Knowledge Base Articles
Part I - Introduction to Artificial Neural Networks
In this article series, we present a machine learning-based approach to solving a common problem in financial modelling where one is faced with the task of estimating the value of a function which requires a significant amount of computation to evaluate. More specifically, a function that corresponds to a so-called nested simulation aimed at, for example, estimating a capital requirement for a financial institution or the risk associated with a structured product for a retail investor.
Beyond Modern Portfolio Theory: Expected Utility Optimisation
The modern wealth management industry still relies on the 50-year-old approaches to portfolio management, widely popularized by Markowitz's Modern Portfolio Theory (1952). Despite heavy criticism within the academic circles, the alternative methods remain undeservingly overlooked in practice. In the context of the modern leap for hyper-customization, we look into one of the alternatives to Modern Portfolio Theory in greater detail - the Utility-based approach.
Part II - Portfolio Construction - Sampling & Optimisation
The second part of the “Portfolio Construction”-series explores whether introducing parameter uncertainty to the model would improve the out-of-sample performance of the optimal portfolio. Additionally, the article proposes and tests two adjustments to regular utility optimisation.
Part I - Portfolio Construction - Parameter & Model Uncertainty
There is a number of challenges associated with portfolio construction based on historical data. This three-part article series explores some of the most common issues attributed to the model-based portfolio optimization: the sensitivity to changes in data, large variations in portfolio weights and the bad out-of-sample performance.
Hierarchical Clustering: Prediction of Systematic Underperformance
As machine learning methods grow in use and popularity, we explore yet another dimension of wealth management that our experts consider fit for applying such frameworks. In this article, we deploy hierarchical clustering to find more consistent ways of predicting the relative future performance of funds.
Part I: An Introduction to Self-Normalizing Neural Networks
Machine learning applications have become more prominent in the financial industry in recent years. Our new article series is exploring the benefits and challenges of using self-normalising neural networks (SNNs) for calculating liquidity risk. The first piece of the series introduces the main concepts used in the investigative case study for the Swedish bond market.
Part III: Asset and Liability Management Using LSMC - Allocation Optimisation
In the third and concluding article in the ALM using LMSC series, we focus on analyzing the optimal asset allocations in the context of changing asset classes as well as finding the optimal allocation by maximizing the risk-adjusted net asset value. The estimates based on the LSMC method are then compared to the estimates obtained from the full nested Monte Carlo method.
Part II: Asset and Liability Management Using LSMC - Accuracy and Performance
The second part of the series exploring the use of Least Squares Monte Carlo in Asset and Liability Management is focused on evaluation of accuracy and performance of this method in comparison to full nested Monte Carlo simulation benchmarks.
Part I: Asset and Liability Management Using LSMC - Introduction to the Framework
In the first part of the ”Asset and Liability Management using LSMC” article series, we outline an ALM framework based on a replicating portfolio approach along with a suitable financial objective. This ALM framework, albeit simplified, is constructed to provide a straightforward replication of the complex interactions between assets and liabilities. Moreover, a brief introduction to the LSMC method used to generate all underlying risk factors is presented.
Introduction to Credit Index Modelling
This article will discuss why it is important to model credit indices and detail a number of different approaches to this problem.
Davids and Goliaths: The Role of Big Tech in Financial Services
We shouldn’t be surprised that Fintech firms are pioneering the current wave of mass digital adoption. Account management, payments and identity verification are just three areas where digital technology has and continues to augment products. In the past decade, much of the innovation has decoupled from the mainstream. Firms in hubs such as Stockholm and London have been at the forefront of pioneering fresh ideas and translating them into new consumer-centric tools. Now, as the industry matures, mainstream Tech firms are looking to add their heft into the mix: Will they overpower the relative minnows swimming in the Fintech waters, or will their efforts sink without a trace?
Leaning Into the Curve of the Pandemic
Few would have predicted a few months ago that 2020 would prove to be such a seismic event, notwithstanding that it’s US election year. Decisions made now will reverberate for years, if not decades to come. We will stay in our lane here and look at how FinTech can support better outcomes as we come out the other side.
The Role of Economic Scenario Generators in the Age of Covid-19
Economic Scenario Generators (ESGs) are fundamental to the analysis of ALM problems. Oversimplifying, they are software tools that facilitate simulated analysis of economic variables and risk factors. 6 months ago, no one in the West could have predicted what we are now experiencing. Nonetheless, we are truly now in un-navigated economic territory globally. Stress-testing and scenario analysis comes in a variety of formats and styles. Many are formulated by benchmarking variability on previous events and crises. None of these would have offered any forewarning of the impending magnitude of Covid-19. Specific predictions vary and are challenging to make, but we can be confident in seeing a record single quarter decline in global GDP. ESGs are not crystal balls and would not, ceteris paribus, have provided any direct mitigation to these challenges. However, as we prepare to make our first tentative steps into the ‘new normal’ we must surely re-evaluate the role that enhanced analytics can provide for asset allocators.
Those of us working in financial services are tasked with trying to quantify the impact the pandemic is having on the global economy. If for the purpose of this analysis alone, we selectively classify the outbreak as a financial crisis, we see a familiar pattern of behaviour: A flight to safety away from risky assets has certainly been evident in the past 6 or so weeks. Bonds, the dollar and (to some degree) gold have all benefited from the market volatility. The global financial crisis of 2008-9 is a relatively recent reminder of the last time we witnessed similar moves in asset prices. Therefore, it is absolutely reasonable to look for a correlation between that crisis and where we might head in the coming months and years.