Creditspring
Applied Data Scientist – Fraud Prevention
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
Applied Data Scientist – Fraud Prevention
Senior Applied Data Scientist & Business Analyst (Fraud Prevention) – Credit Underwriting @ Creditspring
We are Creditspring, a FCA-regulated consumer credit company offering safe, short-term financial products designed to empower members—not customers—with financial security.
As one of the UK’s only subscription-based lending companies, we innovate to enhance members’ financial stability, tackle predatory financing, and build sustainable credit habits through product design, partnerships, and education. Our mission is clear: get people away from risky, unregulated credit.
About You & The Opportunity
We’re seeking an experienced, analytical full-stack data science professional to lead our fraud detection and prevention initiatives within the Underwriting team. This mid-level hybrid role bridges advanced statistical modelling, machine learning, and business analytics—with a focus on scalability, integrity, and system-level impact.
This is more than coding iteratively: it’s about moving the needle by:
- Building fraud detection models that scale
- Monetising data for growth
- Imbibing AI-first risk evaluation into our platform’s core decision-making
- Turning operational noise into actionable insights
You’ll work across engineering, product, risk, and compliance teams to craft solutions that protect members while enabling credit product innovation. Join a dynamic modern business where sustainable lending and cutting-edge modelling intersect.
Key Responsibilities
Model Development & Innovation
- Design and refine fraud scoring, identity authenticity, and creditworthiness machine learning models, integrating both traditional predictive signals and novel techniques (behavioural biometrics, adversarial robustness, network graph analysis, let alone AI agent networks).
- Test and deploy real-time fraud detection, leveraging live/aperture data feeds and event-driven architectures (e.g., AWS-powered workflows).
- Translate influences from external research papers, trade reports, and industry (e.g., banks, fintechs) into actionable schemes applicable to our member-centric models.
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
Data & Systems Integration
- Effectively cleanse, synthesise, and link internal histories to external breaches (syndicates, currencies, KYC sources) to build unified scoring pipelines.
- Integrate real-time SaaS and 3rd-party APIs into our decisioning engine (e.g., credential validity checks, EIDAS, Open Banking).
- Lead A/B tests, Proof-of-Concept demonstrations, and retro-hindcast exercises to validate innovations and likelihood of innovation.
Insights & Stakeholder Influence
- Develop performance dashboards (monitoring model drift, denial rates, revenue leakage but still keeping laser focus on member well-being).
- Partner with product managers to influence features that trade-off lending convenience against sustainable default risk (e.g., payroll-linked deferral ‘reprieve’ features).
- Collaborate in a risk-control-focused organisation: contribute to Fraud, AML, and KYC casework resolution via well-structured data investigation alongside infrastructure teams.
Why You’ll Succeed
| Required Experience | Nice-to-Have Bonus |
|---|---|
| Proven expertise in fraud prevention analysis (especially in SME/retail credit). | Domain experience in Open Banking, decisioning SaaS platforms, or JavaScript API layering. |
| Holistic end-to-end model development lifecycle: from feature engineering through to MLops-Ready deployment in cloud environments. | Hands-on fluency with real-time partitioning detection frameworks (e.g., fraud triage using Redis ‘mouse-click streams’). |
Strong Python implementation: Think pytest-Pandas-sklearn combination, plus brevity toolkits (e.g., tenacity/nltk). Numeratize reporting via metrics (precision, funnel penetration by fraud type, returns on blocked fraud). | Exposure to Fintech’s borrower psychology— understanding cohorts susceptible to manipulation or ultimately trapped in rollover cycles. |
| SQL ninja skills to federate data across on-premise resources and external sources (functional hooks → SQL –> optimal alignments with datasheets embargoed for machine learning models). | Product-team leanings – pioneer features only to drop them if A/B indicates counter-educational impact. |
| Figuring, crafting, and explaining commercial impact to CFOs as well as “summarising” data signals for non-technical teams (e.g., ‘borrower’s rollerscoaster’). | Having baked schema change into CI/CD pipelines, even on limited AWS RDS capacity (skew parameter revelations). |
Get help with your application
Your very own career expert that helps elevate your application to the next level.
We value potential as much as perfect bullet points. If you’re generally aligned here but haven’t precisely checked everything—this purpose-driven mission is likely valuable to you. We’re a flat, mercurial team of over-indexers, but we thrive on proactive then emphatic collaboration.
For access to the application and eail directly to our People team, head to: people@creditspring.co. (‘DoNotPot’: Unsubmitted applications will not be reviewed.)
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Skills
Location