Data Scientist, Card Testing & Distributed Fraud

Key Skills

Analytical and Problem solving, Data science techniques, Large data sets, Machine learning techniques, Python Programming, R Programming, SPARK Programming, SQL

Job Description

About the Team

Payment Fraud Data Science helps keep Stripe free from fraud by prototyping and optimizing machine learning models and making data driven policy recommendations from analyzing large amounts of data. We’re looking for data scientists with a passion for analyzing data, prototyping models, and running experiments to prevent fraud and card testing on Stripe. You can find more information about Card Testing in this recent blog post from Stripe, How Stripe responded to a wave of card testing attacks. 

What you'll do

In this role, you’ll work closely with our partner Engineering and Product teams to improve Stripe’s fraud and card-testing defenses at scale. Recent team projects include developing a system for dynamically setting model thresholds based on real time signals; optimizing model hyper-parameters based on data collected in online-experiments; and semi-automated label generation. 

Responsibilities

You will:

• Partner closely with Product, Engineering, Risk and other Data Science teams to analyze and visualize data, prototype models, and run experiments.
• Coordinate and potentially lead data-driven responses to fraud attacks. 
• Develop and scale innovative datasets that can be used for near real-time fraud alerting and model training.
• Interpret complicated patterns in data and communicate accurate, actionable recommendations to partner teams.

Who you are

The ideal candidate has experience in analytics and statistical modeling, values rigor in data and modeling and is passionate about leveraging ML techniques.

Minimum requirements

• 5+ years experience working with and analyzing large data sets to solve problems 
• PhD or MS in a quantitative field (e.g., Economics, Statistics, Engineering, Natural Sciences, Operations Research)
• Expert knowledge of SQL and a scientific computing language (such as R or Python)
• Strong knowledge of machine learning, statistics, and optimization
• Demonstrated track record of identifying and executing on impactful data science projects with cross-functional partners
• Ability to communicate complex quantitative analysis in a clear, precise, and actionable manner

Preferred qualifications

• Experience working with engineering to deploy model prototypes to production and adjust model thresholds to improve performance.
• Experience designing, running, and analyzing experiments to optimize hyper-parameters.

Hybrid work at Stripe

Our Chicago, Dublin, and Singapore teams spend at least 50% of their time in their local offices. We believe that more in-person interactions will contribute to better results for our employees and Stripe. Increased office time allows for improved collaboration, efficiency, and informal learning opportunities, fostering a stronger community and building our culture. We will apply the insights gained from these initial three locations to continue refining our hybrid approach.

Pay and benefits

The annual US base salary range for this role is $168,691 - $228,229. For sales roles, the range provided is the role’s On Target Earnings (OTE) range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role. This salary range may be inclusive of several career levels at Stripe and will be narrowed during the interview process based on a number of factors, including the candidate’s experience, qualifications, and location. Applicants interested in this role and who are not located in the US may request the annual salary range for their location during the interview process.