
The primary object of the present invention is to provide system and method for fraud detection in insurance sector by using artificial intelligence technology.
Another object of the present invention is to provide system and method for fraud detection in insurance sector which analyses historical data of insurers.
Another object of the present invention is to provide system and method for fraud detection in insurance sector which check set of pattern data of insurers.
Another object of the present invention is to provide system and method for fraud detection in insurance sector which reduces counterfeit.
Another object of the present invention is to provide system and method for fraud detection in insurance sector which eliminates double booking/ spending.
Summary of the invention:
The present invention discloses system and method for fraud detection in insurance sector by using artificial intelligence technology. System and method for fraud detection in insurance sector is comprising of;
Fraud detection web application
Backend Server – All data related to all insurer of insurance company is stored on server
Insurance Database – This database has all the records of Insurance customers
Any Electronic device which has active internet connection
Insurance company manager opens the web application of fraud detection on any electronic device which has active internet connection. Manager check application which is come for approval of insurance claims. Firstly, manager checks documents submitted by insurer. Then it checks for premium instalment is paid or not. For any application, with the help of artificial intelligence technology, manager checks whether past and present data of insurer is matching or not. Also, it checks all set of pattern data of insurer to clarify whether this insurer is the same who buy the policy. If there is negative result found then manager will make comment as fraud application.
Brief description of the drawings:
Fig. 1 illustrates flowchart of system and method for this invention.
Detailed description of the invention:
The present invention discloses system and method for fraud detection in insurance sector by using artificial intelligence technology.
Artificial intelligence (AI) emphasizes the development of intelligence machines, thinking and working like humans such as: speech recognition, problem-solving, learning and planning.
The goal of Artificial Intelligence is mainly reasoning, knowledge representation, planning, learning, natural language processing, perception and the ability to move an manipulate objects. Artificial intelligence main goal is the general intelligence.
The present invention discloses system and method for fraud detection in insurance sector by using artificial intelligence technology is comprising of;
Fraud detection web application
Backend Server – All data related to all insurer of insurance company is stored on server
Insurance Database – This database has all the records of Insurance customers
Any Electronic device which has active internet connection
The embodiment of present invention discloses system and method for fraud detection in insurance sector includes backend server. This backend server contains all data related to all customer of insurance company. For fraud detection, the application check database for particular insurer which is stored on backend server.
Fig. 1 illustrates system and method for fraud detection in insurance sector by using artificial intelligence technology is comprising of the steps are as;
Step 1) Insurance company manager opens the web application of fraud detection
Step 2) Manager check the list of applications which are file for insurance claim shown on the screen
Step 3) Manager select one application from the list
Step 4) Manager checks for premium instalments are completed or not
Step 5) Manager checks for documents submitted by user
Step 6) With the help of artificial intelligence technology, manager checks data patterns of data belonging to applicants
Step 7) If there is any negative result found then system generate fraud message on screen of electronic device
Step 8) Manager put this particular application in fraud application list
The embodiment of present invention checks insurance claims application for 5 types of frauds claims, to ensure that the application is not fraud. These 5 types of fraud are as follows:
False Claims – The system firstly checks for false claims. This is the one of the most common types of insurance fraud. Claiming for an accident which not happened in real. These occurs number of ways and for a number of reasons also. For example, Slip and fall claims is one of the common types of staged accident, in which it is really hard to prove or disprove whether it is real or not. For vehicle insurance, sometimes vehicle owner themselves damage the vehicle and make an accident claim. Sometimes homeowners also claim for planned accidents or property damage. Sometimes, a building which is insured is less worth than it is insured for.
Inflated Claims – It is generally related to natural disasters. These claims are more in number when there is any natural disaster happens which affect large area or region such as flood, earth quake, fire.
Disaster claims – In any disaster chaos ensues which results in wide range of fraudulent activities. In this situation it is very difficult for insurance company to go personally for checking and investing each and every claim. In this disaster condition insurance company depend on data provided by insurer. But sometimes it may happen home or other property remain intact in affected area and policy holders still submit claims application which is not checked by insurance company.
Faked Death – Most commonly faking news of claimant death is a type of fraud where policyholder take large life insurance policy for themselves and then spread fake news of their own death. And when insurance remuneration gets, they go to other place and start living there with different name.
Insurance Company Fraud – It is the not the case that all insurance fraud is committed by policyholders sometimes it is also committed by insurance agents or agencies. It includes premium diversion and fee churning. Premium diversion is an act where insurance agents or agencies keep policyholder’s premium rather than sending it to the underwriters. In other case, insurance agents which is not licensed, sell insurance then collect the premiums and after that refuse to pay claims. Fee churning happens when an insurance agent continually changes a life insurance policy to different insurance companies for getting the commission. In some cases, insurance agents move policy around to get a good commission for themselves from various companies and dur to which policy holder’s premiums often go rise as life insurance get more expensive as age of insurer is older and its coverage get down.
The present invention discloses the system and method for fraud claiming in insurance sector check whether the applicant is not the case for these 5 types of fraud claims. If insurance company manager found any one suspicious, then he/she comment it as a fraud claim and place this particular application into fraud claim list.
The present invention discloses the system and method for fraud detection in insurance sector has some advantages:
Due to artificial intelligence technology, claim evaluation and fraud detection is investigated more deeply. It detects fraud at very early stage which reduces industrial costs and affect insurance premiums positively.
It shields their customers from frauds or criminals who plot against them.
It checks data pattern to confirm the Genuity of insurer and claims in large range of claims cause by disaster.
As artificial intelligence process data quickly, claim application checking and investigating is done very quickly and it accelerate the claims process which resolves better insight in claims renumeration.
The present invention can be better understood with the help of examples.
Example 1:
Insurance company manager opens the web application of fraud detection on any electronic device which has active internet connection. Manager check application which is come for approval of insurance claims. That application is related to death of insurer. Firstly, manager checks documents submitted by insurer’s nominee. Then it checks for premium instalment is paid properly or not. With the help of artificial intelligence technology, manager checks whether past and present data of insurer is matching or not. Also, it checks all set of pattern data of insurer to clarify whether this insurer is the same who buy the policy. Manager found that past data and present data of insurer is not matching, there is something which is suspicious then manager comment as fraud claims and keep that claim application in fraud list.
Example 2:
Insurance company manager opens the web application of fraud detection on any electronic device which has active internet connection. Manager check application which is come for approval of insurance claims. That application is related to vehicle insurance. Firstly, manager checks documents submitted by insurer. Then it checks for premium instalment is paid properly or not. With the help of artificial intelligence technology, manager checks whether past and present data of insurer is matching or not. Also, it checks all set of pattern data of insurer’s vehicle is matching or not. Manager found that vehicle is not facing any type of accident or damage and documents and proof is not correct, there is something which is suspicious then manager comment as fraud claims and keep that claim application in fraud list.
It should be kept in mind that the described embodiment(s) is only presented by way of example and should not be construed as limiting the inventive concept to any particular physical configuration.
The present invention is not limited to components, which is mentioned in the description. Based on the same concept, fraud detection system in insurance sector application can be built. Those who are familiar in the art will understand that a number of variations may be made in the disclosed embodiments, all without departing from the scope of the invention, which is defined solely by the appended claims.