This blog post explores the impacts of Covid-19 by simulating two investment portfolios – a portfolio consisting of peripheral stocks, versus a portfolio consisting of central stocks in the Planar Maximally Filtered Graph. The goal was to highlight the repercussions of the Covid related decline in the market, which shook the world in mid-February (in the case of the US markets). The portfolios take positions at the worst possible timing in order to understand – had you invested just before the dramatic crash of the market, how would a peripheral portfolio behave compared to a central portfolio? Are peripheral portfolios any better during an unexpected crisis?
Research articles for the Hudson and Thames home page.
Following the work of Professor Tim Leung and Xin Lee, we explore how the Ornstein-Uhlenbeck process known for modelling mean-reverting interest rates, currency exchange rates, and commodity prices can be used in pairs trading and statistical arbitrage. The two-step process looks the following way:
Network analysis can provide interesting insights into the dynamics of the market and the continually changing behaviour. A Minimum Spanning Tree (MST) is a useful method of analyzing complex networks, for aspects such as risk management, portfolio design, and trading strategies. For example:
There are 6 properties that empirical correlation matrices exhibit that no synthetic generation method has been able to replicate, until now.
Enabling researchers to backtest strategies on an abundance of data would make our algorithms and strategies more robust, accurate, and efficient. Since historical data can be biased and does not have enough high-stress events to test multiple scenarios, generating synthetic data is a practical way to overcome this problem. However, generating data that is realistic is not an easy task.
“Everybody complains about the weather, but nobody does anything about it.” A quip by Charles Dudley Warner, a contemporary of Mark Twain perhaps captures the (lack thereof) action on the environmental crisis. The extreme weather events, rising sea levels, more frequent and stronger storms are further exacerbating the social, economic and environmental stress on the most vulnerable communities of the world. So, what can be done to turn around this situation?
For a long while, investors worked under the assumption that the risk and return relationship of a portfolio was linear, meaning that if an investor wanted higher returns, they would have to take on a higher level of risk. This assumption changed when in 1952, Harry Markowitz introduced Modern Portfolio Theory (MPT). MPT introduced the notion that the diversification of a portfolio can inherently decrease the risk of a portfolio. Markowitz’s work on MPT was groundbreaking in the world of asset allocation, eventually earning him a Nobel prize for his work in 1990. Throughout this blog post, we will explore Markowitz’s Modern Portfolio Theory and work through a full implementation in the MlFinLab library.
Risk has always played a very large role in the world of finance with the performance of a large number of investment and trading strategies being dependent on the efficient estimation of underlying market risk. The covariance matrix is one of the most popular and widely used estimator of risk but due to its sensitivity to market conditions and dependence on historical data, it produces an unreliable estimation of true market risk. In this post, we go over some important methods of estimating covariance matrices which can be used in practice to remove noise from empirical estimates and produce better and reliable risk estimations.
In 2018, Thomas Raffinot developed the Hierarchical Equal Risk Contribution (HERC) algorithm, combining the machine learning approach of the Hierarchical Clustering based Asset Allocation (HCAA) algorithm with the recursive bisection approach from Hierarchical Risk Parity. The HERC algorithm aims to diversify capital and risk allocations and generate robust risk-adjusted portfolios which outperform out-of-sample.
For over half a century, most asset managers have used historical correlation matrices (empirical or factor-based) to develop investment strategies and build diversified portfolios. The Theory-Implied Correlation matrix combines external market views with emprirical values to generate new correlations which are less noisy and in sync with the economic theory.
As diversification is the only free lunch in finance, the Hierarchical Equal Risk Contribution Portfolio (HERC) aims at diversifying capital allocation and risk allocation. Briefly, the principle is to retain the correlations that really matter and once the assets are hierarchically clustered, a capital allocation is estimated. HERC allocates capital within and across the “right” number of clusters of assets at multiple hierarchical levels.