Welcome to the repository of projects and educational tasks related to data analysis, machine learning, and related topics! In this repository, you will find solutions and code in programming languages such as Python, SQL, PySpark, Keras, and more. Each project represents a unique task related to data analysis or building machine learning models. Below is a brief overview of each project:
| Project Title | Domain | Role | Tools & Skills | Project Description | Key Tasks |
|---|---|---|---|---|---|
| Exploring Data from "Yandex.Music" Service | Internet Services, Streaming | Data Analyst | Pandas, Python | Analyze real data from Yandex.Music using Pandas to compare user behavior and preferences in Moscow and St. Petersburg. | Data processing, duplicates, missing values, logical indexing, grouping, sorting |
| Assessing Borrower Creditworthiness | Banking, Lending | Data Analyst, Financial Analyst | Pandas, Python | Investigate the influence of a client's marital status and number of children on loan repayment. | Data analysis, duplicates, missing values, categorization, decomposition |
| Real Estate Market Analysis in St. Petersburg | Internet Services, Classifieds | Data Analyst, Fraud Analyst, Marketing Analyst | Matplotlib, Pandas, Python, data visualization, exploratory data analysis, data preprocessing | Determine property market values and typical apartment characteristics using Yandex.Real Estate data. | Data processing, histograms, box plots, scatter matrices, categorization, scatterplots, fraud monitoring |
| Optimal Tariff Plan for a Telecom Company | Telecommunications | Data Analyst, Marketing Analyst, Product Analyst | Matplotlib, NumPy, Pandas, Python, SciPy, descriptive statistics, hypothesis testing | Analyze customer data to recommend optimal service packages. | Preliminary tariff analysis, customer behavior analysis, data preprocessing, hypothesis testing, Student's t-test |
| Russian Film Market Research | Offline, Streaming Services | Data Analyst, Product Analyst | Matplotlib, Pandas, Python | Conduct research on the Russian film market and identify current trends. Analyze the appeal of films receiving government support. | - |
| Customer Classification for a Telecom Company | Telecommunications | Classification, Machine Learning | Matplotlib, Pandas, Python, Scikit-learn | Develop a system to recommend tariffs based on customer data. | Customer behavior analysis, hyperparameter tuning, machine learning model selection |
| Customer Churn Prediction for a Bank | Banking, Business, Investments, Credit | Classification, Machine Learning | Matplotlib, Pandas, Scikit-learn | Predict customers at risk of leaving the bank using historical customer behavior and contract termination data. | Classification, hyperparameter tuning, machine learning model selection |
| Determining the Most Profitable Oil Region | Machine Learning in Business | Extraction Companies | Machine Learning, Business Model Development, Regression, Financial Analysis | Select an oil extraction region based on geological data provided by exploration geologists. | Regression, business model development, bootstrap |
| Hotel Sales Prediction System | Composite 2 | Internet Services, Tourism | Machine Learning, Business Model Development, Regression, Financial Analysis | Predict customer booking cancellations. Build a prediction model using machine learning and measure its success in terms of revenue after implementation. | Classification, business model |
| Predicting Housing Prices in St. Petersburg | Big Data, Machine Learning | Internet Services, Offline, Real Estate, Advertising Platforms | Big Data, Machine Learning, Regression, Pandas, Python, Spark | Determine the median price of real estate in St. Petersburg's residential areas based on Yandex.Real Estate data. Perform data preprocessing, visualization, and analysis. | Data preprocessing, visualization, categorical variable encoding |
| Optimal Telecom Tariff Analysis | Statistical Data Analysis | Telecom | Data Analysis, Descriptive Statistics, Statistical Hypothesis Testing | Analyze customer usage data and recommend optimal tariff plans for a telecom company. Preprocess and analyze data, test hypotheses about revenue differences between tariff plans and city regions. | Data preprocessing, hypothesis testing, descriptive statistics |
| Russian Movie Market Research | Composite 1 | Offline, Streaming Services | Data Analysis, Data Visualization, Pandas, Python | Conduct a study of the Russian movie market and identify current trends. Analyze the appeal of movies that received state support to the audience. | Data analysis, data visualization, movie market trends |
| Customer Classification for a Telecom Company | Introduction to Machine Learning | Telecom | Classification, Machine Learning, Pandas, Python, Scikit-learn | Develop a system to classify customers into one of the new tariff plans based on their behavior, device usage, and preferences. | Classification, hyperparameter tuning, machine learning model selection |
| Profitable Oil Region Determination | Machine Learning in Business | Oil and Gas Extraction Companies | Machine Learning, Business Model Development, Regression, Financial Analysis | Select an oil extraction region based on geological data provided by exploration geologists. | Regression, business model development, bootstrap |
| Hotel Reservation Sales Forecasting | Composite 2 | Internet Services, Tourism | Machine Learning, Business Model Development, Financial Analysis | Forecast customer booking cancellations. Build a prediction model and evaluate its performance in terms of revenue after model implementation. | Classification, business model |
| Predicting Apartment Prices in Residential Areas | Big Data Processing Systems | Internet Services, Offline, Real Estate, Advertising Platforms | Big Data, Machine Learning, Regression, Pandas, Python, Spark | Determine the median price of apartments in different types of residential areas using Yandex.Real Estate data. Conduct data preprocessing, add new features, and create various visualizations. | Data preprocessing, feature engineering, data visualization |
| Personal Data Protection for an Insurance Company | Linear Algebra | Insurance, Investments, Internet Services, Telecom | Machine Learning, Data Preprocessing, Anonymization | Protect customer data for "Safe Flood" insurance company. Develop a data transformation method that makes it difficult to reconstruct personal information. Ensure the quality of machine learning models is not compromised during the transformation. | Linear algebra, regression |
| Car Price Model Building | Numerical Methods | Business, Internet Retail, Internet Services | Machine Learning, Regression, Pandas, Python, LightGBM | Develop a car pricing model based on historical data. The model will estimate the market price of a car from its description. | Gradient boosting, regression |
| Star Temperature Prediction | Machine Learning Methods and Algorithms | Science | Machine Learning, Regression, Pandas, Python, PyTorch | Estimate the surface temperature of a star based on indirect data. Create a model to evaluate the temperature on the star's surface. | Neural networks, regression |
| Car Sharing Accident Prevention System | Composite 3 | Business, Internet Services, Offline | SQL, Machine Learning | Build a system to alert car-sharing customers about accidents based on historical database data. | Database management, feature synthesis |
| Taxi Order Volume Forecasting | Time Series | Business, Internet Services, Startups | Machine Learning, Pandas, Python, Scikit-learn, statsmodels | Develop a system for predicting taxi order volume. The company has gathered historical data on taxi orders at airports. To attract more drivers during peak hours, the goal is to forecast the number of taxi orders for the next hour. Build a predictive model for this purpose. | Time series analysis, regression, forecasting |
| Comment Classification Model | Text Analysis | Internet Services, Startups | Natural Language Processing, Machine Learning | Identify comment toxicity. An internet store is launching a new service that allows users to edit and enhance product descriptions, similar to wiki communities. Customers provide their edits and comment on changes made by others. An instrument is needed to detect toxic comments and send them for moderation. | Natural Language Processing, text classification |
| Customer Photo Age Detection | Computer Vision | Business, Offline | Computer Vision, Machine Learning, Keras, Python | Determine age from photos. A retail supermarket is implementing a computer vision system for processing customer photos. Capturing photos in the checkout area will help determine the age of customers for analyzing purchases and offering products that may interest customers of that age group. It will also help monitor cashiers' honesty when selling alcohol. Build a model to estimate a person's approximate age based on a photo. You have a set of photos of people with their indicated ages. | Image processing, neural networks |
| Image Search Engine | Composite 4 | Internet Services, Startups | Computer Vision, Natural Language Processing, Machine Learning | Develop a simple image search based on textual descriptions. Create a model that connects text data and images. | Composite (CV, NLP, ML) |
Each project has its own directory with a description of the task and project files. For additional information, please go to the directory of the project that interests you. Enjoy studying and successful work with data and models!
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent