Senior Data Scientist – IRB Model (M/F)

Your next challenge:  

  • Develop “Data Science” at BIL: relatively new data expertise, often associated to Big Data, applying mathematical and statistical methods for marketing and commercial purposes (client profiling, behavioral analysis, propensity scorings, churn early detection…) and to increase internal efficiency (automated decisions).
  • Continuously follow up on new methods, technologies, market trends in Ai and Data Science (Machine Learning, Big Data, Deep Learning & Neural Networks, NLP…). Contribute to the “Lab” (or “R&D”) mindset of the team.
  • Change Management - Explain and demystify Data Science, Machine Learning, Deep Learning within the bank, to increase leveraging of these new capabitilies to support our business. Accelerate the usage of these kinds of approache in the bank.
  • Apply statistical and quantitative approaches in a growing scope of applications, such as: commercial performance & marketing analysis, Decision-making automation, Fraud detection, AML KYC compliance, Internal processes acceleration, set-up of credit models.
  • Increasing income by feeding marketing campaigns and CRM (measurable).
  • Increase our compliance, and better manage the cost of regulation (eg. New AML profiling which allowed to reduce of 95% the number of high risk profiles, and to avoid the mandatory recurring reviews of these clients).
  • Providing a better understanding of our clients sot that for strategic projects and strategic decisions (such as branch transformation, marketing initiatives, client segmentation) BIL can provide the best possible value proposition. Providing relevant analyses to reduce costs, increase commercial efficiency (e.g. BEF) and Client experience (e.g. Card limits).
  • Increase our internal efficiency and increase client experience by automating manual decisinal processes (BEF automation, clients' messages automated sorting, RBE treatment,…). Measurable, in terms of efficiency.
  • Manage the set-up, the implementation and maintenance of internal database required in the context of credit risk model development/maintenance:
  • Define and manage business requirements of data flow regarding data used in credit risk quantification.
  • Implement data quality processes and reports in order to monitor data consistency and quality.
  • Manage data correction and data improvement requests.
See all articles