| Project | Overview | Stack |
|---|---|---|
| 01. Yandex Music | Data preprocessing, EDA of music preferences in Moscow and St. Petersburg |
Pandas |
| 02. Reliability of borrowers | Data preprocessing, Outlier detection, EDA of factors contributing to delays in loan repayment, Data visualization |
Pandas, Seaborn |
| 03. Real estate analysis | Data preprocessing, Outlier detection, EDA of factors affecting real estate prices in St. Petersburg |
Pandas, Seaborn, Matplotlib |
| 04. Tariff statistical analysis | Data preprocessing, EDA of cell phone services, Hypothesis testing, Data visualization |
Pandas, Seaborn, Numpy, Matplotlib, Scipy |
| 05. Computer games market analysis | Data preprocessing, EDA of the most successful game platforms and genres to date by countries, Hypothesis testing, Data visualization |
Pandas, Numpy, Matplotlib, Seaborn, Scipy |
| 06. Tariff recommendation | Binary classification model of tariff recommendation | Pandas, Sklearn |
| 07. Bank churn prediction | Prediction of a leaving client based on their personal data | Pandas, Sklearn |
| 08. Oil well location prediction | Regression model for oil reserves, Bootstrap for gauging risks and potential profit with a 95% confidence interval |
Pandas, Numpy, Sklearn |
| 09. Gold recovery | Data preprocessing, Data distribution analysis, EDA of inputs and outputs of the filtration process, Regression model for recovery of gold from ore, Data visualization |
Pandas, Numpy, Matplotlib, Seaborn, Sklearn, Scipy |
| 10. Sensitive data protection | Protecting insurance company data with an algorithm that will not affect model's predictions | Pandas, Numpy, Sklearn |
| 11. Auto price prediction | Data preprocessing, EDA of car prices, Auto price regression model |
Pandas, Numpy, Seaborn, Matplotlib, Sklearn, LightGBM, datetime |
| 12. Taxi demand forecasting | Time-series analysis of taxi demand, Regression model for next hour's demand predection |
Pandas, Numpy, Sklearn, Statsmodels, Matplotlib, Seaborn, LightGBM |
| 13. Toxic comment detection | NLP model to detect toxicity of a comment for further moderation | Pandas, Numpy, Nltk, Re, Sklearn, Plotly, LightGBM, Wordcloud, Collections, Matplotlib, Seaborn |
| 14. Startups | Analysis of startups' funding, acquisition, employees' education, etc. | SQL, sqlite3, sqlalchemy |
| 15. Age detection | Computer vision model for clients' age prediction | Pandas, random, Tensorflow, Keras |
| 16. Cellular company churn prediction | Data visualization, Binary classification model for customer churn prediction, Model tuning, Feature importance analysis |
Pandas, Numpy, Seaborn, Matplotlib, Statsmodels, Phik, Sklearn, LightGBM, Shap |
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent