Portfolio Performance Attribution: A Machine Learning‐Based Approach

Author(s):  
Ryan Brown ◽  
Harindra de Silva ◽  
Patrick D. Neal
Author(s):  
Mehmet Fatih Bayramoglu ◽  
Cagatay Basarir

Investing in developed markets offers investors the opportunity to diversify internationally by investing in foreign firms. In other words, it provides the possibility of reducing systematic risk. For this reason, investors are very interested in developed markets. However, developed are more efficient than emerging markets, so the risk and return can be low in these markets. For this reason, developed market investors often use machine learning techniques to increase their gains while reducing their risks. In this chapter, artificial neural networks which is one of the machine learning techniques have been tested to improve internationally diversified portfolio performance. Also, the results of ANNs were compared with the performances of traditional portfolios and the benchmark portfolio. The portfolios are derived from the data of 16 foreign companies quoted on NYSE by ANNs, and they are invested for 30 trading days. According to the results, portfolio derived by ANNs gained 10.30% return, while traditional portfolios gained 5.98% return.


Risks ◽  
2019 ◽  
Vol 7 (3) ◽  
pp. 74 ◽  
Author(s):  
Prayut Jain ◽  
Shashi Jain

The Hierarchical risk parity (HRP) approach of portfolio allocation, introduced by Lopez de Prado (2016), applies graph theory and machine learning to build a diversified portfolio. Like the traditional risk-based allocation methods, HRP is also a function of the estimate of the covariance matrix, however, it does not require its invertibility. In this paper, we first study the impact of covariance misspecification on the performance of the different allocation methods. Next, we study under an appropriate covariance forecast model whether the machine learning based HRP outperforms the traditional risk-based portfolios. For our analysis, we use the test for superior predictive ability on out-of-sample portfolio performance, to determine whether the observed excess performance is significant or if it occurred by chance. We find that when the covariance estimates are crude, inverse volatility weighted portfolios are more robust, followed by the machine learning-based portfolios. Minimum variance and maximum diversification are most sensitive to covariance misspecification. HRP follows the middle ground; it is less sensitive to covariance misspecification when compared with minimum variance or maximum diversification portfolio, while it is not as robust as the inverse volatility weighed portfolio. We also study the impact of the different rebalancing horizon and how the portfolios compare against a market-capitalization weighted portfolio.


Trader performance is currently measured against various benchmarks without consideration for the volatility of trading results. The author introduces trader alpha frontier (TAF) as a way to measure trader performance against the risks taken by the trader. This article formulates how to carve out trader alpha from overall portfolio returns. It also explores trader performance attribution by delineating between the main components of trader alpha and suggesting benchmarks to measure each component. As a result, the author unveils a new benchmark, called execution-weighted price (EWP). It is tough to reach TAF, but it is worth the effort since it aligns the mutual objective of a portfolio manager and a trader to maximize overall portfolio performance.


Financial Ratios have been a major indicator for financial asset selection. It’s seen that the decision taken to construct a portfolio based on financial ratio indicators has been able to make better returns than the random asset allocation process in the portfolio. This research will show multiple classifications based on unsupervised machine learning processes to satisfactorily determine investable assets or securities for portfolio contribution. Our suggested portfolio would then be compared with a random portfolio for a specific time frame in order to determine portfolio return, Sharpe ratio, and portfolio performance.


2013 ◽  
Vol 5 (12) ◽  
pp. 815-824
Author(s):  
Heng-Hsing Hsieh

In the recognition that investment management is an on-going process, the performance of actively-managed portfolios need to be monitored and evaluated to ensure that funds under management are efficiently invested in order to satisfy the mandate specified in the policy statement. This paper discusses the primary performance evaluation techniques used to measure a portfolio’s basic risk and return characteristics, risk-adjusted performance, performance attribution and market timing ability. It is concluded that the Treynor measure is more suitable for evaluating portfolios that are constituents of a broader portfolio, while the information ratio is useful for evaluating hedge funds with an absolute return objective. Although the Sharpe ratio and M-squared arrive at the same evaluation result, M-squared provides a direct comparison between the portfolio and the benchmark. With regard to the analysis of portfolio performance attribution, it is found that the return-based multifactor model of Sharpe (1992) is not suitable for analyzing the performance of hedge funds that engage in short-selling, leverage and derivatives. Additional factors generated by factor analysis could be used as factors in the extended model of Sharpe (1992) to analyze hedge fund return attributions. Finally, the Treynor and Mazuy (1966) model and the Henriksson and Merton (1981) model essentially distinguish the market timing ability from the security selection ability of the portfolio manager.


2020 ◽  
Vol 43 ◽  
Author(s):  
Myrthe Faber

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.


Sign in / Sign up

Export Citation Format

Share Document