Analytics Analyst - Fraud (Hybrid)

Enova•Chicago, IL

1d•Hybrid

About The Position

As an Analyst on Enova’s Fraud Analytics team, you’ll use data to help prevent fraud across the company’s lending products. You’ll develop, enhance, test, deploy, and monitor models and pattern-recognition pipelines that identify emerging and changing fraud trends. You’ll work closely with Fraud Operations: investigation results, including false positives and false negatives, feed back into the analytics process so you can refine identifying characteristics and improve detection. The role also involves analyzing large datasets, recommending risk and verification strategies, communicating findings to cross-functional partners, and supporting implementation. Enova describes its analytics department as comprising 100 quantitative professionals and emphasizes a data-driven culture focused on using analytics to provide access to credit while managing risk. This hybrid role requires in-office work Tuesday through Thursday and allows remote work on Mondays and Fridays. Visa sponsorship and sponsorship takeover are not available.

Requirements

Bachelor’s degree in a quantitative field such as Statistics, Mathematics, Economics, or Computer Science, or equivalent experience.
Solid programming skills for data analysis, demonstrated through work, internships, coursework, or personal projects.
Working knowledge of relational databases and SQL.
Foundational knowledge of statistical methods and machine learning.
Comfort using AI tools to improve workflow and delivery.
Strong problem-solving instincts and an inquisitive, dig-deeper mindset.
Interest in fraud, fintech, or lending; prior experience is not required.

Nice To Haves

Prior exposure to fraud, fintech, or lending.

Responsibilities

Develop, deploy, and monitor models and pattern-recognition algorithms to detect emerging and shifting fraud trends across lending products.
Write customized Python programs for data analysis and predictive modeling, and query large, complex datasets using SQL.
Partner with Fraud Operations throughout the detection process, assembling data, surfacing suspicious patterns, and incorporating investigation results to refine features and reduce false positives and false negatives.
Conduct ad hoc analysis of large, complex datasets to assess new or changing fraud trends and recommend risk, verification, and operational strategies.
Communicate findings to cross-functional partners, provide requirements, and support implementation.
Help improve underwriting and verification processes from a fraud-risk perspective.