van den Berg Analytics

About

My name is Chris van den Berg. I’m a Full Stack Data Developer who loves to build stuff. I have 13 years of industrie experience as Tech lead, Data Scientist, Data engineer and Developer.

linkedimg linkedingitimg git / gist

Me

Latest Professional Experiences

2020 - Present Tech Lead BNP Paribas Paris / Amsterdam

  • Working on Regulatory Supervision and Surveillance - Build a system to monitor and classify millions of events per day
  • Greatly reduce the False Positive alerting rate using statistical and machine learning techniques.
  • Designed and led the implementation of a voice transcription pipeline, transcribing 1000s of calls per day
  • Contributing to the platform strategy and lead its expansion to various regions and business areas

2018 - 2020 Datascientist BNP Paribas New York

  • Setup the holistic regulatory supervisory and surveillance platform.
  • Designed and built various parts of the BNPP specific tooling, including Entity Resolution, NLP systems, and various BI reports.

2016 – 2017 Datascientist Rabobank

  • Working on bank-wide data science projects.
  • Developed a production grade automated transaction fraud detection system using machine learning techniques in Python and R.
  • Utilizing a Hadoop cluster using MapReduce and Spark to generate insights, varying from one-of customer segmentation analysis to fully automated dashboards displaying various KPI’s based on “big” data sources such as financial transaction data and web log data.

2013 - 2015 Senior Consultant Forensic Technology Solutions PwC

2011 - 2013 Analyst Forensic Technology Solutions PwC

Open Source Contributions

  • Creator/Maintainer of string_grouper. A python library for fast string matching. (250+ stars, 3 million+ installs)
  • Creator/Maintainer of pyspark_dist_explore. A python library to visualise data distributions in Spark. (80+ stars, 500k+ installs)

This project is maintained by bergvca