Asset Allocation - Topics and Applications - JEM338

• Anglický název: Asset Allocation - Topics and Applications
• Český název: Asset Allocation - Topics and Applications
• Zajišťuje: Institut ekonomických studií (23-IES)
• Fakulta: Fakulta sociálních věd
• Platnost: od 2024
• Semestr: zimní
• E-Kredity: 3
• Způsob provedení zkoušky: zimní s.:
• Rozsah, examinace: zimní s.:6/0, Z [HT]
• Počet míst: 97 / neurčen (neurčen)
• Minimální obsazenost: neomezen
• 4EU+: ne
• Virtuální mobilita / počet míst pro virtuální mobilitu: ne
• Stav předmětu: vyučován
• Jazyk výuky: angličtina
• Způsob výuky: prezenční
• Poznámka: předmět je možno zapsat mimo plán; povolen pro zápis po webu; při zápisu přednost, je-li ve stud. plánu
• Garant: PhDr. František Čech, Ph.D.
• Vyučující: PhDr. František Čech, Ph.D.; Mgr. Luboš Hanus, Ph.D.; Attila Sarkany
• Třída: Courses for incoming students

Anotace

This compact course will be taught by Jakub Rojček PhD on Monday–Wednesday, September 23-25, 2024, in room 314 during following times 9:30-10:50, 11:00-12:20,14:00-15:20. For more information about the course see the Course Info video.

Course objectives
This three-day course introduces the topic of asset allocation from both a scientific and practical perspective. It synthesizes academic and industry references across fields of portfolio optimization, asset pricing, and risk management on asset class level. The course is rooted in Modern portfolio theory and its subsequent developments until the present time from both theoretical and empirical perspective. First, we motivate the topic of asset allocation by highlighting the current practical industry applications. Afterwards, we briefly review the basic concepts of risk and return trade-off, and the resulting mean-variance optimization, but quickly move towards the current state of asset allocation models with expected returns modeled using building block approach, use of regimes to tackle uncertainty in estimates, and further robust optimization techniques along with inclusion of views into optimal portfolios. We also cover the topic of shorter-term tactical asset allocation rooted in global macroeconomics signals, and include tactical portfolio construction. We conclude by exploring further cutting edge natural language processing (NLP) based signals and discuss avenues of future research and practical applications. In addition to lectures, coursework consists of practical coding sessions with short coding homeworks, as well as group projects, where students are expected to solve a practical asset allocation problem and write a short report. Individually, students will also submit a short essay discussing what investment process would be suitable to their individual financial objectives. Students are expected to gain a broad overview of asset allocation topics, learn about practical considerations of predicting future returns and portfolio optimization, as well as gain practical coding experience.

Poslední úprava: Čech František, PhDr., Ph.D. (23.05.2024)

Podmínky zakončení předmětu

Class participation (10%)

Group project (60%)

• Deadline: 31.10.2024 midnight
• Students are required to analyze and tackle a project in groups of two/three and submit a report  of maximum ten pages alongside working Python code. Sample data will be provided for each individual project. Students may choose from the following list of topics or submit and get approval of their own topic by the last lecture.
• Possible topics:
• Define and backtest a macroeconomics based tactical strategy based on estimates of aggregate supply and demand and analyze its performance. (Based on a chapter in Pedersen (2019))
• Replicate an equity risk-premium strategy for US equities and define, backtest and report on a strategy that can invest in US equities, but also in US Treasuries. (GS paper)
• Optimize a static portfolio robustly using the absolute worst mean-variance optimization for a CZK reference currency based investor, who can invest globally in aggregate bonds, International equities, gold and commodities. (Based on Tütüncu and Koenig 2004).
• Create, backtest and report on a risk-parity allocation investing in bonds, equities, commodities and inflation protected treasuries (UBS case study).
• Create an annually updated portfolio based on mean-variance optimization when including views on US equities derived from realized time series of return and forward-looking estimates discussed in the class using entropy pooling of Meucci (2010).

Individual essay (30%)

• hand-written during the last session, i.e. 25.9.2024 11:00-12:20
• Students are required to submit an essay of up to 2 pages written without any equations, on the topic of “The investment strategy that will help me accomplish my financial goals is the following...”Students do not necessarily have to discuss their own personal goals and possible investment strategy, they can also impersonate one from the following list (not exhaustive) and add whatever assumptions needed:
• Newly founded family office
• Working professional 10 years before reaching retirement age
• Entrepreneur in an AI space
• Foundation supporting wildlife conservancy with annual dividend
• Venture capitalist running a series of closed-end funds
• Portfolio manager running a liquid multi-asset portfolio
• Young professional aiming at early financial independence
•  ...

CONDITION: group project and individual essay cannot have overlapping topic

Poslední úprava: Čech František, PhDr., Ph.D. (05.08.2024)

Literatura

References

Books (required)

Fabozzi, F. J., Kolm, P. N., Pachamanova, D. A., & Focardi, S. M. (2007). Robust portfolio optimization and management. John Wiley & Sons.

Kinlaw, W., Kritzman, M. P., & Turkington, D. (2021). Asset allocation: from theory to practice and beyond. John Wiley & Sons.

 

Books (further reading)

Boyd, S. P., & Vandenberghe, L. (2004). Convex optimization. Cambridge university press.

Grinold, R. C., & Kahn, R. N. (2000). Active portfolio management.

Ilmanen, A. (2011). Expected returns: An investor's guide to harvesting market rewards (Vol. 535). John Wiley & Sons.

Ilmanen, A. (2012). Expected returns on major asset classes. CFA Institute Research Foundation, 1.

Ilmanen, A. (2022). Investing Amid Low Expected Returns: Making the Most when Markets Offer the Least. John Wiley & Sons.

Lopez de Prado, M. (2022). Causal Factor Investing: Can Factor Investing Become Scientific?. Available at SSRN 4205613.

Meucci, Attilio. Risk and asset allocation. Vol. 1. New York: Springer, 2005.

Pedersen, L. H. (2019). Efficiently inefficient: how smart money invests and market prices are determined. Princeton University Press.

Siegel, J. J. (2021). Stocks for the long run: The definitive guide to financial market returns & long-term investment strategies. McGraw-Hill Education.

 

Articles (selected)

Ang, A., & Bekaert, G. (2002). International asset allocation with regime shifts. The review of financial studies, 15(4), 1137-1187.

AQR, 2017: “Capital Market Assumptions Technical Appendix: Equity Expected Return Methodology”

AQR, Q1 2021: “Capital Market Assumptions for Major Asset Classes”

Bacchetta, P., Benhima, K., & Renne, J. P. (2022). Understanding Swiss real interest rates in a financially globalized world. Swiss Journal of Economics and Statistics, 158(1), 16.

Barclays, 2021: “Capital Market Assumptions”

Bauer, M. D., & Rudebusch, G. D. (2020). Interest rates under falling stars. American Economic Review, 110(5), 1316-1354.

Campbell, J. Y., & Shiller, R. J. (2001). Valuation ratios and the long-run stock market outlook: An update.

De Prado, M. L. (2016). Building diversified portfolios that outperform out of sample. The Journal of Portfolio Management, 42(4), 59-69.

Engle, R. F., Ledoit, O., & Wolf, M. (2019). Large dynamic covariance matrices. Journal of Business & Economic Statistics, 37(2), 363-375.

Ferreira, M. A., & Santa-Clara, P. (2011). Forecasting stock market returns: The sum of the parts is more than the whole. Journal of Financial Economics, 100(3), 514-537.

Fung, W., & Hsieh, D. A. (2004). Hedge fund benchmarks: A risk-based approach. Financial Analysts Journal, 60(5), 65-80.

Geltner, D. M. (1991). Smoothing in appraisal-based returns. The Journal of Real Estate Finance and Economics, 4, 327-345.

Geltner, D. (1993). Estimating market values from appraised values without assuming an efficient market. Journal of Real Estate Research, 8(3), 325-345.

Goodwin, T. H. (1998). The information ratio. Financial Analysts Journal, 54(4), 34-43.

Grinold, R. C., Kroner, K., & Siegel, L. B. (2011). A Supply Model of the Equity Premium. Rethinking the Equity Risk Premium, 53-70.

Holston, K., Laubach, T., & Williams, J. C. (2017). Measuring the natural rate of interest: International trends and determinants. Journal of International Economics, 108, S59-S75.

Kaplan, S. N., & Schoar, A. (2005). Private equity performance: Returns, persistence, and capital flows. The journal of finance, 60(4), 1791-1823.

Kim, J. H., Kim, W. C., & Fabozzi, F. J. (2014). Recent developments in robust portfolios with a worst-case approach. Journal of Optimization Theory and Applications, 161, 103-121.

Knox, B., & Vissing-Jorgensen, A. (2022). A stock return decomposition using observables.

Kuhn, D., Esfahani, P. M., Nguyen, V. A., & Shafieezadeh-Abadeh, S. (2019). Wasserstein distributionally robust optimization: Theory and applications in machine learning. In Operations research & management science in the age of analytics (pp. 130-166). Informs.

Kritzman, M., Li, Y., Page, S., & Rigobon, R. (2010). Principal components as a measure of systemic risk. Available at SSRN 1582687.

Ilmanen, A., Israel, R., Moskowitz, T. J., Thapar, A. K., & Lee, R. (2021). How do factor premia vary over time? A century of evidence. A Century of Evidence (February 18, 2021).

Ledoit, O., & Wolf, M. (2004). A well-conditioned estimator for large-dimensional covariance matrices. Journal of multivariate analysis, 88(2), 365-411.

Ledoit, O., & Wolf, M. (2022). The power of (non-) linear shrinking: A review and guide to covariance matrix estimation. Journal of Financial Econometrics, 20(1), 187-218.

López de Prado, M., & Lewis, M. J. (2019). Detection of false investment strategies using unsupervised learning methods. Quantitative Finance, 19(9), 1555-1565.

Meucci, A. (2010). Fully flexible views: Theory and practice. arXiv preprint arXiv:1012.2848.

Michaud, R. O., & Michaud, R. (2007). Estimation error and portfolio optimization: a resampling solution. Available at SSRN 2658657.

Rockafellar, R. T., & Uryasev, S. (2002). Conditional value-at-risk for general loss distributions. Journal of banking & finance, 26(7), 1443-1471.

Rogoff, K. (1996). The purchasing power parity puzzle. Journal of Economic literature, 34(2), 647-668.

Rousseeuw, P. J., & Driessen, K. V. (1999). A fast algorithm for the minimum covariance determinant estimator. Technometrics, 41(3), 212-223.

Ross, S., 1976a. The arbitrage theory of capital asset pricing. Journal of Economic Theory 13, 341–60.

Ross, S., 1976b. Risk, return and arbitrage. Risk Return in Finance ed. I. Friend and J. Bicksler, Cambridge, Mass.: Ballinger.

Scherer, B. (2007). Can robust portfolio optimisation help to build better portfolios?. Journal of Asset Management, 7, 374-387.

Stambaugh, R. F. (1997). Analyzing investments whose histories differ in length. Journal of Financial Economics, 45(3), 285-331.

Straehl, P. U., & Ibbotson, R. G. (2017). The long-run drivers of stock returns: Total payouts and the real economy. Financial Analysts Journal, 73(3), 32-52.

Sung, C. H. (2023). Invesco Investment Insights.

Tütüncü, R. H., & Koenig, M. (2004). Robust asset allocation. Annals of Operations Research, 132, 157-187.

Poslední úprava: Čech František, PhDr., Ph.D. (26.04.2024)

Sylabus

DAY 1 (depending on progress in class)

1. Introduction to asset allocation
    a. Strategic asset allocation
    b. Tactical asset allocation
    c. Risk and portfolio management    

Reading required: Kinlaw et al (2021) chapters 1, 2, 3, 10 ; Fabozzi et al (2007) chapters 1, 14

2. Modern portfolio theory
    a. Utility functions and investment evaluation
    b. Mean-variance optimization
    c. Convex optimization
    d. Two fund separation theorem
    e. Factor investing 
    f. Arbitrage pricing theory

Reading required: Fabozzi et al (2007) chapters 2, 3, 4, 5, 9; Kinlaw et al (2021) chapter 8
Reading optional: Ross (1976)

3. Robust covariance estimation
    a. Sample covariance
    b. Exponential weighted moving average (EWMA)
    c. Ledoit Wolf shrinkage
    d. Factor based covariance
    e. If time: Constant and dynamic conditional correlation (CCC, DCC); Minimum covariance determinant; Hierarchical risk parity; Translations between local and reference currencies and hedging decisions; Backfilling returns time series; Risk of private markets investments and un-smoothing of time series; 

Reading required: Fabozzi et al (2007) chapter 8
Reading optional: De Prado (2016); Ledoit and Wolf (2003, 2022); Engle, Ledoit and Wolf (2019); Rousseeuw and Driessen (1999); Stambaugh (1997); Geltner (1991)

4. Coding session 1
    a. Geometric vs Arithmetic vs Continuous returns
    b. Portfolio evaluation
    c. Basics of portfolio optimization
    d. Covariance
    e. Sample returns
    f. Time to discuss group projects

DAY 2 (depending on progress in class)

5. Long-term expected returns
    a. Equilibrium approach
    b. Building block approach for fixed income and foreign exchange
    c. Expected returns on equities including building block approach
    d. If time: Building block approach for commodities, hedge funds, private markets, real assets
    e. If time: Translations between local and reference currencies and hedging decisions

Reading required: Barclays (2021) Capital Market Assumptions; Ilmanen (2012); Kinlaw et al (2021) chapter 13
Reading optional: Ferreira and Santa-Clara (2011); Grinold et al (2011); Holston et al (2017); Fung and Hsieh (2004); Pedersen (2019) chapter 10; Siegel (2021) chapters 5, 6, 7, 8, 9, 10; Invesco (2023) Capital Market Assumptions

6. Robust optimization
    a. Optimization of utility vs variance vs CVaR
    b. Resampled robust optimization
    c. If time: Bayesian approach; Absolute robust optimization; Relative robust optimization; Distributionally robust optimization

Reading required: Fabozzi et al (2007) chapters 10, 11, 12; Kinlaw et al (2021) chapter 19; Scherer (2007); Rockafellar and Uryasev (2002)
Reading optional: Michaud and Michaud (2007); Kuhn et al (2019)

7. Views on markets
    a. Black Litterman
    b. Meucci’s Entropy pooling

Reading required:Fabozzi et al (2007) chapter 9
Reading optional: Meucci (2010)

8. Coding session 2

    a. Forward looking expected returns
    b. CVaR optimization
    c. Black-Litterman
    d. Resampled optimization
    e. Time to discuss group projects

DAY 3 (depending on progress in class)

9. Macroeconomic and market regimes
    a. What are regimes and why they matter
    b. Macroeconomic regimes
    c. Regimes in optimization
    d. If time: Market regimes; Risk parity portfolios

Reading required: Kinlaw et al (2021) chapters 14, 22
Reading optional: Pedersen (2019) chapter 11; Ang and Bekaert (2002)

10. Tactical asset allocation and dynamic strategies
    a. What is tactical asset allocation?
    b. Signal generation and backtesting systematic strategies
    c. Macro investing
    d. Technical and sentiment analysis
    e. Valuations
    f. Trend and momentum
    g. Value and carry
    h. If time: Grinold Kahn approach; Regime bases strategies; Factor based strategies; Protection and defensive strategies; AI and NLP applications

Reading required: Kinlaw et al (2021) chapter 17; Ang and Bekaert (2002)
Reading optional: Pedersen (2019) chapters 1, 2, 3, 4, 5, 10, 11, 12; López de Prado (2016, 2019, 2022); Ilmanen et al (2021); Goodwin (1998)

11. Coding session 3
    a. Generating and backtesting signals
    b. Example single asset and cross-asset strategies
    c. Optimization and backtesting of dynamic multi asset strategies
    d. Time to discuss group projects

Poslední úprava: Čech František, PhDr., Ph.D. (26.04.2024)

Vstupní požadavky

Python resources

Students are expected to bring their own laptops to the coding sessions.

Data and functional Jupyter notebooks will be distributed a few weeks before the start of the course and we’ll cover these during the coding sessions.

 

Students are responsible for creating their own Python capable setup that they will be able to use throughout the course and during the group projects.

 

I recommend using an individual Anaconda distribution that solves the different packages dependencies and you can download and install it using resources here: https://www.anaconda.com/

 

You will find the resources there helpful, this video should also help get you started https://www.youtube.com/watch?v=4DQGBQMvwZo

 

Then you can use any IDE you want, be it Spyder (similar to RStudio), or Pycharm- more professional coding experience, or even Jupyter notebook or JupyterLab. You can install any of these through Anaconda navigator.

 

For portfolio optimization, we’ll try coding a few routines ourselves, but we’ll also make use of already existing software. I encourage you to explore e.g. the very good pypfopt package https://pyportfolioopt.readthedocs.io/en/latest/

 

Useful libraries for statistics and econometric purposes would be scipy and statsmodels https://www.statsmodels.org/stable/index.html ; https://www.scipy.org/

Poslední úprava: Čech František, PhDr., Ph.D. (26.04.2024)