Instructions:
For Data Analytics Internship, you will need to complete any one (either Level 1, Level 2, or Level 3) as per your convenience for successful completion of the internship.
If you have completed Level 3, you will be eligible for a Letter of Recommendation.
Level 1 Tasks
Task 1: Exploratory Data Analysis (EDA)
Perform EDA on a publicly available dataset (e.g., Kaggle or UCI Machine Learning Repository). Use Python libraries such as Pandas, Numpy, and Matplotlib/Seaborn to: - Clean the dataset (handle missing values and duplicates). - Generate descriptive statistics and visualize key patterns. - Provide actionable insights based on your analysis.
Task 2: Sales Data Visualization
Using a sample sales dataset, create visualizations that depict monthly sales trends, product performance, and regional growth. Utilize tools such as Matplotlib, Seaborn, or Tableau for the visuals. Highlight key trends and insights.
Level 2 Tasks
Task 1: Customer Segmentation
Using a customer dataset, perform segmentation based on purchasing patterns using clustering techniques such as K-Means. The project should include: - Preprocessing of data (handling outliers, scaling). - Applying clustering and visualizing results using Python libraries like Scikit-learn and Matplotlib. - Interpretation of segments and actionable insights for marketing strategies.
Task 2: Stock Price Analysis
Analyze stock price data for a company of your choice. Use Python libraries such as Pandas, Numpy, and Matplotlib/Seaborn to: - Clean and preprocess the dataset. - Visualize historical trends and calculate key metrics like moving averages. - Use linear regression to predict future trends (optional).
Level 3 Tasks
Task 1: Real-Time Dashboard
Create an interactive dashboard using tools like Power BI, Tableau, or Python (Dash/Streamlit). The dashboard should include: - Live data updates (use APIs or CSV files as sources). - Key performance indicators (KPIs) for metrics like revenue, growth, and user engagement. - Interactive filters to customize the view (e.g., by time period or region).
Task 2: Predictive Analytics Model
Develop a predictive model using machine learning techniques to solve a business problem. Example: - Predict customer churn using logistic regression or decision trees. - Predict sales based on historical data using regression models. Use Python libraries such as Scikit-learn, Pandas, and Matplotlib for implementation.