Louis de Bruijn
32-year old Python enthusiast
-
Data Scientist at ING Netherlands
-
Computational Linguistics, University of Groningen
-
Natural Language Processing
Full stack Web (Python)
-
PySpark
Sklearn, NLTK, Pandas, Numpy, Scipy
Flask, Django, Javascript, HTML, CSS
- message me!
- charge me
Personal resume
Senior Data Scientist with 5+ years of experience owning production ML systems in regulated financial environments, specializing in transaction monitoring.
Work experience
-
Senior Data Scientist | Transaction Monitoring
Apr 2022 - Present • 4 yrs 1 mos
End-to-end ownership of production ML models in AML monitoring, operating in a regulated, multi-country environment.
• Owned the design and productionization of a monolithic ML model to reduce false positives in second‑line AML transaction monitoring, now deployed and rolled out across seven countries.
• Collaborated … read more End-to-end ownership of production ML models in AML monitoring, operating in a regulated, multi-country environment.
• Owned the design and productionization of a monolithic ML model to reduce false positives in second‑line AML transaction monitoring, now deployed and rolled out across seven countries.
• Collaborated in an ML-based risk detection model for third‑party payment providers, covering SWIFT and PSP transaction flows in correspondent banking.
Extracurricular activities:
• Kickstart AI challenge '23 ING: Allow More, prediction governmental financial allowancesCOO Analytics
KYC
Kickstart AI
-
Data Scientist | International Talent Programme
Oct 2020 - Mar 2022 • 1 yrs 6 mos
1st rotation: Customer Dialogue Analytics
• Developed and productionized Named Entity Recognition package for the anonymization of Personable Identifiable Information (PII)
• Organized the NLP conference, a 2-day event for data scientists in natural language processing
2nd rotation: Advanced Real-Time Analytics
• Experimentation to reduce the time to prediction for the "Look Ahead" in the ING app
• Restructuring the code from Hive to PySpark.
3rd rotation: Risk & Pricing Advanced Analytics
• Developing two credit risk prediction models in the direct business lending domain
• Open-source: Data lineage checks for data filtering steps: waterfall-logging
Extracurricular … read more 1st rotation: Customer Dialogue Analytics
• Developed and productionized Named Entity Recognition package for the anonymization of Personable Identifiable Information (PII)
• Organized the NLP conference, a 2-day event for data scientists in natural language processing
2nd rotation: Advanced Real-Time Analytics
• Experimentation to reduce the time to prediction for the "Look Ahead" in the ING app
• Restructuring the code from Hive to PySpark.
3rd rotation: Risk & Pricing Advanced Analytics
• Developing two credit risk prediction models in the direct business lending domain
• Open-source: Data lineage checks for data filtering steps: waterfall-logging
Extracurricular activities:
• Machine learning explained (c.q. 75 participants total)
• Python for beginners training (c.q. 20 participants total)ML Engineer
ING
Amsterdam • 5 yrs 7 mos
ML Engineer | Data Scientist
Ortec Finance
Sep 2019 - Aug 2020 • 1 yr
Amsterdam
Responsible for implementing various Natural Language Processing (NLP) microservices (APIs), most notably a curriculum-vacancy matching service, topic modeling, (legal) document understanding product, and conversational agents.
Data Science Intern
Lootjestrekken
Jun 2019 - Aug 2019 • 3 mos
Delft
This internship aimed to develop a recommender system that improved over the current rule-based system for personalized gift suggestions to users of Lootjestrekken.nl. During this project, I successfully showed and … read more This internship aimed to develop a recommender system that improved over the current rule-based system for personalized gift suggestions to users of Lootjestrekken.nl. During this project, I successfully showed and implemented an enhanced infrastructure where past user-behavior descriptions predict future behaviors over the rule-based baseline.
Education
-
Computational Linguistics | Master
Sep 2019 - Aug 2020 • 1 yr
Data Science, Machine Learning, Natural Language Processing, Computational Semantics.
Thesis … read more Data Science, Machine Learning, Natural Language Processing, Computational Semantics.
Thesis
"Contextual Feature Abuse Detection,
The Use Of Author And Parent Micro post Features For Abuse Detection Datasets." -
Computational Linguistics | Pre-master
Sep 2018 - Aug 2019 • 1 yr
Programming in Python, Database Design, Quantitative Text Analysis, Search Engines, Database driven ‐ Webtechnology, Logic Programming.
-
Communication and Information Science | Bachelor
Sep 2014 - Aug 2018 • 4 yrs
Text and Conversation Analysis, Usability, Multi modal and Digital Communication.
Thesis … read more Text and Conversation Analysis, Usability, Multi modal and Digital Communication.
Thesis
"Finding the right answer is a skill in and of itself,
Discovering differences in linguistic characteristics between expert and non-expert knowledge holders on Stack Overflow."
University of Groningen
Groningen • 6 yrs
Extracurricular
PyData Conference
NumFOCUS
Apr 2024 - Present • 2 yrs 1 mos
Amsterdam
Active contributor to the PyData Amsterdam community, supporting the organisation of meetups and conferences focused on Python, data science, and machine learning. Facilitate knowledge sharing between industry practitioners and researchers, … read more Active contributor to the PyData Amsterdam community, supporting the organisation of meetups and conferences focused on Python, data science, and machine learning. Facilitate knowledge sharing between industry practitioners and researchers, and contribute to strengthening the local open‑source and data science ecosystem.
Allow More | Kickstart AI challenge
Kickstart AI @ ING
Sep 2023 - Oct 2023 • 2 mos
Amsterdam
Kickstart AI challenge hosted @ ING. A three-week hackathon where data scientists from Ahold Delhaize, KLM, and NS come together to work on an AI challenge: Allow More, a project … read more Kickstart AI challenge hosted @ ING. A three-week hackathon where data scientists from Ahold Delhaize, KLM, and NS come together to work on an AI challenge: Allow More, a project to identify the underutilization of national household allowances.
Souschef
De Patchka
Feb 2023 - Jul 2023 • 6 mos
Amsterdam
Vegan Korean & Japanese takeaway shop. Their food is different from authentic traditional Korean and Japanese food. The vegan bulgogi is something I have never tasted before!
Food delivery
Eigen krachtvoer
Dec 2021 - Sep 2023 • 1 yrs 10 mos
Amsterdam
Every week I organised the food delivery from Eigen krachtvoer to Amsterdammers that have a Stadspas (low income). Eigen krachtvoer prepares a three-course meal and provides it on a discounted offer.
Buddies project
Humanitas
Feb 2017 - Jul 2017 • 6 mos
Groningen
Buddy for an autistic and underprivileged teen, whom I met with on a weekly basis to take him out of his habitat and do lots of fun things in and around Groningen.
Chairman
ComMa Congres
Mar 2016 - Oct 2016 • 8 mos
Groningen
Responsible for the organisation of the annual ComMa Congres, a collaboration between the communication and marketing study associations at the University of Groningen.
National Junior Representative
CISV
Jan 2013 - Dec 2013 • 1 yr
The Netherlands
Dutch representative in the junior branch of CISV. Worked together with many representatives around Europe on the branch's strategy, both nationally and internationally.
Core expertise
| Production machine learning |
| NLP |
| Transaction Monitoring |
| AML/KYC analytics |
| Model monitoring & governance |
Tools & Platform
| Scikit-Learn, Pandas, Spark |
| Django, Flask, FastAPI |
| Docker, Kubernetes |
Interests
| Interior design |
| Marktplaats |
| Medium articles |
| Art |
Languages
| English | native/bilingual |
| Dutch | native/bilingual |
| German | professional working |
| Spanish | professional working |
| French | limited working |
