About Philipp
I’m a freelance Data Scientist and PhD Economist with over 10 years of experience in data analysis, econometrics, applied machine learning, and strategic communication. My background combines rigorous academic research with hands-on projects in business and public policy — giving me a unique perspective on how to turn complex data into actionable insights.
How I help businesses:
- Build and deploy predictive analytics and machine learning models for forecasting, risk assessment, and performance optimization.
- Apply causal inference and econometric methods to uncover what truly drives business outcomes — beyond simple correlations.
- Translate analytical results into clear, data-driven strategies that support confident decision-making and measurable impact.
For more on my services, contact options and projects visit philippschaz . com
German
Native or bilingual
English
Fluent
Spanish
Conversational
Greek
Conversational
French
Basic
Can work on-site
Berlin (up to 50km)
Experience
- MercorAI Expert (PhD)TECHSeptember 2025 - December 2025 (3 months)San Francisco, United States• Develop, evaluate and optimize advanced AI/LLM systems for economic decision-making, including benchmarking, reasoning assessment, reliability checks and error analysis.• Improve model accuracy and domain-specific performance through prompt engineering, RAG/LLM optimization techniques and deep research rubrics.
- Sparkassen Rating und Risikosysteme,Data ScientistBANKING AND INSURANCEMarch 2025 - August 2025 (5 months)Berlin, Germany• Build a predictive model identifying attrition risks among young customers and partner with the national banking association to design a data-driven strategy for long-term customer retention.• Develop and evaluate data models (XGB) for automated customer targeting across 40 million accounts, including KPI design and impact measurement to optimize sales channels.
- DatascientestData ScientistEDUCATION AND E-LEARNINGJune 2024 - October 2024 (4 months)Paris, France- Develop deep learning and classic ML (SVM, XGB) models to detect lung diseases from 21,000 X-rays, achieving a 95% macro F1-score with the best TensorFlow transfer learning model.- Deploy a Streamlit web app on AWS Cloud enabling real-time predictions and Grad-CAM visualizations from uploaded chest X-rays.
Recommendations
Be the first to recommend Philipp
Help this freelancer shine by sharing your experience working together.
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- PhD in EconomicsHumboldt University of Berlin, Germany2019• Apply advanced statistical methods in scientific data projects, including econometrics, causal analysis, leading to a publication in a top-3 journal. • Engineer and integrate large-scale datasets from seven global sources into a relational SQL database to model 2 million credit observations. Enabling robust analysis on the effect of global banking crises on firm performance. • Automate structured data pipelines using Python WAF to preprocess and transform data for modeling, ensuring reproducibility, and improving efficiency in data-driven modelling. Demonstrating that geographically diversified banks stabilize loan supply by 7.6% during banking crises.
- Data ScientistUniversity of Paris I: Panthéon-Sorbonne, France2024• Training in machine learning with Python (NumPy, pandas), data visualization (Matplotlib, Seaborn, Plotly), and programming tools (Bash, Git). • Deepen expertise in classic ML (SVM, Logistic Regression, Random Forest, XGBoost, Boosting, Bagging) and build advanced deep learning models (Keras, TensorFlow, PyTorch), including CNNs, transfer learning, NLP, recommender systems, and graph algorithms (OpenCV, Hugging Face, NetworkX). • Build end-to-end data pipelines and MLOps workflows (SQL, APIs, PySpark, MLflow, Docker) and earn AWS Cloud Practitioner certification.