Data Scientist - Optimization Data Analytics

Key Skills

Java Programming, Python Programming, SQL, Git, Apache Hadoop, Machine learning techniques, Data Visualization, NumPy, Pandas, Algorithms, PySpark, SPARK Programming, Github

Job Description

• You are experienced Python programmer and very familiar with modules pandas, sklearn, pyspark, numpy,
• You have strong knowledge of Apache Hadoop and Spark,
• You are experienced with writing SQL statements,
• You have experience with statistical inference (e.g. predictive analytics, clustering, Machine Learning Algorithms)
• You are fluent in English speaking and in writing
• You are able to clearly and succinctly express ideas, opinions and present results of analysis to non-technical guidance.
• You are able to support internal and external customers to meet and understand their needs and expectations
• You have influence skill

You'll get extra points for

• Experience with Transaction Monitoring AML optimization processes in international financial institutions,
• AML Cerification (ACAMS, ICA).

Your responsibilities

• Execute Optimisation activities and interact with teams and stakeholders
• Developing and enhancing new tools to support Optimisation processes
• Perform advanced analytics using Python (e.g., customer segmentation, predictive analytics)
• Contribute to the process and tools improvements as well as TM pillar development

Information about the squad

The resource operates in a team supporting optimisation activities related to our regulatory committed programs, to ensure optimal configuration of the global rule based monitoring systems before go-live. These global systems monitor customer transactions for indicators of financial and economic crime. The tuning, testing and optimization of these systems is a regulatory requirement and requires statistical, investigative, program and operational disciplines to deliver. After go-live the rule based system needs to be calibrated continuously based on analysis conducted by the analytics team. Key elements of the role includes: - Operating in a team of data scientists to simulate the rule based systems and providing relevant events to be investigated by alert investigations team - Provide information to help set thresholds that prevent false negatives to occur and to minimize false positives - Develop and test scenario’s to understand how changes of the parameters of the rule based systems affect effectiveness and efficiency of the alert generation - Investigate and propose additional segmentation to increase productive alerts - Interpret and analyze data problems and guarantee data quality and integrity - Adhere to stringent quality assurance and documentation standards using version control and code repositories (e.g., Git, GitHub, Markdown) - Utilize data visualization tools to deliver insights to stakeholders