Principal Fraud Data Analyst

LexisNexis Risk Solutions
London
1 year ago
Applications closed

Related Jobs

View all jobs

Principal Data Engineer (Azure, PySpark, Databricks)

Principal Data Analyst

Principal Machine Learning Engineer - Production Systems

Principal Data Engineer

Principal Data Engineer...

Principal Data Engineer...

About the Business : LexisNexis Risk Solutions is the essential partner in the assessment of risk. Within our Business Services vertical, we offer a multitude of solutions focused on helping businesses of all sizes drive higher revenue growth, maximize operational efficiencies, and improve customer experience. Our solutions help our customers solve difficult problems in the areas of Anti-Money Laundering/Counter Terrorist Financing, Identity Authentication & Verification, Fraud and Credit Risk mitigation and Customer Data Management. You can learn more about LexisNexis Risk at the link below, risk.lexisnexis.com About our Team : You will be part of a team that use global data from the largest real-time fraud detection platform to deliver valuable solutions for our enterprise customers. About the Role : You will apply your deep expertise in fraud and large-scale data analysis to investigate suspicious behaviour and provide insights that lead to immediate real-world impact. You will underline the value of your recommendations by leveraging your experience with operational measures within industry and your ability to quickly translate customers’ fraud KPIs into opportunities. You’ll leverage a real-time platform analysing billions of transactions per month for some of the largest companies operating in Financial Services, Insurance, e-Commerce and On-Demand Services. These tools will allow you to attain a unique perspective of the Internet and every persona connected to it. You’ll be continually collaborating with customer-facing account teams, external business leaders and risk managers to shape world-class fraud solutions. The comprehensive solutions that you build will go head-to-head against some of the most motivated attackers in the world to protect billions in revenue. Responsibilities Conducting in-depth reviews of complex fraud cases to identify trends and actionable insights. Making clear recommendations on how our customers can use your findings to build trust and mitigate risks. Acting as a go-to source of knowledge and inspiration for how to outsmart fraudsters in a range of settings now and in the future. Acting as a role model on how to develop and maintain a deep knowledge of fraud. Applying effective questioning skills to quickly understand the business and fraud requirements of our customers, no matter their industry. Share best practices with fraud managers, risk analysts and project managers for combating consistent and emerging security threats. Demonstrate a professional and customer-centric persona when interacting directly with customers via phone, e-mail, and chat. Using your attention to detail and ability to craft a story through data, delivering industry-leading presentations. Presenting to external and executive audiences with non-technical backgrounds Collaborating with ThreatMetrix teams including Products, Engineering, Sales and Marketing to support our common goals. Also work with other Professional Services colleagues around the world to continually redefine best practices Requirements Experience in the fraud, financial crime, security and/or payments industry, especially with very large organizations. Banking would be ideal Demonstrate exceptional analytical skills (SQL, Python, etc.) Show ability to work independently and proactively generate value-add opportunities Experience of working on and communicating fraud strategies in large organizations. Consulting experience ideally. Experience of working with fraud system management, such as ThreatMetrix, Featurespace, Hunter, Iovation, BioCatch, Actimize Falcon, etc Experience working with large and small datasets intuitively exposing meaningful correlations. Experience building external and executive report Demonstrate A keen eye for detail, accuracy and critical thinking skills with advanced judgment capability. Extensive multi-tasking and prioritization skills. Needs to excel in fast paced environment with frequently changing priorities Have fluency in more than one language spoken across EMEA is a bonus, but not essential. Learn more about the LexisNexis Risk team and how we work here

Subscribe to Future Tech Insights for the latest jobs & insights, direct to your inbox.

By subscribing, you agree to our privacy policy and terms of service.

Industry Insights

Discover insightful articles, industry insights, expert tips, and curated resources.

How to Write a Machine Learning Job Ad That Attracts the Right People

Machine learning now sits at the heart of many UK organisations, powering everything from recommendation engines and fraud detection to forecasting, automation and decision support. As adoption grows, so does demand for skilled machine learning professionals. Yet many employers struggle to attract the right candidates. Machine learning job adverts often generate high volumes of applications, but few applicants have the blend of modelling skill, engineering awareness and real-world experience the role actually requires. Meanwhile, strong machine learning engineers and scientists quietly avoid adverts that feel vague, inflated or confused. In most cases, the issue is not the talent market — it is the job advert itself. Machine learning professionals are analytical, technically rigorous and highly selective. A poorly written job ad signals unclear expectations and low ML maturity. A well-written one signals credibility, focus and a serious approach to applied machine learning. This guide explains how to write a machine learning job ad that attracts the right people, improves applicant quality and strengthens your employer brand.

Maths for Machine Learning Jobs: The Only Topics You Actually Need (& How to Learn Them)

Machine learning job adverts in the UK love vague phrases like “strong maths” or “solid fundamentals”. That can make the whole field feel gatekept especially if you are a career changer or a student who has not touched maths since A level. Here is the practical truth. For most roles on MachineLearningJobs.co.uk such as Machine Learning Engineer, Applied Scientist, Data Scientist, NLP Engineer, Computer Vision Engineer or MLOps Engineer with modelling responsibilities the maths you actually use is concentrated in four areas: Linear algebra essentials (vectors, matrices, projections, PCA intuition) Probability & statistics (uncertainty, metrics, sampling, base rates) Calculus essentials (derivatives, chain rule, gradients, backprop intuition) Basic optimisation (loss functions, gradient descent, regularisation, tuning) If you can do those four things well you can build models, debug training, evaluate properly, explain trade-offs & sound credible in interviews. This guide gives you a clear scope plus a six-week learning plan, portfolio projects & resources so you can learn with momentum rather than drowning in theory.

Neurodiversity in Machine Learning Careers: Turning Different Thinking into a Superpower

Machine learning is about more than just models & metrics. It’s about spotting patterns others miss, asking better questions, challenging assumptions & building systems that work reliably in the real world. That makes it a natural home for many neurodivergent people. If you live with ADHD, autism or dyslexia, you may have been told your brain is “too distracted”, “too literal” or “too disorganised” for a technical career. In reality, many of the traits that can make school or traditional offices hard are exactly the traits that make for excellent ML engineers, applied scientists & MLOps specialists. This guide is written for neurodivergent ML job seekers in the UK. We’ll explore: What neurodiversity means in a machine learning context How ADHD, autism & dyslexia strengths map to ML roles Practical workplace adjustments you can ask for under UK law How to talk about neurodivergence in applications & interviews By the end, you’ll have a clearer sense of where you might thrive in ML – & how to turn “different thinking” into a genuine career advantage.