# Research articles for the 2021-06-24

Bayesian Estimation and Optimization for Learning Sequential Regularized Portfolios
Marisu, Godeliva Petrina,Pun, Chi Seng
SSRN
This paper incorporates Bayesian estimation and optimization into portfolio selection framework, particularly for high-dimensional portfolio in which the number of assets is larger than the number of observations. We leverage a constrained ð"1 minimization approach, called linear programming optimal (LPO) portfolio, to directly estimate effective parameters appearing in the optimal portfolio. We propose two refinements for the LPO strategy. First, we explore improved Bayesian estimates, instead of sample estimates, of the covariance matrix of asset returns. Second, we introduce Bayesian optimization (BO) to replace traditional grid-search cross-validation (CV) in tuning hyperparameters of the LPO strategy. We further propose modifications in the BO algorithm by (1) taking into account time-dependent nature of financial problems and (2) extending commonly used expected improvement (EI) acquisition function to include a tunable trade-off with the improvement's variance (EIVar). Allowing a general case of noisy observations, we theoretically derive the sub-linear convergence rate of BO under the newly proposed EIVar and thus our algorithm has no regret. Our empirical studies confirm that the adjusted BO result in portfolios with higher out-of-sample Sharpe ratio, certainty equivalent, and lower turnover compared to those tuned with CV. This superior performance is achieved with significant reduction in time elapsed, thus also addressing time-consuming issues of CV. Furthermore, LPO with Bayesian estimates outperform original proposal of LPO, as well as the benchmark equally weighted and plug-in strategies.

Consistent Recalibration Models and Deep Calibration
Matteo Gambara,Josef Teichmann
arXiv

Consistent Recalibration models (CRC) have been introduced to capture in necessary generality the dynamic features of term structures of derivatives' prices. Several approaches have been suggested to tackle this problem, but all of them, including CRC models, suffered from numerical intractabilities mainly due to the presence of complicated drift terms or consistency conditions. We overcome this problem by machine learning techniques, which allow to store the crucial drift term's information in neural network type functions. This yields first time dynamic term structure models which can be efficiently simulated.

Evaluating the Role of Insurance in Managing Risk of Future Pandemics
Kunreuther, Howard,Schupp, Jason
SSRN
This paper provides stakeholders with a practical framework, informed by the recent experience with COVID-19, for defining a meaningful role for insurance in managing business interruption (BI) and other risks from future pandemics. The insurance industry will be part of that solution set, whether through the continued development of ad hoc state-by-state initiatives, a private-public partnership in which the insurance industry commits its servicing capabilities, or a private-public partnership drawing on both its servicing and risk-bearing capabilities. Policymakers, regulators, businesses, and other stakeholders interacting with representatives from the insurance industry can assist in defining its role in providing protection against the financial consequences of future pandemics. This framework, while designed for dealing with future pandemics, may be applied to other catastrophic and systemic risks.

Financial Inclusion-Exclusion Paradox: How Banked Adults Become Unbanked Again
Ozili, Peterson K
SSRN
This paper analyses how financially included adults might become unbanked again. Agents of financial inclusion incorporate economic and social constraints in the delivery of formal financial services. These constraints limit the ability of poor banked adults to use basic financial services to the fullest. The constraints affect agents of financial inclusion positively, and affect customers negatively up to a point where the marginal benefit of being financially included is negative for poor customers. When the marginal benefit of using formal financial services becomes negative, the affected banked adults may discontinue using their formal accounts or exit the formal financial sector when they can no longer bear the negative effect of social and economic constraints that hinder their ability to enjoy basic financial services to the fullest.

Fund2Vec: Mutual Funds Similarity using Graph Learning
Vipul Satone,Dhruv Desai,Dhagash Mehta
arXiv

Identifying similar mutual funds with respect to the underlying portfolios has found many applications in financial services ranging from fund recommender systems, competitors analysis, portfolio analytics, marketing and sales, etc. The traditional methods are either qualitative, and hence prone to biases and often not reproducible, or, are known not to capture all the nuances (non-linearities) among the portfolios from the raw data. We propose a radically new approach to identify similar funds based on the weighted bipartite network representation of funds and their underlying assets data using a sophisticated machine learning method called Node2Vec which learns an embedded low-dimensional representation of the network. We call the embedding \emph{Fund2Vec}. Ours is the first ever study of the weighted bipartite network representation of the funds-assets network in its original form that identifies structural similarity among portfolios as opposed to merely portfolio overlaps.

High-dimensional statistical arbitrage with factor models and stochastic control
Jorge Guijarro-Ordonez
arXiv

The present paper provides a study of high-dimensional statistical arbitrage that combines factor models with the tools from stochastic control, obtaining closed-form optimal strategies which are both interpretable and computationally implementable in a high-dimensional setting. Our setup is based on a general statistically-constructed factor model with mean-reverting residuals, in which we show how to construct analytically market-neutral portfolios and we analyze the problem of investing optimally in continuous time and finite horizon under exponential and mean-variance utilities. We also extend our model to incorporate constraints on the investor's portfolio like dollar-neutrality and market frictions in the form of temporary quadratic transaction costs, provide extensive Monte Carlo simulations of the previous strategies with 100 assets, and describe further possible extensions of our work.

How Does Private Firm Disclosure Affect Demand for Public Firm Equity? Evidence from the Global Equity Market
Kim, Jinhwan,Olbert, Marcel
SSRN
We investigate the relationship between private firmsâ€™ disclosures and the demand for the equity of their publicly traded peers. Using data on the global movement of public equity, we find that a one standard deviation increase in private firm disclosure transparency â€" proxied by the number of disclosed private firmsâ€™ financial statement line items â€" reduces global investorsâ€™ demand for public equity by 13% to 16% or by $206 million to$253 million in dollar terms. These findings are consistent with private firm disclosures generating negative pecuniary externalities â€" global investors reallocate their capital away from public firms to more transparent private firms â€" and less consistent with these disclosures creating positive information externalities that would benefit public firms. Consistent with this interpretation, we find that the reduction in demand for public equity is offset by a comparable increase in capital allocation to more transparent private firms. Using staggered openings of the Bureau van Dijk database offices in each investee country as a plausibly exogenous shock to private firm disclosures, we conclude that the negative relationship between private firm disclosures and public equity demand is likely causal.

Interest Rate Skewness and Biased Beliefs
Chernov, Mikhail,Bauer, Michael
SSRN
Conditional yield skewness is an important summary statistic of the state of the economy. It exhibits pronounced variation over the business cycle and with the stance of monetary policy, and a tight relationship with the slope of the yield curve. Most importantly, variation in yield skewness has substantial forecasting power for future bond excess returns, high-frequency interest rate changes around FOMC announcements, and consensus survey forecast errors for the ten-year Treasury yield. The COVID pandemic did not disrupt these relations: historically high skewness correctly anticipated the run-up in long-term Treasury yields starting in late 2020. The connection between skewness, survey forecast errors, excess returns, and departures of yields from normality is consistent with a theoretical framework where one of the agents has biased beliefs.

Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport
Hengxu Lin,Dong Zhou,Weiqing Liu,Jiang Bian
arXiv

Successful quantitative investment usually relies on precise predictions of the future movement of the stock price. Recently, machine learning based solutions have shown their capacity to give more accurate stock prediction and become indispensable components in modern quantitative investment systems. However, the i.i.d. assumption behind existing methods is inconsistent with the existence of diverse trading patterns in the stock market, which inevitably limits their ability to achieve better stock prediction performance. In this paper, we propose a novel architecture, Temporal Routing Adaptor (TRA), to empower existing stock prediction models with the ability to model multiple stock trading patterns. Essentially, TRA is a lightweight module that consists of a set of independent predictors for learning multiple patterns as well as a router to dispatch samples to different predictors. Nevertheless, the lack of explicit pattern identifiers makes it quite challenging to train an effective TRA-based model. To tackle this challenge, we further design a learning algorithm based on Optimal Transport (OT) to obtain the optimal sample to predictor assignment and effectively optimize the router with such assignment through an auxiliary loss term. Experiments on the real-world stock ranking task show that compared to the state-of-the-art baselines, e.g., Attention LSTM and Transformer, the proposed method can improve information coefficient (IC) from 0.053 to 0.059 and 0.051 to 0.056 respectively. Our dataset and code used in this work are publicly available: https://github.com/microsoft/qlib.

Monetary-Fiscal Policies and Stock Market Performance: Evidence from Linear Ardl Framework
Submitter, GATR Journals,Emamian, Aref,Mazlan, Nur Syazwani
SSRN
Objective - To explore the impacts of monetary and fiscal policies, the appropriateness of both policies and how the stock market is affected by their adoption and implementation in the United States (US). Hence, this study aims to determine the short and long run relationships between monetary and fiscal policies and stock market performance as well as establish potential factors and policies contributing to the highs and lows.Methodology/Technique - We use autoregressive distribution lag (ARDL) developed by Pesaran et al. (2001) to achieve the objective. In this study, annual time series data from the Federal Reserve, World Bank, and International Monetary Fund, from 1986 to 2017 pertaining to the American economy, was used.Findings - The results show that both policies play a significant role in the stock market. We find a significant positive effect of real gross domestic product (RGDP) and the interest rate on the US stock market in the long run and significant negative relationship effect of the consumer price index (CPI) and broad money on the US stock market both in the short run and long run. On the other hand, this study only could support the significant positive impact of tax revenue and significant negative impact of real effective exchange rate on the US stock market in the short run while in the long run are insignificant.Novelty - As the US stock market heavily depends on the Tax Revenue in the short run, any changes in TR can impact on the US stock market considerably. Thus, shareholders can benefit from these results when they look at macroeconomic data in order to enhance their investment strategy.Type of Paper - Empirical.

Next-Day Bitcoin Price Forecast Based on Artificial intelligence Methods
Liping Yang
arXiv

In recent years, Bitcoin price prediction has attracted the interest of researchers and investors. However, the accuracy of previous studies is not well enough. Machine learning and deep learning methods have been proved to have strong prediction ability in this area. This paper proposed a method combined with Ensemble Empirical Mode Decomposition (EEMD) and a deep learning method called long short-term memory (LSTM) to research the problem of next-day Bitcoin price forecast.

Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
Ben Hambly,Renyuan Xu,Huining Yang
arXiv

We explore reinforcement learning methods for finding the optimal policy in the linear quadratic regulator (LQR) problem. In particular, we consider the convergence of policy gradient methods in the setting of known and unknown parameters. We are able to produce a global linear convergence guarantee for this approach in the setting of finite time horizon and stochastic state dynamics under weak assumptions. The convergence of a projected policy gradient method is also established in order to handle problems with constraints. We illustrate the performance of the algorithm with two examples. The first example is the optimal liquidation of a holding in an asset. We show results for the case where we assume a model for the underlying dynamics and where we apply the method to the data directly. The empirical evidence suggests that the policy gradient method can learn the global optimal solution for a larger class of stochastic systems containing the LQR framework and that it is more robust with respect to model mis-specification when compared to a model-based approach. The second example is an LQR system in a higher dimensional setting with synthetic data.

Price Discovery and Market Microstructure Noise
Fruet Dias, Gustavo,Fernandes, Marcelo,Scherrer, Cristina Mabel
SSRN
We show that the standard econometric framework typically yields inconsistent estimates of price discovery measures in the presence of richer market microstructure noise dynamics. We address this errors-in-variable issue using instrumental variables. We devise valid instruments for two alternative microstructure noise settings, and then establish the asymptotic behavior of the corresponding price discovery measures. Our empirical analysis reveals that market leadership conclusions depend heavily on whether we account or not for the market microstructure noise.

Risk Perceptions, Board Networks, and Directorsâ€™ Monitoring
Ding, Wenzhi,Lin, Chen,Schmid, Thomas,Weisbach, Michael S.
SSRN
What makes independent directors perform their monitoring duty? One possible reason is that they are worried about being sanctioned by regulators if they do not monitor sufficiently well. Using unique features of the Chinese financial market, we estimate the extent to which independent directorsâ€™ perceptions of the likelihood of receiving a regulatory penalty affect their monitoring. Our results suggest that they are more likely to vote against management after observing how another director in their board network received a regulatory penalty related to negligence. This effect is long-lasting and stronger if the observing and penalized directors share the same professional background or gender and if the observing director is at a firm that is more likely to be penalized. These results provide direct evidence suggesting that the possibility of receiving penalties is an important factor motivating directors.

Robust Decisions for Heterogeneous Agents via Certainty Equivalents
Anne G. Balter,Nikolaus Schweizer
arXiv

We study the problem of a planner who resolves risk-return trade-offs - like financial investment decisions - on behalf of a collective of agents with heterogeneous risk preferences. The planner's objective is a two-stage utility functional where an outer utility function is applied to the distribution of the agents' certainty equivalents from a given decision. Assuming lognormal risks and heterogeneous power utility preferences for the agents, we characterize optimal behavior in a setting where the planner can let each agent choose between different options from a fixed menu of possible decisions, leading to a grouping of the agents by risk preferences. These optimal decision menus are derived first for the case where the planner knows the distribution of preferences exactly and then for a case where he faces uncertainty about this distribution, only having access to upper and lower bounds on agents' relative risk aversion. Finally, we provide tight bounds on the welfare loss from offering a finite menu of choices rather than fully personalized decisions.

Stock Market Analysis with Text Data: A Review
arXiv

Stock market movements are influenced by public and private information shared through news articles, company reports, and social media discussions. Analyzing these vast sources of data can give market participants an edge to make profit. However, the majority of the studies in the literature are based on traditional approaches that come short in analyzing unstructured, vast textual data. In this study, we provide a review on the immense amount of existing literature of text-based stock market analysis. We present input data types and cover main textual data sources and variations. Feature representation techniques are then presented. Then, we cover the analysis techniques and create a taxonomy of the main stock market forecast models. Importantly, we discuss representative work in each category of the taxonomy, analyzing their respective contributions. Finally, this paper shows the findings on unaddressed open problems and gives suggestions for future work. The aim of this study is to survey the main stock market analysis models, text representation techniques for financial market prediction, shortcomings of existing techniques, and propose promising directions for future research.

The Market for CEOS
Cziraki, Peter,Jenter, Dirk
SSRN
We study the market for CEOs of large publicly-traded US firms, analyze new CEOsâ€™ prior connections to the hiring firm, and explore how hiring choices are determined. Firms are hiring from a surprisingly small pool of candidates. More than 80% of new CEOs are insiders, defined as current or former employees or board members. Boards are already familiar with more than 90% of new CEOs, as they are either insiders or executives who directors have previously worked with. There are few reallocations of CEOs across firms â€" firms raid CEOs of other firms in only 3% of cases. Pay differences appear too small to explain these hiring choices. The evidence suggests that firm-specific human capital, asymmetric information, and other frictions have first-order effects on the assignment of CEOs to firms.

The Pricing of Vanilla Options with Cash Dividends as a Classic Vanilla Basket Option Problem
Jherek Healy
arXiv

In the standard Black-Scholes-Merton framework, dividends are represented as a continuous dividend yield and the pricing of Vanilla options on a stock is achieved through the well-known Black-Scholes formula. In reality however, stocks pay a discrete fixed cash dividend at each dividend ex-date. This leads to the so-called piecewise lognormal model, where the asset jumps from a fixed known amount at each dividend date. There is however no exact closed-form formula for the pricing of Vanilla options under this model. Approximations must be used. While there exists many approximations taylored to this specific problem in the litterature, this paper explores the use of existing well-known basket option formulas for the pricing of European options on a single asset with cash dividends in the piecewise lognormal model.

The Role of Institutional Investors in Pension Risk Transfers
Pana, Elisabeta,McCarthy, Mary,Weinberger, Andrew
SSRN
Risk transfers represent a preferred method for removing pension liabilities from corporate balance sheet. We examine the role of institutional shareholders on firmâ€™s decision to offload pension liabilities to professional risk managers. We find that the likelihood of pension risk transfers is higher for firms with higher level of institutional ownership and independent institutional owners. Firms with higher concentration of institutional ownership adopting a passive investment strategy are less likely to complete pension risk transfers. We also document the plan and sponsor-level factors affecting firmsâ€™ decision to undertake pension risk transfers.

The gig economy in Poland: evidence based on mobile big data
Beręsewicz Maciej,Nikulin Dagmara,Szymkowiak Marcin,Wilak Kamil
arXiv

In this article we address the question of how to measure the size and characteristics of the platform economy. We propose a~different, to sample surveys, approach based on smartphone data, which are passively collected through programmatic systems as part of online marketing. In particular, in our study we focus on two types of services: food delivery (Bolt Courier, Takeaway, Glover, Wolt and transport services (Bolt Driver, Free Now, iTaxi and Uber).

Our results show that the platform economy in Poland is growing. In particular, with respect to food delivery and transportation services performed by means of applications, we observed a growing trend between January 2018 and December 2020. Taking into account the demographic structure of apps users, our results confirm findings from past studies: the majority of platform workers are young men but the age structure of app users is different for each of the two categories of services. Another surprising finding is that foreigners do not account for the majority of gig workers in Poland.

When the number of platform workers is compared with corresponding working populations, the estimated share of active app users accounts for about 0.5-2% of working populations in 9 largest Polish cities.

Welfare-Based Optimal Macroprudential Policy with Shadow Banks
Gebauer, Stefan
SSRN
In this paper, I show that the existence of non-bank financial institutions (NBFIs) has implications for the optimal regulation of the traditional banking sector. I develop a New Keynesian DSGE model for the euro area featuring a heterogeneous financial sector allowing for potential credit leakage towards unregulated NBFIs. Introducing NBFIs raises the importance of credit stabilization relative to other policy objectives in the welfare-based loss function of the regulator. The resulting optimal policy rule indicates that regulators adjust dynamic capital requirements more strongly in response to macroeconomic shocks due to credit leakage. Furthermore, introducing non-bank finance not only alters the cyclicality of optimal regulation, but also has implications for the optimal steady-state level of capital requirements and loan-to-value ratios. Sector-specific characteristics such as bank market power and risk affect welfare gains from traditional and NBFI credit.