Hi, I’m Monika! I am an experienced technical professional with 7+ years of industry experience and a strong background in engineering, analysis, and problem-solving. My career began in the electronics industry, where I worked as a Component Engineer specializing in sourcing electronic components, managing EDA libraries, and performing lifecycle and compliance analysis. Throughout my work, I developed a solid understanding of electronic device construction, technical documentation, and supply chain dynamics.
In this role, I gained strong skills in analysing PCB projects, identifying and resolving design issues, and preparing clear, structured technical reports and presentations for cross-functional teams. I also worked extensively with large datasets related to electronic components, which strengthened my analytical mindset and ultimately sparked my interest in data-driven decision-making.
I recently completed a Junior Data Analyst training program and earned a certificate, gaining practical experience in SQL, Python (Pandas, NumPy), Power BI, and Excel. This allowed me to expand my analytical skill set and transition my engineering problem-solving mindset into the world of data. I am eager to apply my attention to detail, structured thinking, and analytical approach to uncover insights, improve processes, and support data-driven decision-making.
I enjoy working with data, exploring new tools, and continuously developing my skills. Whether working independently or as part of a team, I am motivated by the challenge of transforming complex information into meaningful conclusions and actionable insights.
This repository is a place where I showcase my projects, track my progress, and document my learning journey in Data Analytics and Data Science.
In this section, I list my data analytics projects and briefly describe the technologies and methods used.
Code: Loan Default Prediction Model
Goal: To build a predictive model that determines whether a client will default on a loan using the Berka Dataset. The task involved combining multiple relational tables, performing data analysis, and developing classification models to identify high-risk clients.
Description: This project analyzes a relational banking dataset, including information on customer accounts, transactions, loans, and demographics. The work involved cleaning and integrating multiple tables to create a unified customer profile, followed by exploratory data analysis to identify financial patterns, customer behaviors, and loan characteristics. The second part of the project focused on developing a predictive model to classify loans as repaid or defaulted, testing several machine learning algorithms and comparing their performance.
Skills: Data cleaning and preprocessing, exploratory data analysis (EDA), feature engineering, data modeling and integration, correlation analysis, classification modeling, model evaluation (accuracy, precision, recall, F1, ROC-AUC), data visualization.
Technology: Python, Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, Jupyter Notebook.
Results: The analysis showed that loan default is primarily influenced by financial behavior - especially total transaction amounts, average transaction value, and payment patterns. Demographic factors such as age, gender, and region had only minor impact, indicating that spending and repayment habits are far more predictive of default risk.
Code: Customer Transactions Analysis & Dashboard
Goal: To explore customer financial behavior and loan patterns using the Berka Dataset and create an interactive Power BI dashboard.
Description: The project analyzes customer accounts, transactions, and loan. Data was first cleaned and transformed in Power Query, and calculated columns and measures were created in DAX to enable meaningful analysis. The dashboard’s interactive elements allow users to explore transaction patterns, loan amounts, debt levels, and customer activity, uncovering key trends and insights that support data-driven decisions.
Skills: Data cleaning in Power Query, creating calculated columns and measures in DAX, interactive data visualization, dashboard design, filtering, bookmarks, tooltip configuration, customer behavior analysis, business insight generation.
Technology: Power BI, Power Query, DAX, CSV data.
- Gdańsk University of Technology: Master of Biomedical Engineering, 2016 - 2017
- Gdańsk University of Technology: Bachelor of Biomedical Engineering, 2011 - 2016
In addition to practical projects, I have completed the following certification, which strengthened my data analytics skills:
- Junior Data Analyst Certificate (Dec 2025) – Szkoła Biznesu LABA
- LinkedIn: www.linkedin.com/in/monika-komsta-9084b2140
- Email: mkomsta1@gmail.com