Network Data Scientist
Pubblicato il 17-08-2026 - Altro in Turbigo
Are you looking for a new challenge? Prima could be the place for you. Since 2015, we've been using our love of data and tech to rethink motor insurance and bring drivers a great experience at a great price. Our story began in Italy, where we've quickly become the number one online motor insurance provider. To help fuel that growth, we need a Data Scientist to join our Anti Fraud Team.You'll collaborate with engineers, claims handlers and business leaders to improve the detection of fraud, directly influencing real‐world fraud decisions with impact on the company's bottom line measured in millions. This is a highly practical area of work where strong business judgment is just as important as technical expertise.What You'll Do Design and improve fraud detection systems that prioritize high‐risk claims, optimizing the trade‐off between detection accuracy and operational efficiency.Collaborate across teams and functions, working closely with fraud analysts, engineers, and product managers.Develop deep expertise in fraud dynamics, identifying emerging fraud patterns,
understanding how they evolve across the insurance lifecycle, and translating these insights into effective detection and prevention strategies, for example identifying suspicious networks of related claims, synthetic entities, or anomalous behavioral patterns.
Extensive experience (3+ years) in data science or applied machine learning, leading end‐to‐end initiatives in complex technical domains and delivering measurable business impact.Strong analytical and quantitative mindset able to translate data into insights, assess model performance, and guide decision‐making with evidence and clarity.Strong Python programming skills, especially in the data domain, and fluent use of Git.Knowledge of Spark, SQL or any other data‐oriented programming language and proficiency with standard data wrangling and modeling libraries (Pandas, Scikit‐Learn, Keras, XGBoost, LightGBM, etc.).
Experience in analytical fraud detect