Industry Portfolios Research Articles

Industry return prediction via interpretable deep learning

We apply an interpretable machine learning model, the LassoNet, to forecast and trade U.S. industry portfolio returns. The model combines a regularization mechanism with a neural network architecture. A cooperative game-theoretic algorithm is also applied to interpret our findings. The latter hierarchizes the covariates based on their contribution to the overall model performance. Our findings reveal that the LassoNet outperforms various linear and nonlinear benchmarks concerning out-of-sample forecasting accuracy and provides economically meaningful and profitable predictions. Valuation ratios are the most crucial covariates, followed by individual and cross-industry lagged returns. The constructed industry ETF portfolios attain positive Sharpe ratios and positive and statistically significant alphas, surviving even transaction costs.

Discover the Impact by COVID-19 Pandemic on Biopharmaceutical Index and Its Related Industry Portfolio

This research is trying to explore the changes in biopharmaceutical and other medically related indices under the impact of the pandemic, and how pharmacy related portfolio impact by the pandemic. The research utilizes EGARCH and VAR models to analyze the volatility of the biopharmaceutical index and the dynamic relationships among various related indices. The research mainly demonstrates the changes in risk of the biopharmaceutical index before and during the pandemic, providing a certain degree of alert to investors who are interested in investing in biopharmaceutical-related stocks but are relatively risk-averse. It also explores the impact of the biopharmaceutical index on other pharmaceutical-related indices, verifying its influence on other indices and whether it has predictive capabilities. Finally, by comparing the portfolios constructed using the biopharmaceutical index and its related industry indices before and during the pandemic, it provides recommendations for investors interested in investing in pharmaceutical stocks during large-scale health events.

Tests for Large-Dimensional Shape Matrices via Tyler’s M Estimators

Tyler’s M estimator, as a robust alternative to the sample covariance matrix, has been widely applied in robust statistics. However, classical theory on Tyler’s M estimator is mainly developed in the low-dimensional regime for elliptical populations. It remains largely unknown when the parameter of dimension p grows proportionally to the sample size n for general populations. By using the eigenvalues of Tyler’s M estimator, this article develops tests for the identity and equality of shape matrices in a large-dimensional framework where the dimension-to-sample size ratio p/n has a limit in (0, 1). The proposed tests can be applied to a broad class of multivariate distributions including the family of elliptical distributions (see model (2.1) for details). To analyze both the null and alternative distributions of the proposed tests, we provide a unified theory on the spectrum of a large-dimensional Tyler’s M estimator when the underlying population is general. Simulation results demonstrate good performance and robustness of our tests. An empirical analysis of the Fama-French 49 industrial portfolios is carried out to demonstrate the shape of the portfolios varying. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

The flow‐performance puzzle: Insights from passive and active ETFs

AbstractThis study examines the relationship between fund flows and subsequent performance, testing the smart money and price pressure hypotheses within the context of passive and active exchange‐traded funds (ETFs). By differentiating between managerial skill and non‐fundamental demand shocks, we uncover a significant positive flow‐performance relationship, challenging traditional attributions solely to investor skill in identifying superior fund management. We further develop a measure of flow shocks to individual stocks by aggregating daily changes in ETF ownership of 5600 stocks. An event study on ETF constituents further disentangles the effects of price pressure from smart money. Through robust analyses, including Fama–French industry portfolios and propensity score matching, our findings suggest a nuanced interaction between investor behaviour and market dynamics, contributing to the discourse on fund flows' impact on performance. This research highlights the complexity of the flow‐performance relationship and its implications for fund management and investment strategies, offering new insights into the mechanisms driving fund performance in the ETF landscape.

Impact of sentimental factors on stock portfolio returns –an empirical analysis

This study aims to introduce an integrated model for understanding the influence of various sentimental factors in conjunction with macroeconomic factors on portfolio returns across ten industry sectors within the US market. These sentimental factors are categorized into market-wide, consumer, and individual stock market factors to assess their impact on industry portfolio returns. Employing the Autoregressive Distributed Lag (ARDL) model, the study evaluates the effects of macroeconomic and sentimental factors on stock market portfolio returns. The findings reveal a negative relationship between short-term interest rates and portfolio returns in specific industry sectors like manufacturing, telecom, and wholesale/retail. The study finds a positive relationship between the Hi-tech sector's risk spread and portfolio returns. Market sentimental factors positively influence portfolio returns of durable, non-durable, utility, and other sectors. Individual sentimental factors negatively impact portfolio returns in hi-tech, utility, durable, energy, and other sectors. The stock market-related individual, sentimental factor of the number of IPOs has a positive impact on portfolio returns in the energy sector and a negative impact on portfolio returns in other sectors. Consumer sentimental factors are significant positive determinants for portfolio returns in durable, energy, telecom, health, and other sectors. Discounts on closed-end funds may provide vital fundamental information regarding lower future earnings for stocks in the durable and energy sectors. The study provides valuable insights for investors to optimize their portfolio strategies in response to macroeconomic and sentimental factors within specific industry sectors.

Empirical Asset Pricing with Score-Driven Conditional Betas

Abstract We develop a novel empirical asset pricing framework to estimate time-varying risk premia, building upon score-driven conditional betas models. First, we extend the theory by establishing the asymptotic distribution of standard test statistics, allowing us to assess the significance of a given factor in the regression. Additionally, we introduce a bootstrap procedure and establish its validity. Second, we propose a two-step estimation procedure to recover time-varying risk premia. We illustrate the performance of our tests and risk premia estimation through simulations. Third, we estimate a time-varying premium associated with a carbon risk factor in the cross-section of U.S. industry portfolios.

Challenges and gaps in immunosafety evaluation of therapeutics: An IQ DruSafe survey

Immunotoxicology/immunosafety science is rapidly evolving, with novel modalities and immuno-oncology among the primary drivers of new tools and technologies. The Immunosafety Working Group of IQ/DruSafe sought to better understand some of the key challenges in immunosafety evaluation, gaps in the science, and current limitations in methods and data interpretation. A survey was developed to provide a baseline understanding of the needs and challenges faced in immunosafety assessments, the tools currently being applied across the industry, and the impact of feedback received from regulatory agencies. This survey also focused on current practices and challenges in conducting the T-cell-dependent antibody response (TDAR) and the cytokine release assay (CRA). Respondents indicated that ICH S8 guidance was insufficient for the current needs of the industry portfolio of immunomodulators and novel modalities and should be updated. Other challenges/gaps identified included translation of nonclinical immunosafety assessments to the clinic, and lack of relevant nonclinical species and models in some cases. Key areas of emerging science that will add future value to immunotoxicity assessments include development of additional in vitro and microphysiological system models, as well as application of humanized mouse models. Efforts are ongoing in individual companies and consortia to address some of these gaps and emerging science.

Understanding co-movements based on heterogeneous information associations

Both systematic and idiosyncratic information dissemination contribute to assets co-movement. To proxy for co-movement based on heterogeneous information diffusion, we construct two-layer network structures in terms of the correlations of systematic and idiosyncratic returns for Fama–French 49 industry portfolios. We further delve into the co-movement structures by studying their dynamics and interactions in terms of topological properties at both the system and individual levels. Our findings reveal the following: (1) Co-movement structures exhibit temporal changes and are closely associated with major risk events. (2) At the system level, there is time-varying mutual Granger causality between co-movement structures, particularly during or after recession periods. (3) At the individual level, we identify statistically significant but economically insignificant interplay between the two co-movement structures. Moreover, the co-movement structure based on systematic information diffusion is mainly influenced by industry-level characteristics, including idiosyncratic momentum, idiosyncratic volatility, and market beta. These results deepen our understanding of asset co-movement structures and bear significance for asset allocation and risk management practices.

Measuring national economic resilience through industrial portfolios

Even though the importance of economic resilience has increased as economic shocks have become more frequent in the world, there is still a knowledge gap on how to measure it. In search for effective ways to measure national resilience, this article identifies and mathematically proves the existence of direct correlation between resilience and competitiveness through time-specific global correlation rate. This research proposes an economic performance evaluation method that measures the competitiveness of countries facing economic shocks and recovering from them. A quantified method for identification of global economic shocks through industrial portfolio is proposed as well. The holistic approach internalises most externalities and a nation’s resilience is pared down to its ability to compete in the international trade, linking the main determinants of resilience to the basics of human behaviour. The proposed methodology can be used effectively for national and global economic performance estimations. It also opens a range of new possibilities for economic resilience studies.

External linkages and regional diversification in China: The role of foreign multinational enterprises

This article investigates the role of local external linkages in supporting regional industry entry in new activities, by specifically considering the role of foreign multinational enterprises (MNEs). Theoretically, we construct an original conceptual framework encompassing different potential trajectories of regional diversification based on the presence of MNEs. Empirically, we focus on the case of 279 Chinese prefectures over 1998–2007 and our results suggest that the presence of MNEs is associated with industry entry in unrelated and complex industries, supporting the idea that regional external linkages can activate processes of diversification that modify the technological and industrial portfolio of local economies.

Drug development for major chronic health conditions—aligning with growing public health needs: Proceedings from a multistakeholder think tank

The global pharmaceutical industry portfolio is skewed towards cancer and rare diseases due to more predictable development pathways and financial incentives. In contrast, drug development for major chronic health conditions that are responsible for a large part of mortality and disability worldwide is stalled. To examine the processes of novel drug development for common chronic health conditions, a multistakeholder Think Tank meeting, including thought leaders from academia, clinical practice, non-profit healthcare organizations, the pharmaceutical industry, the Food and Drug Administration (FDA), payors as well as investors, was convened in July 2022. Herein, we summarize the proceedings of this meeting, including an overview of the current state of drug development for chronic health conditions and key barriers that were identified. Six major action items were formulated to accelerate drug development for chronic diseases, with a focus on improving the efficiency of clinical trials and rapid implementation of evidence into clinical practice.

Variational Inference for Large Bayesian Vector Autoregressions

We propose a novel variational Bayes approach to estimate high-dimensional Vector Autoregressive (VAR) models with hierarchical shrinkage priors. Our approach does not rely on a conventional structural representation of the parameter space for posterior inference. Instead, we elicit hierarchical shrinkage priors directly on the matrix of regression coefficients so that (a) the prior structure maps into posterior inference on the reduced-form transition matrix and (b) posterior estimates are more robust to variables permutation. An extensive simulation study provides evidence that our approach compares favorably against existing linear and nonlinear Markov chain Monte Carlo and variational Bayes methods. We investigate the statistical and economic value of the forecasts from our variational inference approach for a mean-variance investor allocating her wealth to different industry portfolios. The results show that more accurate estimates translate into substantial out-of-sample gains across hierarchical shrinkage priors and model dimensions.

Measuring Economic Resilience through Industrial Portfolio: The Cases of New EU Member States Since 2004

The relevance of economic resilience topic is increasingly growing, still mixed results prevail in academic research. Resilience research typically concentrates on the Western European region. The research gap appears in focus towards the East since the concept of economic resilience is context dependent. By adapting the calculation mechanism of Martin and Gardiner (2019) to national level, we empirically analysed the economic resilience of 10 Southern and Eastern European countries between 2004 and 2020. We found common competition-related structural changes suggesting where to look for possible consistencies when analysing resilience: countries rarely change industrial portfolios when resist to shocks, unless specific or longer lasting production chain disruptions occur; individual properties dominate when countries recover from shocks, although common industrial portfolio shifts evident in manufacturing, and real estate industries. Results provide an original methodology and initial basis for the development of nation-specific policies to increase economic resilience and structural reforms effectiveness.

WHAT DRIVES INNOVATION AND CHANGE IN ACL SURGERY? AN ANALYSIS OF 14,352 PATIENTS

IntroductionAnterior cruciate ligament reconstruction (ACLr) is the most widely published operation in the orthopaedic literature. Over recent years there has been increased interest in the surgical technique and role of concomitant procedures performed during ACLr. The National Ligament Registry (NLR) collects robust data on ACLr performed in the UK. In this registry analysis we explore trends in ACLr surgery and how they relate to published literature and the growing industry portfolio available to surgeons.MethodsUsing data from the NLR, 14,352 ACLr performed between 2013–2021 were analysed. High impact papers on ACLr were then cross referenced against this data to see if surgical practice was influenced by literature or whether surgical practice dictated publication. Common trends were also compared to key surgical industry portfolios (Arthrex, Smith and Nephew) to see how new technology influenced surgical practice.ResultsThe number of ACLr performed in isolation is decreasing. The number of ACL reconstructions involving meniscal surgery shows an increasing trend since 2013, with 57% of ACLr in 2021 now involving meniscus surgery. The number of ACLr with lateral extra-articular tenodesis (LET) has increased sharply since 2018, preceding the stability trial publication in 2020. Graft preference and size has remained static despite the introduction of new graft harvest and fixation devices. Additional procedures such as other ligament reconstruction and additional cartilage surgery have also remained static over time.ConclusionIn this analysis we looked at surgical trends in ACLr and their relation to literature and industry. Meniscal intervention is increasing, in keeping with the growing level of literature in this area. In the setting of LET, a high impact level 1 study appears to have significantly changed the practice of UK surgeons with a sharp increase in the number of LET procedures being performed. Industry appears to have little influence on the change in surgical trends, suggesting high quality evidence is what drives innovation in ACLr while industry supports rather than influences innovation. It will be interesting to see the impact of the stability 2 study, recent work on the medial structures of the knee and the commissioning of cartilage centres on future trends.

The Effects of Common Macroeconomics Factors on U.S. Stock Returns

In this study, the explanatory power of the macro variables in relation to the variation of stock returns has been discussed in terms of the economy of the USA. To make an analysis on the cross section of the stock returns, 131 Macroeconomic variables between 1964 and 2007 have been put into use. Summing up the information in 131 monthly series, dynamic factor analysis is used to take out 8 potential factors. So that the pragmatic presentation of the factor model can be measured, Fama-Macbeth’s test procedure of two phases is applied. In addition to the variables included in the literature such as market risk factor, size factor, value factor and momentum factors, it is found out that the macro factors are highly influential on the explanation of the common variation in U.S stock returns. The tests stated above have been performed by the means of Fama French 49 industry portfolios, apart from Fama French 100 portfolios that have been formed on size and book. Furthermore, the factor model is established and intended for the certain periods of boom and recession. The relations established between latent factors and stock returns appear to be unimportant during the downturn periods.

Heterogeneous tail generalized common factor modeling

A multivariate normal mean–variance heterogeneous tails mixture distribution is proposed for the joint distribution of financial factors and asset returns (referred to as Factor-HGH). The proposed latent variable model incorporates a Cholesky decomposition of the dispersion matrix to ensure a rich dependency structure for capturing the stylized facts of the data. It generalizes several existing model structures, with or without financial factors. It is further applicable in large dimensions due to a fast ECME estimation algorithm. The advantages of modelling financial factors and asset returns jointly under non-Gaussian errors are illustrated in an empirical comparison study between the proposed Factor-HGH model and classical financial factor models. While the results for the Fama–French 49 industry portfolios are in line with Gaussian-based models, in the case of highly tail heterogeneous cryptocurrencies, the portfolio based on the Factor-HGH model almost doubles the average return while keeping the volatility, the maximum drawdown, the turnover, and the expected shortfall at a low level.

Dependence and risk management of portfolios of metals and agricultural commodity futures

This paper examines the dependence structure and the portfolio allocation characteristics of a main industrial portfolio metals (gold, platinum, palladium, aluminum, silver, copper, zinc, lead, and nickel), and of an agricultural commodities portfolio (wheat, corn, soybeans, coffee, sugar cane, sugar beets, cocoa, cotton, and lumber). Our methodology is based on regular vine copulas and the conditional Value-at-Risk. The motivation to investigate the dependence structure and connectedness between agricultural, and metal commodities is to identify ways in which agricultural and metal commodities can hedge each other and to explore the possibilities of parallel investments. The results indicate that the dependence dynamics of the main metals portfolio are characterized by symmetric features. However, the dependence dynamics of the agricultural commodities portfolio are characterized by symmetric and asymmetric features; symmetric dynamics are predominant. Finally, the metal commodities portfolio is observed to be less risky for financial resource allocation during the global financial crisis.

Midterm elections and stock returns

The midterm election effect is one of the most persistent regularities related to US politics reported in empirical finance, but it has also been one of the least examined. We explore practical implications for investors, analysing monthly excess and risk-adjusted returns on 49 industry portfolios for the period 1926–2022. Contrary to much commentary in the professional media and prior literature, higher returns around midterm elections all but disappear after returns are adjusted for risk. We also find that midterm elections are predominantly associated with the market factor, and thus, higher returns appear to merely compensate investors for bearing risk.

Market segmentation and international diversification across country and industry portfolios

We conjecture that partially segmented stock indexes that are characterized by low correlation with the world market are mainly priced by local factors and should produce abnormal returns relative to a global asset-pricing model. This implies a negative relation between correlation and future index returns in the presence of segmented indexes. Empirical evidence confirms such a relationship for the sample of industry indexes, suggesting a heterogeneous segmentation. However, we do not observe a similar pattern for country indexes. In addition, the international diversification potential of industries does not vanish during volatile periods. The hypothesis that the negative relationship should be stronger for the more segmented subsamples that are characterized by small market size and emerging country origin is verified for the industry sample. Thus, cross-industry diversification is superior to mere cross-country diversification.

Is ESG a Novel Pricing Risk Factor for the Chinese Stock Markets during COVID-19?

This paper examines the potential of ESG as a novel risk factor, explaining different industry portfolio returns from 2018 to 2021 (including two years of the unique COVID-19 window). The ESG factor(SMU) is designed as the spread between the top 30% high-ESG(Sustainable) group and the bottom 30% low-ESG(Unsustainable) group. Based on empirical evidence from the Chinese stock markets, this paper finds: 1) The ESG factor significantly explains industry returns along with Fama-French three factors; 2) Sustainable portfolios consistently outperform unsustainable groups, particularly during the pandemic period; 3) Modified models with ESG factors slightly outperform the classic FF-3 model according to the GRS F-test; and 4) Industry portfolio returns during COVID-19 are surprisingly higher than in normal times, most likely due to the central bank and governments Quantitative Easing(QE) policies.