Senior Data Scientist, ML— Fraud Prevention

Written by the T&S Network from Adobe's posting.

Builds and evaluates machine learning models for fraud and abuse detection, covering the full fraud lifecycle from ground-truth labeling and modeling through performance measurement and monitoring. The role sits in a fraud detection and effectiveness team and works with engineering, product, policy and risk teams to improve detection and quantify business impact.

• Fraud and scams

What you'd do

• Tune classical and statistical ML models that catch fraud and abuse.
• Create the datasets, metrics and assessment methods used to judge how well models and controls work.
• Analyze false positives and false negatives, model drift and emerging fraud patterns.
• Define ground truth, labeling approaches and fraud taxonomies for model development and evaluation.
• Run experiments weighing precision, recall, customer impact and fraud loss.
• Build dashboards that translate detection performance into business impact.
• Check models and data for leakage, bias and data-quality problems that could mislead results.

What it asks for

• 8 years in applied data science or ML, including building and evaluating production models.
• Strong grounding in statistical and classical ML, experimentation and performance measurement.
• Strong hands-on Python and SQL with large, complex datasets.
• Experience with model monitoring, drift, and imperfect or delayed labels.
• Strong data visualization and ability to present findings to leadership.
• Bachelor's in statistics, math, computer science or related field; advanced degree a plus.

Terms in this role

Prevalence.

How often people see violating content, usually counted as views of it per 10,000 views. A common way to measure enforcement.

Our best summary of the posting, and it can be wrong. The employer's posting is what counts: read it in full on Adobenorth_east before you apply. If we got something wrong, report this listing.