Ifeoma28/datascience_salary_prediction

This project aimed to predict the salary of Data Scientists in North America, Africa, Asia and Europe # datascience_salary_prediction This project aimed to predict the salary of Data Scientists in North America, Africa, Asia and Europe # Comparing & Predicting Data Scientist Salaries Across Continents ## 👤 Author Ifeoma Mary-Ann James ## 📌 Project Overview An end-to-end descriptive and predictive analysis comparing annual salaries of Data Scientists across Africa, Asia, North America and Europe. **The core question:** > "What drives the salary gap between Data Scientists > across continents and can we predict it?" --- ## 🗂️ Project Structure | File | Description | |---|---| | `Project_2.ipynb` | Full analysis notebook | | `salaries.csv` | Raw dataset — 105,434 records | | `README.md` | Project documentation | --- ## 📊 Dataset | Property | Details | |---|---| | Source | Global Data Science Salaries Dataset | | Original Records | 105,434 rows | | After Deduplication | 52,437 rows | | Target Variable | salary_in_usd | | Continents | Africa, Asia, North America, Europe | | Features | work_year, experience_level, employment_type, job_title, salary_currency, remote_ratio, company_size | --- ## 🔍 Key Questions Answered ### Geographic & Distributional - What is the mean and median salary per continent? - How does salary variance differ between continents? - Does North America show wider salary distribution? - Are there extreme outliers pulling the global average? ### Experience & Demographics - How does experience level distribution vary by continent? - Does a Senior Data Scientist in Asia out-earn an Entry-level in North America? - Where does the salary gap widen or narrow most? ### Employment Structure - What proportion of African and Asian data scientists work for foreign companies? - How much more do foreign company employees earn? - How does company size correlate with salary? - Does USD payout vs local currency explain salary variance? --- ## 📈 Key Findings - **North America dominates** highest mean and median salary by a significant margin - **Geo-ar …