Monday, March 18, 2024

ARPs - stock and bond betas can be very different

 


Investors can buy alternative risk premium products across many styles and asset classes, but there are trade-offs between equity and bond risk. You carry strategies will often have positive equity betas but will also have negative bond betas. Alternatively, trend strategies will have positive bond betas but negative equity betas. Both have betas that are relatively low. This is one of the reasons why many investors or managers find the combination of trend with carry appealing. You give up some directional exposure; however, you gain protection between both up and own moves with equities and bonds.

The following analysis is available in a thorough research paper which has been recently published but can still be found in working paper form, "A Framework for Risk Premia Investing: Anywhere to Hide" by Kari Vatanen and Antti Suhonen. We have looked at their work in previous posts on beta stability, "ARP strategies and market beta - Check the stability when constructing portfoliosand with cluster analysis in "Alternative risk premia and the advantage of cluster analysis".

Saturday, March 16, 2024

Hedge funds versus ARP - Worth a hard look

 


The real battle in hedge fund land is the choice between buying a hedge or buying an alternative risk premia product often in the form of a swap. The ARP products were created to provide a low cost way of gaining exposure to long-short risk premia factors through total return swaps. The risk premium you have often seen described in the finance literature can be packaged in a form that does not have the same high fees as hedge funds and do not include incentive fees. 

They are not perfect. You must manage the exposure as opposed to having a manager control the risks, yet it provides a simple way to gain access to momentum, carry, and value across all major asset classes. This paper is a few years old but it makes a strong case for ARPs, see "Hedge Funds vs Alternative Risk Premia" by Philippe Jorion.

The burden is now on hedge funds to provide a unique return profile that is can dynamically adjust exposures or have a unique strategy that cannot be easily translated into an index that can be placed in a swap form. Bank risk premia swaps are intermediating the hedge fund market with exposure, trading, operating, and leverage expertise. In fact, the ARP products are cheaper so if they can closely match hedge fund gross returns, they will have a cost advantage. 

The development of ARP factor exposures is no different than the factor and index boom for long-only investing. If you can buy an index associated with a specific factor like size which will provide most of the desired exposure, the burden is on the active manager to provide alpha relative to that factor or benchmark.

Can you find better hedge fund? Yes, but now there is an alternative which places the burden on the manager to prove their value.   




Friday, March 15, 2024

Private equity dispersion a key risk


The table above is from the CAIS group and shows another risk from private equity beyond the standard deviation of returns over time. There is large dispersion  in return, much more than what is seen with traditional asset and hedge funds. Simply put, the risk of picking the wrong manager is much higher in the private equity space. 

The median return for private equity may be higher than traditional and hedge fund managers but the downside risk is more significant. Investor disappointment versus the median can be significant. This requires extra due diligence on the part of investors.  Yes, the upside from picking the right manager is higher, but everyone cannot be above average.

Thursday, March 14, 2024

SHAP and explainable AI - Getting to know your models

 



ML models are hard to understand relative to classic regression analysis. Some fear that ML is often a black box but there are ways to make these models more transparent or have interpretability. The tool most used for explainable AI is the SHAP values (SHapley Additive exPlanations) uses game theory to measure each player or in this case feature contribution to the outcome. 

Each feature is assigned an importance value which represents the contribution to model's output. Features with a positive (negative) SHAP value will have a positive (negative) impact on the prediction. These SHAP values are additive, so each feature can have a contribution to the final prediction and summed.  While the SHAP values can tell us the contribution to the prediction, it cannot tell us about the quality of the model. 

Given the properties of SHAP values, there several ways to display their information. It can be displayed as a waterfall graph which tells whether each feature is adding or subtracting from the prediction. The sum of all predictions will be equal to E[f(x) - f(x)]. The absolute value of the SHAP tells us the overall importance of the feature. Note, the SHAP values can be calculated for any prediction model. 

It may be interesting to measure the impact of non-price information on a prediction through using the SHAP value. There are many ways to use this tool to help refine forecasts and provide insights on non-linear relationships. 

The SHAP values tells us the importance of a specific feature observation, so information is often displayed as a bee swarm plot which tells us the impact of different observations associated with a feature.  You can also use violin plots which again will tell the SHAP value for specific observations associated with specific feature. Force, bar, and waterfall plots all tell us something about the drivers of our model, and all these tools are available in python.