Data Science & Machine Learning Consultant

10/2017 – 12/2019

In-house Data Science consulting covering diverse parts of the Henkel value chain

- Built various machine learning applications (classification and time series fore- casting, etc.) incl. tech stack selection, architecture, model training, and deployment
- Mentored junior data scientists in multiple projects incl. own contributions: marketing analytics based on IoT data, customer complaint analysis, production optimization, accounts receivable prediction, sales success prediction, epigenetics research, hair color prediction from sensor measurements
- Consulted and performed QA in multiple machine learning projects with external implementation partners - Contexts: source-to-pay, intercompany, EDI
- Participated in the definition of standard architectures for machine learning applications at Henkel in collaboration with the DevOps team

Technologies: Python, Pandas, XGBoost, scikit-learn, Keras, facebook Prophet, Plotly Dash, PowerBI, Docker, Spark, git, Linux

Power Bi, Keras, Pandas, Scikit-learn, Apache Spark, Docker, Git, Python

2/2016 – 9/2017

Helped to establish Data Innovation Lab and implemented Data Science use cases

- Implemented Spark data preparation and pseudonymization solutions on Hadoop
Collaborated in the specification and implementation of Kafka and Flume data streaming architectures
- Built statistical models for customer churn prediction
- Examined print data and identified opportunities for cost reduction
- Integrated external data scraped from the web
- Pioneered and supported the establishment of Python, Scala and R development environments within the company
- Gathered project management experience, leading the project initialization of a small IT infrastructure project (~500TEUR)

Technologies: Python, Scala, R, Hadoop, Spark, Flume, Kafka, SQL on Impala and Hive, Hue, Oozie, bash, git, Pandas, scikit-learn, Selenium WebDriver

Apache Hadoop, Pandas, Scikit-learn, Apache Spark, Python, Scala, Selenium