Senior Fraud Analytics Scientist — ML Leader

Enova International; Chicago (IL); Hybrid; USD 106,000 - 140,000; Full time

Benefits offered by this job

In-office hybrid schedule

Health, dental, and vision insurance

401(k) matching + Roth option

PTO & paid holidays

Sabbatical program

Summer hours

Paid parental leave

DEI groups

Employee recognition program

Charitable matching and volunteer day

Job summary

Enova International is seeking a Lead Data Scientist to drive fraud analytics across lending products. You will develop and deploy models, work with Fraud Operations to surface patterns, and iterate on features based on investigation results.

You will apply advanced Python and SQL to large-scale data, translate findings into business strategy, and partner with senior stakeholders while guiding a small team through an iterative detection loop that improves underwriting and verification from a

Qualifications

• 5+ years of analytics, applied machine learning, or quantitative modeling.
• Hands-on fraud experience in fintech or lending.
• Experience translating analysis into business strategy and communicating with senior stakeholders.
• Proven leadership in mentoring teammates and driving team initiatives.

Responsibilities

• Develop, deploy, and monitor models to detect fraud trends across lending products.
• Write Python programs for data analysis and predictive modeling; query large datasets in SQL.
• Collaborate with Fraud Operations to refine features and reduce false positives/negatives.

Skills

Fraud analytics

Leadership

Data analysis

Communication

Tools

Python

SQL

Job description

Enova International is seeking a Lead Data Scientist to drive fraud analytics across lending products. You will develop and deploy models, work with Fraud Operations to surface patterns, and iterate on features based on investigation results.

You will apply advanced Python and SQL to large-scale data, translate findings into business strategy, and partner with senior stakeholders while guiding a small team through an iterative detection loop that improves underwriting and verification from a