Yanick Annema
Quantitative finance and machine learning, applied to questions about firms rather than to models for their own sake. The work is empirical: assemble the data, fit an interpretable estimator, then state what it does and does not support.
Education
MSc Financial Engineering & Management
University of Twente · graduated July 2026
- Coursework: Structured Financial Products 9.0, Applied Statistical Learning 8.8, Machine Learning 8.7, Risk Management, and Applied Corporate Finance.
- Projects: Deep Q-Network trading-agent benchmarking under realistic market frictions; random-forest modelling of corporate capital structure against linear baselines.
Exchange programme, Finance
University of Melbourne
Advanced coursework in applied corporate finance and strategy, M&A, IPOs, LBOs, hedging, and valuation.
BSc Applied Physics
Saxion
Quantitative and analytical foundation in programming, data analysis, and computational modelling. Propaedeutic-year GPA 8.8.
Experience
Financial Data Engineer
Moni IT & Consulting B.V. · part of Moore MKW
Builds internal corporate-finance tools, data pipelines, and measurement systems; contributes to AI implementation across professional-services workflows.
Corporate finance analyst
Moore MKW Corporate Finance
Builds data and automation tools supporting deal evaluation and financial analysis, alongside valuation and transaction execution.
- Built Python pipelines and internal applications that structure permitted financial and transaction data for analysis.
- Developed document-processing workflows that transform approved source files into structured analytical inputs.
- Built interpretable machine-learning research prototypes using XGBoost and SHAP for questions about post-merger operating performance.
- Supported DCF/APV valuations, information memoranda, and teasers.
Research internship
Saxion
Optimised chip placement by simulation and delivered validated adhesive application parameters.
Engineering internship
Thales Group
Designed and tested a radar cooling system and improved experimental accuracy with a robust testing framework.
Karate instructor
Muga Mushin Ryu
Instruction across age groups; eight students coached to black belt.
Instruments
Programming & ML
Python · XGBoost · SHAP · scikit-learn · pandas · NumPy · R · MATLAB · SQL/PostgreSQL · VBA/Excel
Finance & analysis
M&A · DCF/APV valuation · LBOs · IPOs · risk management · structured products
Research data
LSEG · Worldscope · public filings · transaction and financial databases
Research interests
Empirical AI economics and labour-market dynamics: adoption gaps between firms, task displacement in professional services, and the effect of AI on skill formation. The method remains empirical: measure observable workflow change and keep inference within the evidence.