Research

The main purpose of IQAM Research is to perform quantitative research in the area of capital markets and prepare academic papers in cooperation with universities and partners. Modern methods are used to empirically investigate and explain capital market phenomena and answer fundamental investment-related questions.

Reset filter

06.09.2021

Dividend Predictability and Higher Moment Risk Premia

Journal of Asset Management

Al-Jaaf, Aşty

Abstract

I use model-free methods to estimate the term structures of the variance risk premium (VRP) and the skewness risk premium (SRP) derived from dividend futures and options. I find that VRP is on average negative, whereas SRP is on average positive. They have unique characteristics and can hardly be explained by equity risk factors and equity moment risk premia. I present evidence that both dividend moment risk premia contain significant forecasting power for dividend futures returns in- and out-of-sample. Dividend futures returns are predicted by the VRP (SRP) in almost all setups with a negative (positive) sign.

24.08.2021

Empirical Capital Market Research, Risk & Optimization

Factor-Investing and Asset Allocation Strategies

Abstract

Factor investing has experienced enormous growth in recent years.
In the following article, Prof. Dr. Wolfgang Bessler,
Dr. Georgi Taushanov and Dr. Dominik Wolff investigate whether factor based
allocation strategies offer investors better portfolio performance than traditional sector allocations.
than traditional sector allocations. In the process
the performance and the performance differences of sector and
factor portfolios for different allocation strategies and portfolio optimization
optimization approaches are analyzed.

 

28.05.2021

Factor-Investing and Asset Allocation Strategies: A Comparison of Factor Versus Sector Optimization

Journal of Asset Management

Wolff, Dr. Dominik Prof. Dr. Wolfgang Bessler Dr. Georgi Taushanov

Abstract

Given the tremendous growth of factor allocation strategies in active and passive fund management, we investigate whether either asset allocation strategies based on factors or sectors provide investors with a superior portfolio performance. Our focus is on comparing factor versus sector allocation as some recent empirical evidence indicates the dominance of sector over country portfolios. We analyze the performance and performance differences of sector and factor portfolios for various weighting and portfolio optimization approaches including ‘equal-weighting’ (1/N), ‘risk-parity’ (RP), minimum-variance (MinVar), mean-variance (MV), Bayes-Stein (BS) and Black-Litterman (BL) by employing a sample-based approach in which the sample moments are the input parameters for the allocation model. For the period from May 2007 to November 2020, our results clearly reveal that, over longer investment horizons, factor portfolios provide relative superior performances. For shorter periods, however, we observe time varying and alternating performance dominances as the relative advantage of one over the other strategy depends on the economic cycle. We find that during “normal” times factor portfolios clearly dominate sector portfolios, whereas during crisis periods sector portfolios are superior offering better diversification opportunities.

More information

27.05.2021

Asset Pricing, Empirical Capital Market Research

Stock Picking with Machine Learning

Wolff, Dr. Dominik Echterling, Dr. Fabian

Abstract

We combine insights from machine learning and finance research to build machine learning algorithms for stock selection. Our study builds on weekly data for the historical constituents of the S&P 500 over the period from 1999 to 2019 and includes typical equity factors as well as additional fundamental data, technical indicators, and historical returns. Deep Neural Networks (DNN), Long Short-Term Neural Networks (LSTM), Random Forest, Boosting, and Regularized Logistic Regression models are trained on stock characteristics to predict whether a specific stock outperforms the market over the subsequent week. We analyze a trading strategy that picks stocks with the highest probability predictions to outperform the market. Our empirical results show a substantial and significant outperformance of machine learning based stock selection models compared to a simple equally weighted benchmark. Moreover, we find non-linear machine learning models such as neural networks and tree-based models to outperform more simple regularized logistic regression approaches. The results are robust when applied to the STOXX Europe 600 as alternative asset universe. However, all analyzed machine learning strategies demonstrate a substantial portfolio turnover and transaction costs have to be marginal to capitalize on the strategies.

Link to the paper

More information

30.04.2021

Empirical Capital Market Research, Risk & Optimization

Optimal Asset Allocation Strategies for International Equity Portfolios: A Comparison of Country versus Sector Optimization

Working Paper

Wolff, Dr. Dominik Taushanov, Georgi Bessler, Wolfgang

Abstract

Although most academic studies conclude that mutual funds cannot outperform a passive investment strategy in the long run, there is some recent empirical evidence that a persistent outperformance can be achieved in an out-of-sample framework when using sophisticated optimization techniques. These empirical findings are for equity-bond-commodity-portfolios, international equity-bond portfolios and US-industry portfolios. The latter can even be further improved when return predictions are included. Given these empirical findings, we analyze in this study whether an industry-based or a country-based optimization model performs best. We employ a variety of optimization- and weighting-techniques to compare the country- and the sector-based allocation strategies. These include naive ‘equally weighted’ (1/N) portfolio, the two risk-based asset allocation rules ‘risk-parity’ (RP) and minimum-variance (MinVar) as well as three portfolio optimization approaches mean-variance (MV), Bayes-Stein (BS) and the Black-Litterman (BL) model. We also include simple return prediction models. To determine whether one approach is persistently superior to the other approach, we analyze time varying effects based on the state of the economy, i.e. expansionary or recessionary periods. Moreover, we investigate investment style or investor clientele ef-fects, the full period and different sub-periods, equity-only and equity-bond portfolios as well as aggressive and conservative investments styles. Summarizing of all analyzed cases, we find strong evidence for the fact that in the long run the sector-oriented asset allocation provided a higher performance than the country-allocation. In almost all the observed cases, the sector-based allocation achieved higher Sharpe ratios than the country-based allocation.

More information

31.12.2020

Asset Pricing, Empirical Capital Market Research

Machine Learning Approaches for Equity Market Predictions

Journal of Asset Management, forthcoming

Wolff, Dr. Dominik Neugebauer, Dr. Ulrich

Abstract

We empirically analyze equity premium predictions with ‘traditional’ linear models and machine learning approaches. Based on a commonly used dataset of equity market predictors extended by additional fundamental, macroeconomic, sentiment and risk indicators, we find mixed results for machine learning algorithms for equity market predictions. In contrast to sophisticated linear models such as penalized least squares or principal component regressions (PCR), the analyzed machine learning algorithms fail to significantly outperform the historical average benchmark forecast. However, an investment strategy that uses machine learning predictions in a market timing strategy, outperforms a passive buy-and-hold investment. Compared to sophisticated linear prediction models, in our problem set, machine learning algorithms do not improve forecast accuracy.

More information

28.02.2020

Asset Pricing, Empirical Capital Market Research

Factor-based Investing in Government Bond Markets: The Current State of Research

Journal of Asset Management volume 21, pages 94–105 (2020)

Hachenberg, Britta Schiereck, Dirk

Abstract

Factor investing has become very popular during the last decades, especially with respect to equity markets. After extending Fama–French factors to corporate bond markets, recent research more often concentrates on the government bond space and reveals that there is indeed clear empirical evidence for the existence of significant government bond factors. Voices that state the opposite refer to outdated data samples. By the documentation of rather homogeneous recent empirical evidence, this review underlines the attractiveness of more sophisticated investment approaches, which are well established in equity and even in corporate bond markets, to the segment of government bonds.

More information

07.12.2019

Asset Pricing, Empirical Capital Market Research

Extending Fama-French Factors to Corporate Bond Markets

Journal of Portfolio Management, forthcoming

Wegener, Dr. Michael Spielmann, Timo Prof. Dr. Dirk Schiereck

Abstract

The explanatory power of size, value, profitability and investment has been extensively studied for equity markets. Yet, the relevance of these factors in global credit markets is less explored although equities and bonds should be related according to structural credit risk models. We investigate the impact of the four Fama-French factors in the U.S. and European credit space. While all factors exhibit economically and statistically significant excess returns in the U.S. high yield market, we find mixed evidence for U.S. and European investment grade markets. Nevertheless, we show that investable multi-factor portfolios outperform the corresponding corporate bond benchmarks on a risk-adjusted basis. Finally, our results highlight the impact of company level characteristics on the joint return dynamics of equities and corporate bonds.

More information

10.05.2019

Asset Pricing, Empirical Capital Market Research, Risk & Optimization

Systematic or Idiosyncratic? Spillover Effects in Corporate Bond Markets and Portfolio Implications

Evangelos Salachas

Abstract

Periods with high financial distress and uncertainty are characterized by increased co-movement in corporate bond markets. In this paper, we study the dynamic interactions among corporate bond returns in a period from 2004 to 2016 that covers important macroeconomic, financial and political events. In particular, we provide a framework for the evaluation of contagion among corporate bonds in different regions during a period with increased financial turmoil. We measure contagion in terms of dynamic spillovers, which capture the degree of homogeneity in bond returns. Our specification distinguishes two sources of bond risk: the systematic risk and the idiosyncratic risk. To account for a market-level analysis of co-movement we employ a panel VAR model in which the variables (bond markets) are treated as endogenous. Based on our results, the systematic risk component accounts for a larger portion of variation in bond returns relative to the idiosyncratic component, indicating the existence of homogeneity in global corporate bond markets. The emerging markets are also net receivers of international shocks, whereas innovations in U.S. bond markets contribute importantly to the instability in global bond markets.

More information

16.01.2019

Empirical Capital Market Research, Risk & Optimization

R Tutorial on Machine Learning

WILMOTT magazine

Huber, Dr. Claus

Abstract

Nonlinearity in financial market returns is commonplace, and in particular in hedge fund returns. Hedge funds are known to generate option-like returns based on the products they trade, as well as their trading strategies. This tutorial describes how Kohonen’s self-organizing map (SOM), a method of machine learning, can help to analyze nonlinearity in returns. We focus on simple examples that help the reader to understand where nonlinear hedge fund returns come from, why linear correlation analysis is inappropriate, and how SOMs can help to visualize nonlinear returns to enhance risk analysis. R code and step-by-step instructions enable the reader to reproduce the creation of the SOM. Readers are encouraged to change parameters and study the impacts on results.

More information