Python-Driven Portfolios: Bridging Theory and Practice for Efficient Investments
summary
Claims a working Python implementation of Modern Portfolio Theory using five ETFs pulled from yahu finance (2018–2022), computes daily log returns, covariance and annualized risk, and runs Monte Carlo weight simulations to plot an efficient frontier and pick an optimal Sharpe‑ratio portfolio. Notebook is shown and offered. Demo cuts short for time and questions move to Discord. Watch if seeing the actual code, data source, number of simulations and final portfolios matters.
AI-written summary · about
chapters (17)
- 0:00Introduction
- 2:14Financial portfolio
- 4:00Harry Markowitz and modern portfolio theory
- 8:56Modern portfolio theory
- 11:50Portfolio returns
- 13:41Risk and return modeling
- 16:33Diversification in MPT
- 18:16Correlation and risk
- 19:18Efficient frontier
- 20:25Demo introduction and data gathering
- 21:49Fetching financial data
- 23:18Daily and annual returns
- 24:25Asset return visualization
- 25:10Correlation matrices
- 25:53Random portfolio weights
- 27:00Portfolio variance and return
- 28:01Plotting efficient frontier
related talks
47mCreating a Contemporary Risk Management System Using Python
01h 18mUsing Financial Data APIs: A Guide to Collection & Integration
29mMonte Carlo Business Case Analysis with pandas
36mA Data Science Approach to Systemic Risk
51mLightning Talks
27mEnhancing Analytical Efficiency in Stock Market Analysis
42mRobust Automated Forecasting in Python and R
23mAn Open Source Architecture for Modernizing Market Risk Management