Data Scientist - Fraud Analyst

Key Skills

Java Programming, Python Programming, C++, C Programming, SQL, Cloud computing, Scala Programming, Machine learning techniques, Data science techniques, MATLAB Programming, PyTorch, TensorFlow, R Programming

Job Description

Responsibilities

• Design experiments, test hypotheses, and build models utilizing the traditional datasets and graph data.
• Apply advanced statistical and predictive modeling techniques to build, maintain, and improve on multiple real-time decision systems.
• Identify what data is available and relevant, including internal and external data sources, leveraging new data collection processes such as geo-location or social media.
• Utilize patterns and variations in the volume, speed and other characteristics of data for predictive analysis.
• Extending company’s data with third party sources of information when needed
• Creating automated anomaly detection systems and constant tracking of its performance
• Collaborate with various stakeholders (e.g. tech, product) to understand and design best solutions which can be implemented

Skills and Qualifications

• Bachelors in engineering, mathematics, statistics , economics or a related field.
• 2+ years of work experience as a Data scientist preferably in a fintech environment
• 1+ years of work experience on fraud modelling
• Proficiency in statistical analysis, quantitative analytics, forecasting/predictive analytics, multivariate testing, and optimization algorithms.
• Proficient in machine learning (SVM, GLM, boosting, random forest) and deep neural networks
• Strong programming skills (Spark or other big data frameworks, R, Python), statistical modeling (R, Python, SAS), query languages such as SQL
• Familiarity with basic principles of distributed computing and distributed databases.
• Strong problem solving skills to understand and execute complex analysis
• Familiarity with the best practices of Data Science

Add-on Skills :

• Experience in working with big data preferably in PySpark
• Passion for building new tools/algorithms