Project Power Point

1 MIS540- Innovation Through Technology Group Project

Team 5

Using Artificial Intelligence and Machine Learning Technologies to Improve Decisions and

Fraud Detection at JPMorgan Chase

Team 5 (Aquilnasha Jordan, Kathy Lampinen)

Devry University

MISS540

Dr. James Karagiannes

June 16, 2026

2 MIS540- Innovation Through Technology Group Project

Team 5

Table of Contents:

1. Executive Summary

2. Introduction

3. Project Plan

4. General Description of the Organization

5. Organizational Background

6. Description of Business Problem or Opportunity

7. Overview of the Technology Solution Category- Innovative Idea

8. Alternative Solutions and Recommendations

9. Performance Measurement Plan

10. Organizational Impact

11. Summary - Conclusions

12. Bibliography

3 MIS540- Innovation Through Technology Group Project

Team 5

Using Artificial Intelligence and Machine Learning Technologies to Improve Decisions and

Fraud Detection at JPMorgan Chase

Executive Summary

This report proposes an artificial intelligence and machine learning fraud-detection

system for JPMorgan Chase. The goal is to demonstrate the organization's ability to safeguard

the customer and minimize financial risk through the use of advanced analysis of data. The risks

of fraud are high as customers have become so reliant on digital banking, credit cards, mobile

payments, and online transfers. Although these services are convenient, they also offer the

opportunity for unauthorized transactions, stolen identities, and payment scams. The size of the

internet crime threat was illustrated by the number of internet crime complaints submitted to the

FBI, Internet Crime Complaint Center [FBI IC3] in 2024, which totaled 859,532 complaints,

with $16.6 billion in losses reported (Federal Bureau of Investigation, Internet Crime Complaint

Center [FBI IC3] 2025). The proposed solution enables business innovation, leveraging real-time

monitoring, behavior analysis, account risk scoring, and explainable alerts.

 

4 MIS540- Innovation Through Technology Group Project

Team 5

Introduction

The final project description is an explanation of the organization, business problem,

technology solution, implementation plan, alternative vendors, performance measures, and

organizational impact. The main goal is to present a practical solution that could be proposed to

decision makers or funding leaders. The project is a development of an existing business

direction that J.P. Morgan has identified as a means to enhance payment validation and combat

payment fraud, extending it to be used as an enterprise fraud-detection solution (J.P. Morgan,

2023).

Project Plan

JPMorgan Chase would need a structured project team to identify needs, test the system,

and implement the solution. The team would consist of nine people: project manager, AI/ML

engineer, data engineer, cybersecurity specialist, fraud operations specialist, compliance and

privacy officer, systems integration specialist, customer-service training lead, and executive

sponsor. The PM will oversee coordination of tasks and timelines, budget, risks, and stakeholder

communication. Effective project managers possess a variety of crucial skills and experience,

such as communication, risk management, coordinating with stakeholders, budgeting, regulatory

knowledge, and technology proficiency. If the data is of low quality, if the model is biased, if the

employees do not accept it, if the privacy rules are not respected, if the current payment

platforms are not integrated, etc., the project could fail. Audiencing, compliance review, vendor

support, and cybersecurity testing are all areas that should be outsourced. The most appropriate

methodology is agile development, with test cycles, pilot releases, feedback from fraud analysts,

and continuous improvement as fraud patterns evolve (Project Management Institute, n.d.).

5 MIS540- Innovation Through Technology Group Project

Team 5

General Description of the Organization

JPMorgan Chase & Co. is one of the largest financial-services organizations in the United

States and the global economy. It offers consumer banking, credit card, payment, commercial

banking, investment services and financial-management services. JPMorgan Chase has massive

customer and business transactions, making it a target for financial information, customer

account and payment systems to be defrauded. This is significant as banks are a common victim

of criminals exploiting false payment details, phishing, stolen identities and malware. AI and ML

can be used in banking systems to aid in fraud prevention, threat detection, process automation,

and cybersecurity decision-making, as illustrated by research (Eskandarany, 2024). Moreover,

JPMorgan's Account Confidence Score indicates that the firm has already started using AI and

ML to assess account risk before making payments (J.P. Morgan, 2025). This banking company

“JPMorgan Chase” functions through different business portions which includes investment

banking, commercial banking and consumer banking (JPMorgan Chase, 2025). Not only does

JPMorgan Chase have one of the largest customer bases and many transactions that occur a day,

it has plenty of support and creative time taking out for fraud detection and technology tools that

help secure a banking account.

Organizational Background and Business Problem

JPMorgan Chase is a major financial services organization with historical roots reaching

back to 1799. It is responsible for consumer banking, commercial banking, investment banking,

credit cards, payments, and wealth management (JPMorgan Chase & Co., n.d.). It has a

6 MIS540- Innovation Through Technology Group Project

Team 5

significant number of customers and transactions, requiring robust fraud prevention measures as

a key operational necessity. Financial fraud, such as phishing, transfer fraud, identity theft,

account takeover, and card transactions, is the primary issue. Most conventional fraud-detection

solutions are based on predetermined rules and manual screening. When criminals create new

fraud patterns, these methods can be slow, expensive, and less effective (Ali et al., 2022).

JPMorgan Chase requires a more intelligent system that learns from the data of the transactions

and can detect abnormal behavior and make quicker decisions before losses happen.

The main problem this proposal addresses is financial fraud. Unauthorized transactions,

payment details stolen, identity theft, fraudulent scams, account takeover, and fraudulent

transfers are examples of fraud. According to the FBI Internet Crime Complaint Center, there

were 859,532 Internet crime complaints and $16.6 billion in monetary losses in 2024, indicating

that financial crimes committed online are a significant issue (Federal Bureau of Investigation,

Internet Crime Complaint Center [FBI IC3], 2025). Most reported losses to IC3 in 2024 were

caused by cyber-enabled fraud, resulting in 333,981 complaints and $13.7 billion in losses (FBI

IC3, 2025). The numbers tell the tale of how technology is crucial to large banks to detect

suspicious activity before it's too late.

Payment-card fraud also is a direct issue to JPMorgan Chase since the firm offers credit

card and payment services. Although card-not-present fraud losses and cardholder fraud losses

have increased over the past few years, the Federal Reserve's research revealed that these loss

rates have continued to increase since the implementation of the chip-card technology in recent

years, despite improving card-present fraud losses (Hayashi, 2026). This will give JPMorgan

7 MIS540- Innovation Through Technology Group Project

Team 5

Chase an opportunity to enhance the capabilities for fraud detection in online, mobile and digital

payments.

Traditional fraud-detection methods are limited because they often rely on fixed rules,

manual reviews. The approaches can be expensive, time consuming and are less effective if the

fraud scheme evolves (Ali et al., 2022). The downside of a rule-based system is that criminals

can easily develop new fraud schemes, which may not be detected by such systems (Aljunaid et

al., 2025). One problem is unbalanced data as the number of fraudulent transactions is small

compared to regular transactions (Dang et al., 2021; Chen et al., 2025). Thus, AI and ML can

help JPMorgan Chase identify patterns where they don't exist and react quickly.

Technology Solution and Integration

The proposed solution is an AI- and ML-powered fraud-detection system using

behavior-based analysis, anomaly detection, payment validation screening, explainable AI, and

account confidence scoring. These checks would be performed in real time: payment amount,

payment history, device activity, account age, customer's location, payment frequency, and

known fraud signals. For instance, a regular customer purchases small items locally, but then

makes a large online purchase from a different device, the system can stop the transaction, alert

the customer, and pass the case on to a fraud analyst. The Account Confidence Score by

JPMorgan is a project that is feasible and in line with the current business practices of the

company, as it leverages AI and ML to evaluate the risk of an account before the payment is

made (J.P. Morgan, 2025). For responsible implementation, privacy, explainability, cybersecurity,

8 MIS540- Innovation Through Technology Group Project

Team 5

and bias controls are required (National Institute of Standards and Technology [NIST] 2023;

U.S. Department of the Treasury 2024a).

Alternative Solutions and Recommendation

Two alternatives are FICO Falcon Fraud Manager and SAS Fraud Management. FICO

Falcon provides AI and machine learning fraud models to help identify and detect fraud, region,

and portfolio (FICO, n.d.). SAS Fraud Management employs analytics and machine learning to

watch payments, nonmonetary transactions, and suspicious activity in real time (n.d., SAS

Institute). Both products provide good fraud analytics. However, the best way is to have a

tailored internal JPMorgan Chase AI/ML solution with selected vendor tools. This hybrid works

better because JPMorgan Chase already has all the payment information, customer behavior

information, capabilities for Account Confidence Score, and strict compliance requirements. The

basic system can be customized to meet the risk environment of JPMorgan Chase, with vendor

tools complementing that.

Performance Measurement Plan

Success should be measured using data gathered before and after implementation. These

data sources consist of the following: fraud-loss reports, transaction alerts, analyst review logs,

customer complaints, customer verification results, false-positive records, and confirmed fraud

cases. These are: Fraud-loss reduction, Detection accuracy, False-positive rate, Average review

time, Prevented-loss value, Customer satisfaction, and Number of compliance issues. These

measures must demonstrate the enhanced financial performance, customer experience,

operational efficiency, and responsible usage of AI (Uddin, 2025). A pilot is to be conducted

9 MIS540- Innovation Through Technology Group Project

Team 5

over a six to twelve-month period, and results should be compared with the previous

fraud-review process.

Organizational Impact

The solution would change JPMorgan Chase’s fraud-detection process from mainly

rule-based review to real-time, data-driven risk scoring. AI-generated alerts, explanations, and

risk scores would be provided to fraud analysts, enabling quicker and more consistent decisions.

Employee training would be required to communicate the reasons for transaction holds, alerts,

verification procedures, etc., clearly to customers. The teams of compliance and cybersecurity

would have to be monitored for privacy, fairness, explainability, third-party risks, and model

security (U.S. Department of the Treasury, 2024b). Additionally, the organization might require

an AI governance team to analyze the performance of the models and ethical dangers. The

system would enable employees to receive up-to-the-minute information and have more

pronounced "fraud risk" signals to give them better information for making decisions.

Summary and Conclusion

In conclusion, AI and ML offer JPMorgan Chase a practical way to reduce fraud losses,

protect customer accounts, and improve trust in digital banking. The proposed system combines

innovation with a business need through real-time monitoring, behavior analysis, anomaly

detection, and explainable decision support. Pilot testing, KPI tracking, model auditing, staff

training, and implementation in specific high-risk payment channels should be the next steps.

With responsible governance and careful implementation, JPMorgan Chase can make fraud

prevention faster and more reliable while maintaining customer confidence and regulatory

compliance.

10 MIS540- Innovation Through Technology Group Project

Team 5

References

Ali, A., Abd Razak, S., Othman, S. H., Eisa, T. A. E., Al-Dhaqm, A., Nasser, M., Elhassan, T.,

Elshafie, H., & Saif, A. (2022). Financial fraud detection based on machine learning: A

systematic literature review. Applied Sciences, 12(19), Article 9637.

https://doi.org/10.3390/app12199637

Federal Bureau of Investigation, Internet Crime Complaint Center. (2025). 2024 IC3 annual

report. https://www.ic3.gov/AnnualReport/Reports/2024_IC3Report.pdf

Federal Bureau of Investigation, Internet Crime Complaint Center. 2024 IC3 Annual Report.

FBI, 2025, https://www.ic3.gov/AnnualReport/Reports/2024_IC3Report.pdf

Hayashi, F. (2026, February 25). New data on card-present and card-not-present fraud rates in

the United States. Federal Reserve Bank of Kansas City.

https://www.kansascityfed.org/documents/14934/PaymentsSystemResearchBriefing26Ha

yashi0225.pdf

FICO. (n.d.). FICO Falcon Fraud Manager. Retrieved June 19, 2026, from

https://www.fico.com/en/products/fico-falcon-fraud-manager

J.P. Morgan. (2023, November 20). How AI will make payments more efficient and reduce fraud.

https://www.jpmorgan.com/insights/payments/security-trust/ai-payments-efficiency-fraud

-reduction

J.P. Morgan. (2025, May 14). Enhancing our trust & safety solutions with Account Confidence

Score.

https://www.jpmorgan.com/payments/newsroom/introducing-account-confidence-score

11 MIS540- Innovation Through Technology Group Project

Team 5

Dang, T. K., Tran, T. C., Tuan, L. M., & Tiep, M. V. (2021). Machine learning based on

resampling approaches and deep reinforcement learning for credit card fraud detection

systems. Applied Sciences, 11(21), Article 10004. https://doi.org/10.3390/app112110004

Eskandarany, A. (2024). Adoption of artificial intelligence and machine learning in banking

systems: A qualitative survey of board of directors. Frontiers in Artificial Intelligence, 7,

Article 1440051. https://doi.org/10.3389/frai.2024.1440051

J.P. Morgan. (2025, May 14). Enhancing our trust & safety solutions with Account Confidence

Score.

https://www.jpmorgan.com/payments/newsroom/introducing-account-confidence-score

JPMorgan Chase & Co. (n.d.). History. Retrieved June 19, 2026, from

https://www.jpmorganchase.com/about/our-history

National Institute of Standards and Technology. (2023). Artificial intelligence risk management

framework (AI RMF 1.0). U.S. Department of Commerce.

https://doi.org/10.6028/NIST.AI.100-1

Project Management Institute. (n.d.). Agile Practice Guide. Retrieved June 19, 2026, from

https://www.pmi.org/standards/agile

SAS Institute. (n.d.). SAS Fraud Management. Retrieved June 19, 2026, from

https://www.sas.com/en_us/software/fraud-management.html

Uddin, N. (2025). Role of AI in preventing financial crime: A comprehensive analytical review.

Journal of Economic Criminology. Advance online publication.

https://doi.org/10.1016/j.jeconc.2025.100200

12 MIS540- Innovation Through Technology Group Project

Team 5

U.S. Department of the Treasury. (2024a). Artificial intelligence in financial services: Report on

the uses, opportunities, and risks of artificial intelligence in the financial services sector.

https://home.treasury.gov/system/files/136/Artificial-Intelligence-in-Financial-Services.p

df

U.S. Department of the Treasury. (2024b, March 27). U.S. Department of the Treasury releases

report on managing artificial intelligence-specific cybersecurity risks in the financial

sector. https://home.treasury.gov/news/press-releases/jy2212