Advanced Portfolio Analysis with Python

Learn advanced portfolio analysis through a practical course with Python programming language using asset classes benchmark indexes replicating funds historical data for back-testing. It explores main concepts from proficient to expert level which can help you achieve better grades, develop your academic career, apply your knowledge at work or do your research as experienced investor. All of this while exploring the wisdom of Nobel Prize winners and best practitioners in the field.

Become an Advanced Portfolio Analysis Expert in this Practical Course with Python

• Read or download asset classes benchmark indexes replicating funds data to perform advanced portfolio analysis operations by installing related packages and running code on Python PyCharm IDE.

• Compare asset classes benchmark indexes replicating funds returns and risks tradeoffs for fixed income or bonds and equities or stocks.

• Estimate asset classes expected returns through historical annualized returns and risks through historical returns annualized standard deviation. 

• Calculate portfolios Sharpe ratios performance metrics.

• Estimate benchmark global portfolio returns from periodically rebalanced equal weighted assets allocation.

• Optimize global portfolios asset allocation weights for mean maximization, standard deviation minimization, mean maximization and standard deviation minimization, mean maximization and value at risk minimization objectives within training range based on Markowitz portfolio theory.

• Approximate global portfolios returns from periodically rebalanced optimized asset allocations within testing range and compare them with equal weighted benchmark portfolio.

• Minimize portfolio assets allocation weights optimization back-testing overfitting or data snooping through multiple hypothesis testing adjustment.

• Approximate two population mean statistical inference two tails tests multiple probability values.

• Adjust two population mean multiple probability values through family-wise error rate or Bonferroni procedure and false discovery rate or Benjamini-Hochberg procedure.

• Reduce portfolio assets allocation weights optimization back-testing overfitting or data snooping through individual time series bootstrap hypothesis testing multiple comparison adjustment.

• Simulate two population mean probability distributions through random fixed block re-sampling with replacement.

• Estimate two bootstrap population mean statistical inference percentile confidence interval and two tails tests percentile probability values.

• Correct two individual bootstrap population mean probability values multiple comparisons through family-wise error rate adjustment.

Become an Advanced Portfolio Analysis Expert and Put Your Knowledge in Practice

Learning advanced portfolio analysis is indispensable for finance careers in areas such as asset management, private wealth management and risk management within institutional investors represented by banks, insurance companies, pension funds, hedge funds, investment advisors, endowments and mutual funds. It is also essential for academic careers in advanced quantitative finance. And it is necessary for experienced investors advanced optimized asset allocation strategies research.

But as learning curve can become steep as complexity grows, this course helps by leading you step by step using asset classes benchmark indexes replicating funds historical data for back-testing to achieve greater effectiveness.

Content and Overview

This practical course contains 36 lectures and 4.5 hours of content. It’s designed for advanced portfolio analysis knowledge levels and a basic understanding of Python programming language is useful but not required.

At first, you’ll learn how to read or download asset classes benchmark indexes replicating funds data to perform advanced portfolio analysis operations by installing related packages and running code on Python PyCharm IDE.

Then, you’ll define asset classes by comparing their benchmark indexes replicating funds returns and risks tradeoffs. For asset classes, you’ll define fixed income or bonds and equities or stocks. Regarding fixed income or bonds asset class, you’ll use U.S. total bond market and international total bond market benchmark indexes replicating funds. Regarding equities or stocks asset class, you’ll use U.S. total stock market and international total stock market benchmark indexes replicating funds. Next, you’ll define returns and risks. For expected returns, you’ll calculate historical annualized returns. For risks, you’ll estimate historical returns annualized standard deviations. Later, you’ll define portfolio optimization through global assets allocation. After that, you’ll calculate Sharpe ratios portfolios performance metrics. Then, you’ll estimate benchmark global portfolio returns from periodically rebalanced equal weighted assets allocation. Next, you’ll optimize assets allocation weights within training range for mean maximization, standard deviation minimization, mean maximization and standard deviation minimization, mean maximization and value at risk minimization objectives based on Markowitz portfolio theory. Later, you’ll calculate global portfolio returns within testing range using previously optimized periodically rebalanced assets allocation weights and compare them with equal weighted benchmark portfolio.

After that, you’ll reduce global portfolios assets allocation weights optimization back-testing overfitting or data snooping through multiple hypothesis testing adjustment. Then, you’ll define multiple hypothesis testing statistical inference. Next, you’ll define probability value estimation. For probability value estimation, you’ll do two multiple population mean two tails tests. Later, you’ll define multiple probability values estimation adjustment. For two multiple probability values estimation adjustment, you’ll do family-wise error rate or Bonferroni procedure and false discovery rate or Benjamini-Hochberg procedure multiple probability values estimations adjustments.

Next, you’ll reduce global portfolios assets allocation weights optimization back-testing overfitting or data snooping through individual time series bootstrap hypothesis testing multiple comparison adjustment. For time series bootstrap, you’ll do two population mean probability distribution simulations through random fixed block re-samples with replacement. Then, you’ll define bootstrap parameters estimation statistical inference. Later, you’ll define point estimation. For point estimation, you’ll do two population mean point estimations. After that, you’ll define bootstrap confidence interval estimation. For bootstrap confidence interval estimation, you’ll do two bootstrap population mean percentile confidence intervals estimations. Then, you’ll define bootstrap hypothesis testing. Next, you’ll define bootstrap probability value estimation. For probability value estimation, you’ll do two bootstrap population mean percentile two tails tests. Finally, you’ll define individual bootstrap probability value estimation multiple comparison adjustment. For two individual bootstrap probability value estimations multiple comparison adjustments, you’ll do family-wise error rate individual probability value estimation multiple comparison adjustments.