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

03.12.2021

Faktor oder Sektor?

Institutional Money

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

Abstract

Faktor- und Sektor-Optimierungen im Rahmen von Asset Allocation-Strategien zeigen unterschiedliche Erfolge in unterschiedlichen Zeiten und Zeitfenstern: Wer wann die Nase vorne hat.

https://www.institutional-money.com/fileadmin/emagazin/2021_4_IM/124/index.html

17.11.2021

Asset Pricing, Empirical Capital Market Research

Decision Support for Classifying Financial News

17.11.2021

Wolff, Dr. Dominik Hans Christian Schmitz Prof. Dr. Dirk Neumann Dr. Bernhard Lutz

Abstract

In this study, we evaluate several trading strategies based on the textual content of corporate disclosures using machine learning. To obtain a conservative estimate of profitability, we require orders to be placed for the close price of the current trading day and stocks must exhibit high liquidity to ensure proper order execution. Our evaluation based on 354,992 form 8-K filings and 10,204 ad hoc announcements shows that the proposed trading strategies yield up to 7.81% and 9.34% out-of-sample annualized return. More importantly, we find that the prevalent approach in the literature of estimating the stock market reaction of a disclosure based on the closing price of the past trading and omitting liquidity filters substantially overestimates profitability. We also provide useful insights for practitioners by describing feature importance to shed light onto how the machine learning models arrive at decisions.

 

 

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3910451

More information

17.11.2021

Asset Pricing, Empirical Capital Market Research

News Embeddings for Sector Timing – A textual similarity based approach to determining trending sectors in news coverage

17.11.2021

Wolff, Dr. Dominik Hans Christian Schmitz Prof. Dr. Dirk Neumann Dr. Berhard Lutz

Abstract

In this study, we present an approach to quantify the relevance of daily newspaper articles  for individual companies and their corresponding sectors. Based on the textual content of daily newspaper, we utilize sentence and paragraph embeddings to compare news articles from daily newspapers over a time span of 15 years with company descriptions from Form 10-K filings. We measure the relevance of a news article as the similarity between the article and the company’s description. In contrast to prevalent approaches in the literature, our relevance estimation does neither rely on stock price data nor on a predefined mapping between news articles and companies. We evaluate the proposed methodology on several strategies on sector exchange traded funds and on the level of individual stocks. We find that the trading strategies based on our relevance estimation approach yield up to 15.38% out-of-sample annualized return after transaction costs.

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