Fraud Risk Analyst

Fiserv•Berkeley Heights, NJ

About The Position

As a successful Fraud Risk Analyst, you will be responsible for executing analytical based processes to detect fraud attacks, analyze impacts, determine effective prevention and mitigation and monitor the performance of the fraud risk ecosystem. Additionally, you will conduct analysis relative to root cause evaluation and associated observed volumes as well as financial and operational impacts with associated recommended remediation paths. You will ultimately create fact and data-based insights, which will be used to inform and influence change across the organization.

Requirements

Bachelor’s degree in Business and/or Computer Science or equivalent work experience.
3+ years of related work experience in Fin Tech, Ecommerce, Banking and/or fraud prevention.
3+ years of experience as a Data Analyst.
Competency in Python/PySpark/SQL and/or comparable data analysis skills in Snowflake, Palantir, AWS, Azure, Splunk, PowerBI, Actimize and/or other Fraud Prevention Platform building Fraud Prevention Rules and Artificial Intelligence Machine Learning models.
Experience mining complex datasets and generating business reports.
Experience developing, creating and presenting complex concepts and outcomes to senior leaders in support of a positive ROI and decreasing Fraud.
Must currently possess valid and unrestricted U.S. work authorization to be considered for this role. Individuals with temporary visas including, but not limited to, F-1 (OPT, CPT, STEM), H-1B, H-2, or TN, or any candidate requiring sponsorship, now or in the future, will not be considered for this role.

Nice To Haves

Master's degree in Computer Science or a related field.
Fraud Certification in ACAMS CAFS, ACFE.
Coding Certification and/or documented supporting use case, education.

Responsibilities

Enhance and execute analysis for identifying new fraud attacks, detect attack signatures and determine root cause of fraud events observed or attempted in the network using data associated with cardholder accounts that includes both financial and non-financial data.
Maintain and monitor a robust suite of early warning monitors to systemically identify abnormal activity and possible pre-cursor attack activity; produce monitors via dashboards, daily monitoring reports and ad-hoc reporting.
Quickly source, analyze and deduce root cause and effective mitigation options consistently and accurately across the network.
Manage fraud ecosystem measures to monitor the effectiveness and performance of all fraud controls.
Conduct ad-hoc analysis to ensure accuracy and speed by maintaining a robust set of analytical capabilities and datasets.