Job Description - AVP Lead Data Scientist, Financial Crimes Analytics
Lead Data Scientist, Financial Crime Analytics
Within Financial Crime, the Analytics team provides support in areas requiring analytics of a quantitative/statistical nature by deploying expertise in data analytics, statistical inference/modelling and risk management.
Data Scientists within this team are responsible for understanding the business area, data and existing systems and providing solutions ranging from Transaction Monitoring system optimization, the development of alert prioritization/scoring models and algorithms, generation of complex insights and actionable MI all in the pursuit of enhancing the effectiveness and efficiency of our AML program.
Our key stakeholders and partners include;
the AML Transaction Monitoring team, responsible for the day-to-day management, optimization, tuning and governance of vendor Transaction Monitoring systems such as Oracle Mantas AML and NICE Actimize SAM;
the AML Investigations team, responsible for case investigations;
the Financial Intelligence Unit, responsible for conducting complex thematic investigations in relation to new and existing AML threats.
The achieve our goals, the team works with our technology partners, Financial Crime/Compliance Transformation, which provide services in the development of data and technology architecture such as the implementation and technical management of Transaction Monitoring systems and the development of data architectures and analytics platforms.
Key Accountabilities and Skills required:
Provide analytics support to the AML Transaction Monitoring team in areas such as threshold tuning/optimization, customer/account segmentation and data-driven decision making and insights. This will involve techniques such as hypothesis testing, regression analysis, optimization methods and clustering analysis.
Engage in a range of innovative PoC/Prototype development activities including the data-driven automation of various currently manual processes, the development of case scoring models and the generation of enhanced AML detection capabilities through the application of machine learning techniques.
Support the growth and scope of the Financial Crime Analytics team through the generation of ideas. This will involve engaging with key stakeholders to identify their key problems and needs, and keeping up-to-date with external industry development through own research and attending key peer-group meetings and conferences.
Provide analytics support to the AML Investigations team in areas such as the development of case-prioritization scoring processes, enhanced alert-case merging and ad-hoc insight requests.
Support in activity relating to the Banks Model Risk Management policy where required.
Engage with our internal Technology team to provide requirements on the development of strategic data infrastructure ensuring that our infrastructure capability aligns to the needs of the Financial Crime Analytics team as well as to the needs of our wider stakeholders.
A Bachelors degree in a quantitative discipline with a significant Statistics component (Statistics, Mathematics, Operational Research, Business Analytics, Computer Science, Computational/Mathematical Finance, Physics, Economics/Econometrics). Masters or Ph.D. a plus but not necessary.
3+ years experience in a role involving the application of statistical analysis, predictive modelling, machine learning and optimization experience within a large corporate/Financial Services institution favorable.
3+ years hands-on experience in the use of statistical analysis and data manipulation tools (SAS, R, Python) some experience in Python preferred.
3+ years hands-on experience in applying a wide range of statistical and machine learning techniques (e.g. hypothesis testing, regression, clustering, decision trees, machine learning models).
Exposure to common Python libraries for data manipulation, statistical analysis and machine learning (Pandas, Scikit, TensorFlow, h2o.io etc) desirable
Experience with visualization tools (e.g., Spotfire, Tableau) beneficial
Exposure/Experience with distributed-data architecture (Hadoop/MapReduce, Spark) and cloud architecture such as AWS a plus
Knowledge and exposure to common Model Risk Management (e.g. SR 11-7) a plus
Knowledge of Financial Crime legislation (specifically Anti-Money Laundering / Terrorist Financing) and exposure to common 'Transaction Monitoring ' systems not required but will be seen as a plus.