Asset Correlation Research Articles

Domain-dependent diversification: The influence of gain–loss domain on correlation choice

Despite compelling evidence of widespread gain–loss-domain-dependent behavior, research on domain-dependent diversification is scarce. We recruited 251 experienced US retail investors to participate in a controlled experiment with the task to select portfolios that differ in asset correlation and, hence, diversification benefits in both the gain and the loss domain. We find evidence of domain-dependent diversification, both unconditional and conditional on benchmark portfolio preferences. Consistent with a loss-attention hypothesis, diversification errors are not observed in the loss domain but are clearly present in the gain domain (with much lower diversification relative to the benchmark).

Quantitative easing and correlation dynamics in the aftermath of the Great Recession: A dynamic conditional correlation with exogenous variables approach

AbstractIdentifying the effects of quantitative easing (QE) on asset return correlations is critical to assessing such policies’ impact across financial markets. In this paper, we use a dynamic conditional correlation model that allows us to measure the impact of unconventional monetary policy on time‐varying correlations. Our results suggest that QE significantly affected correlations between stocks and bonds after the Great Recession via short‐term portfolio balance effects. The findings are critical for policy‐makers and practitioners alike. Central banks should consider the impact of monetary policy on asset correlations in their cost–benefit analyses. Likewise, portfolio managers are encouraged to factor in the effects of monetary policy on correlations to optimize portfolios and reduce potential losses strategically.

A Self-Adaptive Centrality Measure for Asset Correlation Networks

A Self-Adaptive Centrality Measure for Asset Correlation Networks

Estimating Asset Parameters Using Levy’s Moment Matching Method

Conventionally, the unknown parameters in Merton’s model are set using a calibration method that estimates the current asset value and volatility from observable stock prices. This paper describes a completely different approach for estimating these asset parameters. The proposed approach uses Levy’s moment matching method to derive an equation for the asset value based on the sum of equity and debt on the balance sheet, with the current debt value treated as an unknown and estimated from stock prices. Empirical analysis reveals that this method results in simpler calculations than the calibration method and can estimate the asset parameters and default probability to the same degree of accuracy. An additional advantage of the proposed method is that it estimates the asset correlation if the current debt value is known, allowing Merton’s model to be extended to multiple companies. The asset correlation obtained by the proposed method is estimated from multiple parameters related to equity, debt, and the evaluation period, which is useful when the influence of equity volatility, leverage, and time must be considered in estimating asset correlations based on equity correlations.

Portfolio optimization and risk management through Hierarchical Risk Parity and Logic Learning Machine: a case study applied to the Turkish stock market

This study explores an innovative approach to portfolio optimization, bridging traditional Modern Portfolio Theory (MPT) with advanced Machine Learning techniques. We start by recognizing the significance of Markowitz's model in MPT and quickly proceed to focus on the Hierarchical Risk Parity (HRP) method. HRP overcomes some of the limitations of Markowitz's model, particularly in managing complex asset correlations, by offering a more refined risk management strategy that ensures balanced risk distribution across the portfolio. The paper then introduces an innovative Machine Learning approach that employs the Logic Learning Machine (LLM) method to enhance the explainability of the Hierarchical Risk Parity strategy. Such integration is considered the core research part of the study, given that its application makes the output of the model more accessible and transparent. A case study based on the Turkish stock market has been provided as an example. The combination of traditional financial theories with modern Machine Learning tools marks a significant advancement in investment management and portfolio optimization, emphasizing the importance of clarity and ease of understanding in complex financial portfolio models.

Temporal Implicit Multimodal Networks for Investment and Risk Management

Many deep learning works on financial time-series forecasting focus on predicting future prices/returns of individual assets with numerical price-related information for trading, and hence propose models designed for univariate, single-task, and/or unimodal settings. Forecasting for investment and risk management involves multiple tasks in multivariate settings: forecasts of expected returns and risks of assets in portfolios, and correlations between these assets. As different sources/types of time-series influence future returns, risks, and correlations of assets in different ways, it is also important to capture time-series from different modalities. Hence, this article addresses financial time-series forecasting for investment and risk management in a multivariate, multitask, and multimodal setting. Financial time-series forecasting, however, is challenging due to the low signal-to-noise ratios typical in financial time-series, and as intra-series and inter-series relationships of assets evolve across time. To address these challenges, our proposed Temporal Implicit Multimodal Network (TIME) model learns implicit inter-series relationship networks between assets from multimodal financial time-series at multiple time-steps adaptively. TIME then uses dynamic network and temporal encoding modules to jointly capture such evolving relationships, multimodal financial time-series, and temporal representations. Our experiments show that TIME outperforms other state-of-the-art models on multiple forecasting tasks and investment and risk management applications.

The Application of Mathematical Analysis in Investment Planning

Investment serves as a means to cultivate assets and secure long-term profits. However, inadequate investment planning poses a substantial risk of significant losses. Consequently, precise analysis becomes imperative for making intelligent investment decisions. One effective analytical approach involves the application of mathematical concepts in investment planning. This article conducts a comprehensive review of existing literature pertaining to the utilization of mathematical analysis in investment planning. Common mathematical concepts employed in investment analysis encompass probability theory, statistics, portfolio theory, and options theory. Probability theory and statistics aid investors in comprehending and forecasting potential gains and losses from specific investments. The primary objective of investment planning is profit maximization through effective risk management, necessitating a mature and structured analysis. Mathematical analysis emerges as a valuable method, and its application in investment planning yields more accurate and efficient results. Techniques such as statistical analysis, portfolio theory, and probability analysis contribute to risk minimization and return maximization by considering factors like asset correlation and risk levels. Thus, the incorporation of mathematical analysis proves crucial for well-structured and successful investment planning. The fifth entry in the bibliography emphasizes the importance of careful and planned analysis in making investment decisions. Economic and financial factors affecting market and investment performance are explored, along with portfolio risk diversification techniques and investment control. The article underscores the significance of understanding investment objectives and investor profiles while discussing various investment instruments such as stocks, bonds, and mutual funds. Overall, the article provides insights into managing investment portfolios effectively for optimal profitability.

Simulating Credit Loss Distributions: Empirical Versus the Vasicek Model

Because credit losses can be substantial, managing credit risk is a focus area of risk measurement and management. It is important for financial institutions to select credit risk models that accurately forecast losses. The Basel Committee on Banking Supervision (BCBS) chose the closed-form single risk factor Vasicek model for regulatory capital calculations. In this article, its forecast accuracy is compared with empirical loss distributions using simulated probabilities of default and losses given default. The effect of altering probabilities of default on asset correlations was analysed and how this affects credit portfolio loss distributions. The robustness of the Vasicek model against five different portfolios with unique compositions was explored: results highlight two key findings. Firstly, the Vasicek model is a good approximation of credit losses for a portfolio that does not contain dominating loans (it is, after all, based on the assumption of large-scale homogeneity). Secondly, the Vasicek model is a good approximation for expected loss (ELs) but lacks accuracy when determining extreme unexpected losses (ULs). Finally, credit capital requirements as a function of two variables are presented which reveals novel ways of viewing these values.

Enhancing portfolio optimization: A comparative analysis of the mean-variance Markowitz model and risk-parity contribution strategies

Financial markets are still exposed to various crises that increase stock price fluctuations and make predictions extremely difficult (Nguyen et al., 2024). Although there are many diversification methods for building investment portfolios, there has been no agreement on the best of them. This research aims to identify the most effective strategy for constructing an optimal investment portfolio by comparing the mean-variance (MV) model and risk-parity (RP) contribution strategies during the uncertain market period 2018–2022. The study used a quantitative and an optimization method following Ofikwu (2019) based on three critical criteria: 1) low asset correlation, 2) the highest Sharpe ratio, and 3) a mixed strategy for a sample of firms listed in the Amman Stock Exchange (ASE). The results show that the MV model has the highest Sharpe ratio (15.06 percent and 11.84 percent) when applied to the Sharpe and mixed strategies respectively. In comparison, using the low correlation strategy the RP model gains the highest Sharpe ratio (14.92 percent). During COVID-19, all portfolios had a higher positive return and lower total risk than the market portfolio. Both models are valid to be used during uncertain conditions. It highlights the effectiveness of strategies in navigating challenging market conditions and offers practical guidance for investors in uncertain times for asset allocation.

WaveCorr: Deep reinforcement learning with permutation invariant convolutional policy networks for portfolio management

We present a new portfolio policy convolutional neural network architecture, WaveCorr, for deep reinforcement learning applied to portfolio optimization. WaveCorr is the first to treat asset correlation while preserving “asset invariance property”, a new permutation invariance property that significantly increases the stability of performance in problems where input indexing is done arbitrarily. A general theory is also derived for verifying this property in other fields of application. Our experiments show that WaveCorr consistently outperforms other state-of-the-art convolutional architectures.

Measurement and Calibration of Regulatory Credit Risk Asset Correlations

Vasicek’s asymptotic single risk factor (ASRF) model is employed by the Basel Committee on Banking Supervision (BCBS) in its internal ratings-based (IRB) approach for estimating credit losses and regulatory credit risk capital. This methodology requires estimates of asset correlations; these are prescribed by the BCBS. Practitioners are interested to know market-implied asset correlations since these influence economic capital and lending behavior. These may be backed out from ASRF loan loss distributions using ex post loan losses. Prescribed asset correlations have been neither updated nor recalibrated since their introduction in 2008 with the implementation of the Basel II accord. The market milieu has undergone significant alterations and adaptations since then; it is unlikely that these remain relevant. Loan loss data from a developed (US) and developing (South Africa) economy spanning at least two business cycles for each region were used to explore the relevance of the BCBS calibration. Results obtained from three alternative methodologies are compared with prescribed BCBS values, and the latter were found to be countercyclical to empirical loan loss experience, resulting in less punitive credit risk capital requirements than required in market crises and more punitive requirements than required in calm conditions.

Estimation of Yu and Meyer bivariate stochastic volatility model by iterated filtering

In financial applications, understanding the asset correlation structure is crucial to tasks such as asset pricing, portfolio optimisation, risk management, and asset allocation. Thus, modelling the volatilities and correlations of multivariate stock market returns is of great importance. This paper proposes the iterated filtering algorithm for estimating the bivariate stochastic volatility model of Yu and Meyer. The iterated filtering method is a frequentist-based approach that utilises particle filters and can be applied to estimating the parameters of non-linear or non-Gaussian state-space models. The paper presents an empirical example that demonstrates the way in which the proposed estimation method might be used to estimate the correlation between the returns of two assets: Standard and Poor’s 500 index and the price of gold in US dollars. This is accompanied by a simulation study that proves the validity of the approach.

Developing a risk management approach based on reinforcement training in the formation of an investment portfolio

Investments play a significant role in the functioning and development of the economy. Risk management is an integral part of the formation of the investment portfolio. This means that an investor must be willing to take on a certain level of risk in order to receive a certain level of return. However, when forming an investment portfolio, an investor faces such problems as market unpredictability, asset correlation, incorrect asset allocation. Therefore, when forming an investment portfolio, an investor should carefully study all possible risks and try to minimize them. The object of research is an approach to risk management in the formation of an investment portfolio using the method of reinforcement training. The basic principles of formation of the investment portfolio and determination of risks are described. The application of the method of reinforcement training for building a model of risk management of investment portfolio is considered. The process of selecting optimal investment assets based on alternative data sources that minimize risks and maximize profits is also considered. A functional model of the process of risk optimization in the formation of an investment portfolio based on machine learning methods has been developed. The functional model constructed makes it possible to build a process of risk optimization, including asset selection, risk comparison and assessment, to form an investment portfolio and monitor its risks. The study results showed that the proposed approach to the formation of the investment portfolio increased the total growth of the investment portfolio by 0.4363 compared to the base model. Also, the volatility indicator improved compared to the market, as evidenced by the percentage difference between the initial and final cash amount, which increased from 128.98 to 295.57

Daily Semiparametric GARCH Model Estimation Using Intraday High-Frequency Data

The GARCH model is one of the most influential models for characterizing and predicting fluctuations in economic and financial studies. However, most traditional GARCH models commonly use daily frequency data to predict the return, correlation, and risk indicator of financial assets, without taking data with other frequencies into account. Hence, financial market information may not be sufficiently applied to the estimation of GARCH-type models. To partially solve this problem, this paper introduces intraday high-frequency data to improve estimation of the volatility function of a semiparametric GARCH model. To achieve this objective, a semiparametric volatility proxy model was proposed, which includes both symmetric and asymmetric cases. Under mild conditions, the asymptotic normality of estimators was established. Furthermore, we also discuss the impact of different volatility proxies on estimation precision. Both the simulation and empirical results showed that estimation of the volatility function could be improved by the introduction of high-frequency data.

Estimating the Values of Missing Data Related to Infrastructure Condition States Using Their Spatial Correlation

Infrastructure managers consistently monitor the condition of their assets to predict their deterioration speed and determine the optimal time to execute preventive interventions. However, despite the recent progress in more frequent and accurate monitoring of assets and storage of the related results, in practice, real-world data often contains errors and discrepancies such as missing data or faulty entries. This problem can happen owing to collection errors during routine inspections or inconsistency of data storage formats in different years. Because the quality of data plays a significant role in the accuracy of deterioration prediction and the resulting intervention programs, it is important to improve condition state predictions by imputing the values of missing information. This paper examines the efficiency of different models that use the spatial correlation of infrastructure assets in predicting the value of missing data. The models include univariate and multivariate Kriging, a hybrid artificial neural network (ANN)-Kriging model, and the bidirectional long short term memory (bi-LSTM) neural network, which can model the data with spatial correlation or a sequential relationship. The results confirm that the condition indicator values can be estimated with reasonably low levels of error.

Crypto Assets: A New Way of Diversifying Your Investments

International investments have gained momentum since the start of this century. Many investors in the developed economies invest in the growing economies to seek prospects of higher returns. This has become evident in the last two decades, especially after the financial crisis of 2008, when investors were forced to think outside of the box in order to get proper returns for their investments. Investing has become even more challenging when investors are faced with low and even negative yields, especially in the investments on short and medium term. This is where crypto assets come in the picture. Namely, with the appearance of the blockchain technology and all of the new opportunities it brings, crypto assets appeared as a new way for investors to diversify their investments and get higher returns. Though they bring additional choices to investors, they can also be very tricky and should be taken into consideration when investing with high cautiousness, simply because the technology they are based on is relatively new and not very much regulated, thus they bring higher risk than the traditional assets and fiat currencies that are already available. Having that in mind, this paper goes over the pricing, volatility and correlation of crypto assets with other currencies. Additionally, we look at the way they are regulated so far, how accessible is the market for them and their behavior vs the traditional fiat currencies. Lastly, we come to the conclusion that crypto assets, though being more volatile and riskier than fiat currencies, do in fact bring additional return to an investor’s portfolio and should be used carefully according to the individual risk and return preferences. There is still a lot to be examined and researched about crypto assets so that they can be better utilized in the future by investors.

A novel population analysis approach for analyzing financial markets under crisis - a focus on excess returns of the US stocks under 9/11 and COVID-19

ABSTRACT Since the seminal research of Harry Markowitz, the importance of Pareto Optimal portfolios and asset correlation has been a foundation of modern portfolio theory. Recent researchers have expanded on Markowitz-efficient portfolios using advanced statistical methods to identify correlations among assets, while other researchers have demonstrated the decline in asset correlations during periods of market volatility and economic shocks. We extend this research by applying a novel approach based on the concept of population analysis to study the correlation of assets under major economic shocks. We use similarity networks to investigate the impact of the COVID-19 pandemic on various sectors, and then compare it with the behavioural patterns associated with the 9/11 event. The population analysis revealed that during the current pandemic, the behavioural pattern of the finance and energy sectors was significantly different than other sectors. Similar results were found for the finance and the industrial sectors during the 9/11 attacks.

Systemic Risk with Multi-Channel Risk Contagion in the Interbank Market

The systematicness of banks is an important driver of financial crisis. Overlapping portfolios and assets correlation of banks’ investment are important reasons for systemic risk contagion. The existing systemic risk models are all analyzed from one aspect and cannot reflect the real situation of the banking system. In the present paper, considering the overlapping portfolios and assets correlation, a contagion network model with multi-channel risk is proposed, which is with interbank lending (direct contagion channel), overlapping portfolios (indirect contagion channel), and assets correlation (indirect contagion channel). In addition, the model takes investment risk as an impact factor and learns the operation rules of the banking system to help banks compensate for liquidity through asset depreciation. Based on the proposed model, the effects of assets correlation, assets diversity, assets investment strategy, interbank network structure, and the impact of market density on risk contagion are studied and analyzed quantitatively. The method in this paper can more truly reflect the banking system risk than the existing model. This paper provides a solution for quantitative analysis of systemic risk, which provides powerful tools for macroprudential stress testing and a reference for regulatory authorities to prevent systemic risk.

СТОИТ ЛИ ПОЛАГАТЬСЯ НА КОРРЕЛЯЦИЮ ПРИ ФОРМИРОВАНИИ ПОРТФЕЛЯ

The mail solution for compiling and structuring an investment portfolio is the distribution between stocks and bonds, often based on classical indicators and methods from modern portfolio theory (MPT). This article examines the question of whether to rely on asset correlation when forming a portfolio of securities of Russian issuers, when the return on assets has an uneven distribution or when the relationship between variables is not linear

Credit risk measures and the estimation error in the ASRF model under the Basel II IRB approach

In many standard derivation and presentations of risk measures like the Value-at-Risk or the Expected Shortfall, it is assumed that all the model’s parameters are known. In practice, however, the parameters must be estimated and this introduces an additional source of uncertainty that is usually not accounted for. The Prudential Regulators have formally raised the issue of errors stemming from the internal model estimation process in the context of credit risk, calling for margins of conservatism to cover possible underestimation in capital. Notwithstanding this requirement, to date, a solution shared by banks and regulators/supervisors has not yet been found. In our paper, we investigate the effect of the estimation error in the framework of the Asymptotic Single Risk Factor (ASRF) model that represents the baseline for the derivation of the credit risk measures under the Internal-Ratings Based (IRB) approach. We exploit Monte Carlo simulations to quantify the bias induced by the estimation error and we explore an approach to correct for this bias. Our approach involves only the estimation of the long run average probability of default and not the estimation of the asset correlation given that, in practice, banks are not allowed to modify this parameter. We study the stochastic characteristics of the probability of default estimator that can be derived from the Asymptotic Single Risk Factor framework and we show how to introduce a correction to control for the estimation error. Our approach does not require introducing in the Asymptotic Single Risk Factor model additional elements like the prior distributions or other parameters which, having to be estimated, would introduce another source of estimation error. This simple and easily implemented correction ensures that the probability of observing an exception (i.e. a default rate higher than the estimated quantile of the default rate distribution) is equal to the desired confidence level. We show a practical application of our approach relying on real data.