1-2 Final Project Milestone

docx

School

Southern New Hampshire University *

*We aren’t endorsed by this school

Course

610

Subject

Business

Date

Apr 3, 2024

Type

docx

Pages

Uploaded by MinisterAlligator3067

1 1-2 Final Project Milestone One: Develop an Operational Risk Management Proposal Anastasia Bolinaga Southern New Hampshire University DAT 610: Optimization and Risk Assessment Professor Kyle Camac March 2, 2024

2 1. Organizational Background and Goals Using the most recent data analytics techniques, XYZ, a property and casualty insurance firm, has already developed robust risk management systems for the areas of market, credit, and insurance risks. The company leadership decided to create an operational risk management program after realizing that operational losses were higher than expected as a result of fraudulent claims from car accidents and personal injury claims (SNHU DAT-610-Module One, 2024). Operational risk is defined as “the risk of loss resulting from inadequate or failed processes, people and systems or from external events” (Girling, 2022). This program is anticipated to function at the same high caliber as the current credit, market, and insurance risk programs. All programs are to be reported to a single Chief Risk Officer (CRO) in a standardized consolidated way (SNHU DAT-610-Module One, 2024). 2. Established Programs, Policies, Strategies, and Practices When it comes to the operational risk analysis, XYZ currently utilizes a special investigations unit (SIU) for investigating claims that are flagged to be potentially fraudulent since most operational losses come from this category (SNHU DAT-610- Module One, 2024). Investigating suspicious claims is in line with industry standards as all insurance companies now prioritize preventing fraud. It was estimated that the US pays out about one-fifth of auto insurance claims to fraudsters every year (Aslam et al., 2022). The main challenge that XYZ is facing is that their SIU is not capable of handling all incoming suspicious claims in a timely fashion. Another challenge is that currently there is no process on ranking the incoming suspicious claims to categories from least to most suspicious or from lower to higher claim cost. This prevents SIU

3 from prioritizing the claims to be investigated (SNHU DAT-610-Module One, 2024). Finding fraud in an automated, high-volume online transaction processing environment without compromising automation's benefits in terms of effectiveness, speed, and customer service is one of the main issues facing modern fraud detection (Viaene et al., 2007). 3. Recommended Techniques and Practices It is recommended to establish an automated process of detecting high fraud risk and suspicious claims with high cost to be automatically given to SIU for processing. There should also be a process for managers or supervisors of claim handling departments to forward suspicious claims outside of these categories to SIU. Claims worked by SIU should not be allowed to be paid without SIU’s approval which can be accomplished by assigning specific claim flags in the Fraud Detection system, e.g., “Fraud”, “NoFraud”, “Suspicious Fraud but not proven”, etc. (Stavrinoudakis, 2018). Insurance fraud identification has always been difficult, mostly because of the skew known as class imbalance, which occurs because the frequency of frauds is much lower than the total number of claims and each instance of fraud is unique in its own way. Another obvious challenges in fraud detection are missing data or hard to evaluate categorical data. Numerous studies show that algorithm quality is not as important to forecast accuracy as the quantity and quality of data that is accessible, that is why it is also recommended to perform an audit of the existing data for data accuracy and completeness ( Predictive Analytics for Insurance Fraud Detection - WiPRO, n.d.). The importance of adopting automated fraud detection techniques should not be underestimated. The most recent ABI data on detected general insurance fraud shows

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

4 that the rate of fraud detection is rising yearly. For example, vehicle fraud detection rates climbed by 0.55% to 2.05% during the pandemic outbreak, despite a fall in the overall number of motor insurance claims (Rohn, 2024). 4. Support for Enhancement of Risk Assessment Potential It's obvious that traditional methods of managing fraud —sampling, testing, and risk assessment without a thorough plan of action—may not be sufficient for today's firms given the speed at which change is occurring. Organizations should instead consider a strategy known as enterprise fraud management (EFM). In order to proactively monitor the company and brand, EFM primarily entails using increasingly complex analytical approaches to substantially larger volumes of operational and third-party data ( Analytics Innovations in Enterprise Fraud Management (EFM) , n.d.). The application of data analytics to risk management entails gathering, organizing, and interpreting enormous volumes of data in order to recognize, evaluate, forecast, control, and avert risks inside a company. It makes use of a variety of data sources, including external data sets, historical records, and real-time information, to find correlations, patterns, and trends that could indicate possible threats. Implementing the use of data analytics in operational risk management will enable XYZ to proactively address risks and put appropriate measures in place to limit or prevent harm to their business processes (Belova & Belova, 2023).

5 References Analytics innovations in enterprise fraud management (EFM) . (n.d.). Deloitte United States. https://www2.deloitte.com/us/en/pages/advisory/articles/analytics-innovations-in- enterprise-fraud-management.html Aslam, F., Hunjra, A. I., Ftiti, Z., Louhichi, W., & Shams, T. (2022). Insurance fraud detection: Evidence from artificial intelligence and machine learning. Research in International Business and Finance , 62 , 101744. https://doi.org/10.1016/j.ribaf.2022.101744 Belova, K., & Belova, K. (2023, July 10). How to use data analytics in risk Management . PixelPlex. https://pixelplex.io/blog/data-analytics-in-risk-management/ Girling, P. X. (2022). Operational risk management: A Complete Guide for Banking and Fintech . John Wiley & Sons. SNHU DAT-610-Module One (2024, March). 1-2 Final Project Milestone One: Develop an Operational Risk Management Proposal . https://learn.snhu.edu/d2l/lms/dropbox/user/folder_submit_files.d2l? db=2730484&grpid=0&isprv=0&bp=0&ou=1504594 Predictive Analytics for Insurance Fraud Detection - WiPRO . (n.d.). https://www.wipro.com/analytics/comparative-analysis-of-machine-learning-techniques- for-detectin/ Rohn, S. (2024, January 5). The Future of Insurance Fraud Detection is Predictive Analytics . The Whatfix Blog | Drive Digital Adoption. https://whatfix.com/blog/insurance-fraud- detection/ Stavrinoudakis, S. (2018, March 22). Insurance fraud: a practical guide to tackle it - operational processes and automated controls. Bright Data.

6 https://blogs.sas.com/content/brightdata/2017/03/03/insurance-fraud-operational- processes-automated-controls/ Viaene, S., Ayuso, M., Guillén, M., Van Gheel, D., & Dedene, G. (2007). Strategies for detecting fraudulent claims in the automobile insurance industry. European Journal of Operational Research , 176 (1), 565–583. https://doi.org/10.1016/j.ejor.2005.08.005

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Related Documents

HRM 310 6.2 Assignment Changing Work Environment.docx

QSO 321 Module Three Assignment.docx

HRM 300 5.2 HR Inbox.docx

Case swot starbucks - Copy.docx

2-1 Module Two Exercise_Introduction to Risk Management Analyses Using R.docx

3-2 Final Project Milestone Two_ERM.docx

HRM 310 7.1 Project Two Investigation Process.docx

5.1 HR Learning Journal Attraction and Recruitment Strategies.docx

HRM 310 7.1 Project Two Union Grievance.docx

HRM 300 2.2 Milestone One Assignment.docx

HRM 310 6.3 Assignment Create a Workplace Policy.docx

HRM 300 4.2 Project one.docx

Recommended textbooks for you

Management, Loose-Leaf Version

Management

ISBN:9781305969308

Author:Richard L. Daft

Publisher:South-Western College Pub

Understanding Management (MindTap Course List)

Management

ISBN:9781305502215

Author:Richard L. Daft, Dorothy Marcic

Publisher:Cengage Learning

Principles of Management

Management

ISBN:9780998625768

Author:OpenStax

Publisher:OpenStax College

Foundations of Business (MindTap Course List)

Marketing

ISBN:9781337386920

Author:William M. Pride, Robert J. Hughes, Jack R. Kapoor

Publisher:Cengage Learning

Foundations of Business - Standalone book (MindTa...

Marketing

ISBN:9781285193946

Author:William M. Pride, Robert J. Hughes, Jack R. Kapoor

Publisher:Cengage Learning

SEE MORE TEXTBOOKS

Recommended textbooks for you

Management, Loose-Leaf Version
Management
ISBN:9781305969308
Author:Richard L. Daft
Publisher:South-Western College Pub
Understanding Management (MindTap Course List)
Management
ISBN:9781305502215
Author:Richard L. Daft, Dorothy Marcic
Publisher:Cengage Learning
Principles of Management
Management
ISBN:9780998625768
Author:OpenStax
Publisher:OpenStax College
Foundations of Business (MindTap Course List)
Marketing
ISBN:9781337386920
Author:William M. Pride, Robert J. Hughes, Jack R. Kapoor
Publisher:Cengage Learning
Foundations of Business - Standalone book (MindTa...
Marketing
ISBN:9781285193946
Author:William M. Pride, Robert J. Hughes, Jack R. Kapoor
Publisher:Cengage Learning