01
Data Collection & Mining
Build tailored workflows to gather structured information from websites, APIs and other digital sources.
- Web data extraction
- Python crawler scripts
- API data collection
- Multi-source integration
From scattered data to something useful.
I help companies collect, structure and analyse complex data, resolve duplicate records, and automate repetitive data workflows.
Python
SQL
R
Power BI
Excel
Machine Learning
HOW I CAN HELP
Practical data work for problems that do not fit neatly into a spreadsheet.
From one-off analysis to reusable workflows, I focus on concrete business problems: getting hold of the right data, improving its quality, finding relationships inside it and reducing repetitive manual work.
SERVICES
Five ways I can work with your data.
Projects can be delivered independently or combined into a larger end-to-end workflow.
02
Data Cleaning & Quality
Transform messy, inconsistent datasets into information that is reliable enough for analysis, reporting or modelling.
- Data restructuring
- Validation & anomaly checks
- Missing-data diagnostics
- Dataset consolidation
03
SPECIALIST AREA
Entity Resolution
Identify records that refer to the same real-world customer, company, product, even when the records are not identical.
- Duplicate detection
- Fuzzy record matching
- ML-assisted classification
- Graph-based reconciliation
04
Data Analysis & Insights
Investigate business questions, identify patterns and translate analytical results into findings people can act on.
- Exploratory analysis
- Statistical analysis
- Data visualisation
- Decision-ready reporting
05
Data Automation
Replace repetitive manual data work with reliable scripts, reusable processes and lightweight analytical tools.
- Excel workflow automation
- Recurring data processing
- Automated reporting
- Custom Python utilities
SELECTED WORK
Complex methodology, translated into a usable product.
A flagship project demonstrating data collection, machine learning, entity resolution, graph methods and front-end delivery.
Finding the unique property behind duplicate housing listings.
Online housing aggregators can contain several advertisements for the same physical dwelling. I developed an end-to-end entity resolution workflow that scores candidate pairs, detects likely duplicates and reconciles conflicting relationships into unique entities.
A
B
C
D
RAW LISTINGS
4
→
RESOLVED ENTITIES
2
ABOUT
Technical analysis with a business-facing mindset.
My work sits between data analysis, statistical modelling and practical problem-solving. I am particularly interested in situations where data is fragmented, inconsistent or difficult to use directly.
I work in English and French (possibility to accomodate Czech teams) for both one-off analytical assignments and small reusable data products.
HAVE A DATA PROBLEM?
Let’s figure out what can be done with it.
Tell me what you are trying to collect, clean, understand or automate. I can help turn it into a concrete analytical project.