About me
Welcome to my page! I am Rebeka, a data enthusiast and economist, with a BA and MA in applied economics. The past 5 years I have worked with BlackRock, the European Central Bank, Moody's, Tresorit, and many other clients with very different needs.
​
I analyze whatever I can get my hands on, and I use all the tools around: Power BI, Python, SQL you name it. I own the process from begging to end, starting with data collection, cleaning, and setting up a pipeline, all the way through descriptive and predictive analysis, until visualization and presentation to audiences from different backgrounds.
​
These are sample analyses that I have done in my free time. In case of any questions or suggestions, feel free to reach out through the contact form or WhatsApp.
Sample work
Navigating the Data Career Landscape
Revealing Trends and Aspirations Through LinkedIn Web Scraping
Motivation
While being on the job market myself, I noticed some ambiguity between the terms data analyst/scientist/engineer. There was also a shift in trending applications, as well as in often repeated company perks in order to attract talent.
Method
Using a web-crawler written in Python with Selenium, I scraped more than 2,200 jobs fitting my requirements. I was interested in 1) what are the trending skills in the job descriptions and 2) what are the major buzzwords that seem to have an impact on the number of applicants.
Bottom line
-
The absolute champ in the data industry is still SQL: 31.3% of jobs listed it among hard or soft requirements.
-
Based on the top 3 requirements, data analysts were set apart only by requiring knowledge of a visualization tool. 18% of data engineering jobs required knowledge of a C language, which was much less than I anticipated.
-
Remote jobs on average had more applicants of course, but interestingly the number of skills mentioned also had a positive impact on the number of applications.
​​
Python / Selenium Power BI Regression analysis
​
Unlocking USA Flight Insights: 2018-2023 Analysis
Motivation
Experiencing (for the second time) a 9 hour delay when travelling to the US, I asked myself, what was I doing wrong.
Method
Analyzing the dataset from the Bureau of Transportation Statistics to reveal the best and worst airlines, airports, and times we can choose for our domestic US flights. This exploratory modelling, data cleaning and presentation was done using Power BI.
Bottom line
-
Between 2018 and 2023, the average US domestic flight was late 13.5 minutes, peaking at 22 minutes in December 2022 due to lack of staff at airports.
-
The aircrafts are most punctual on Tuesdays and Fridays the least.
-
Ultra low-cost companies (Spirit, Allegiant and Frontier) indeed experience higher delays on average, while Delta, Alaskan and Hawaiian were the most punctual.
​​
Power BI Descriptive statistics Data cleaning/modelling
​