Data Scientist: Predictive Analytics for Risk & Fraud

Talentify; Minneapolis (MN); On-site; USD 77,000 - 129,000; Full time

Benefits offered by this job

Health Benefits

401(k) with match

Employee Share Purchase Plan

Wellbeing platform

Disability Insurance

Life Insurance

Critical Illness

Hospital Indemnity

Family Benefits

Health Savings Account

Dependent Care Accounts

Commuter Spending Accounts

Paid Time Off & Volunteer Leave

Job summary

LexisNexis Risk Solutions is seeking a Data Scientist to lead predictive modeling across risk and fraud. You will develop machine learning models using R, Python, SAS, and SQL, and build cloud-based analytic solutions integrated into enterprise systems.

The role emphasizes analyzing large datasets, validating scoring code with stakeholders, and documenting methodologies to ensure model accuracy and reproducibility.

Qualifications

• BS in CS/Statistics/Math or related field
• Experience in predictive modeling
• Proficiency in SAS, R, Python and Big Data
• Strong communication and cross-functional collaboration
• Fraud analytics experience is a plus

Responsibilities

• Build and deploy machine learning models using R, Python, SAS, and SQL.
• Develop cloud-based analytic solutions and integrate into enterprise systems.
• Analyze large datasets to uncover insights and support product development.
• Collaborate with stakeholders to validate scoring code and ensure model accuracy.
• Document methodologies and follow best practices in statistical modeling.

Skills

Predictive modeling

R

Python

SAS

SQL

Big Data

Communication

Cross-functional work

Education

CS/Stats/Math degree

Tools

SAS

R

Python

Big Data technologies

Cloud platforms

Job description

LexisNexis Risk Solutions is seeking a Data Scientist to lead predictive modeling across risk and fraud. You will develop machine learning models using R, Python, SAS, and SQL, and build cloud-based analytic solutions integrated into enterprise systems.

The role emphasizes analyzing large datasets, validating scoring code with stakeholders, and documenting methodologies to ensure model accuracy and reproducibility.