This project is an end-to-end Mutual Fund Analytics Platform developed using Python, SQLite, and Power BI. The objective is to transform raw mutual fund and investor transaction data into actionable insights through data engineering, financial analytics, and interactive dashboards.
- Data Cleaning & Preprocessing
- SQLite Database Design
- Exploratory Data Analysis (EDA)
- Fund Performance Analytics
- Risk Analytics
- Investor Behavior Analysis
- Power BI Dashboard
- Rule-Based Fund Recommendation Engine
- Python
- Pandas
- NumPy
- SQLite
- Matplotlib
- Seaborn
- Power BI
Data/
├── raw/
├── processed/
Database/
├── mutual_fund.db
notebooks/
├── 01_Data_Cleaning.ipynb
├── 02_EDA.ipynb
├── 03_Advanced_Analytics.ipynb
scripts/
├── recommender.py
Reports/
├── Final_Report.pdf
├── Bluestock_MF_Presentation.pptx
- CAGR
- Annualized Return
- Sharpe Ratio
- Sortino Ratio
- Alpha
- Beta
- Tracking Error
- Value at Risk (VaR)
- Conditional VaR (CVaR)
- Rolling Sharpe Ratio
- Cohort Analysis
- SIP Continuity Analysis
- Demographic Analysis
- Industry Overview
- Fund Performance
- Investor Analytics
- SIP & Market Trends
- Risk-adjusted returns provided better fund comparison than absolute returns.
- SIP inflows showed steady growth.
- Several funds generated positive alpha against benchmarks.
- Investor participation increased across newer cohorts.
- Machine Learning Recommendations
- Real-Time NAV Integration
- Portfolio Optimization
- Investor Segmentation
Ritik Kumar
