Location
PolandRate
$21
/ per hour
Years of experience
7+About
Currently, I am working as a Data Scientist in the Financial Crime Threat Mitigation department at Mthree for HSBC in Poland since July 2020. My primary responsibilities include working on a fraud detection classification project and leading the transition from old to new data source systems, which involved modifying all existing pipeline and modeling scripts. I am skilled in applying new logic for running dbt pipelines in Python and SQL to generate high-quality data and create champion models in BigQuery. Additionally, I write testing scripts in Python to compare output versions, handle confidential data with risk control measures, and work within an agile methodology. The technologies I use include Python (with libraries such as pandas, sklearn, numpy, matplotlib, sns), JupyterLab, SQL, GCP (Google Cloud Platform), BigQuery, Github, and JIRA. Previously, I worked as a Data Scientist in the Advanced Analytics team at Cisco Poland from July 2019 to July 2020. During this time, I developed regression and classification models using supervised machine learning algorithms and analyzed both structured and unstructured data from various sources such as SQL, Snowflake, and Hana. I also gathered project requirements through stakeholder meetings. Before Cisco, I was a Data Analyst in the Evidence Lab department at UBS Business Solutions Poland from January 2017 to June 2019, where I transformed and analyzed large datasets into client-friendly Excel models, automated data management processes using Python, and conducted industry research using market research methodologies. My educational background includes a Bachelor's degree in Information Technology and Econometrics from AGH University of Science and Technology in Cracow, Poland, which I completed in September 2017.Tech Stack
Pandas, Git, Jira, Jupyter, Numpy, Python, SQLExperience
- Automated data management processes by developing scripts in Python using pandas.
- Led a transition from old data source to new data source system, including modification of all existing parts of pipeline and modeling scripts.
- Developed regression and classification models using supervised machine learning algorithms.
- Transformed and analyzed large datasets into client-friendly Excel models.
- Applied new logic for running dbt pipeline in Python and SQL to automatically generate high-quality data and create champion models in BigQuery.
- Conducted research on different industries using market research methodology.
- Handled confidential data with risk control measures while managing datasets.
Employment history
Data Scientist, Mthree (working for HSBC)
July 2020 - Present
- Working on fraud detection classification project.
- Led a transition from old data source to new data source system including modification of all existing parts of pipeline and modeling scripts.
- Applying new logic for running dbt pipeline in Python and SQL to automatically generate high-quality data and create champion model into BigQuery.
- Writing testing scripts in Python to compare differences between different output versions.
- Working with confidential data, applying risk control while handling datasets.
- Working in agile methodology.
Data Scientist, CISCO
July 2019 - July 2020
- Developing regression and classification models using supervised machine learning algorithms.
- Joining and analyzing both structured and unstructured data from different sources (SQL, Snowflake, Hana).
- Working with different data – including products, customers, financial, security, and personal data.
- Meeting with stakeholders to gather the requirements for projects.
Data Analyst, UBS Business Solutions Poland
January 2017 - June 2019
- Transforming and analyzing huge datasets into client-friendly Excel models.
- Working with all kinds of data – starting with geospatial data up to alternative data.
- Wrangling, cleansing, and then analyzing raw data in terms of business usability.
- Taking part in improving ETL methodology.
- Automating data management processes by developing scripts in Python (pandas).
- Enforced naming standards and data dictionary for data models.
- Conducting research on different industries using market research methodology.
- Data mining for urgent projects by myself using Python (beautifulsoup library).
Education history
AGH University of Science and Technology
2014 - 2017
Bachelor in Information Technology and Econometrics
We’ve helped 83 clients with IT recruitment and software development.
Read about a few of them below...