Search

Identifying outperforming mutual funds ex-ante is a notoriously difficult task. We use machine learning to exploit fund characteristics and construct portfolios of equity funds that earn positive and significant out-of-sample alpha net of all costs. In contrast, alphas of portfolios selected with OLS are indistinguishable from zero. We show that the performance of machine-learning methods is the joint outcome of exploiting multiple fund characteristics and allowing for flexibility in the relation between characteristics and performance. Our results hold also for portfolios of only retail funds, for various measures of fund performance, for different methodological choices, and across different market conditions.

The ongoing transformations of power systems worldwide pose important challenges, both economic and technical, for their appropriate planning and operation. A key approach to improve the efficiency of these systems is through demand-side management, i.e., to promote the active involvement of consumers in the system. In particular, the current trend is to conceive systems where electricity consumers can vary their load according to real-time price incentives, offered by retailing companies. Under this setting, retail competition plays an important role as inadequate prices or services may entail consumers switching to a rival retailer. In this work we consider a game theoretical model where asymmetric retailers compete in prices to increase their profits by accounting for the utility function of consumers. Consumer preferences for retailers are uncertain and distributed within a Hotelling line. We analytically characterize the equilibrium of a retailer duopoly, establishing its existence and uniqueness conditions for a wide class of utility functions. Furthermore, sensitivities of the equilibrium prices with respect to relevant model parameters are also provided. The duopoly model is extended to a network that includes multiple retailers with capacity constraints for which we perform static and dynamic numerical simulations. Results indicate that, depending on the retailer costs, loyalty rewards and initial market shares, the resulting equilibrium can range from complete competition to one in which a retailer has a leading or even a dominant position in the market, decreasing the consumers’ utility significantly. Moreover, the retailer network configuration also plays an important role in the competitiveness of the system.

In order to improve the efficiency and sustainability of electricity systems, most countries worldwide are deploying advanced metering infrastructures, and in particular household smart meters, in the residential sector. This technology is able to record electricity load time series at a very high frequency rates, information that can be exploited to develop new clustering models to group individual households by similar consumptions patterns. To this end, in this work we propose three hierarchical clustering methodologies that allow capturing different characteristics of the time series. These are based on a set of “dissimilarity” measures computed over different features: quantile auto-covariances, and simple and partial autocorrelations. The main advantage is that they allow summarizing each time series in a few representative features so that they are computationally efficient, robust against outliers, easy to automatize, and scalable to hundreds of thousands of smart meters series. We evaluate the performance of each clustering model in a real-world smart meter dataset with thousands of half-hourly time series. The results show how the obtained clusters identify relevant consumption behaviors of households and capture part of their geo-demographic segmentation. Moreover, we apply a supervised classification procedure to explore which features are more relevant to define each cluster. This work was supported in part by the Spanish Government through Project under Grant MTM2017-88979-P, and in part by the Fundación Iberdrola through “Ayudas a la Investigación en Energía y Medio Ambiente 2018.” The work of Andrés M. Alonso was supported in part by the Spanish Government through Project under Grant ECO2015-66593-P. Paper no. TSG-01702-2019.

We consider the portfolio selection problem for a multiperiod investor who seeks to maximize her utility of intermediate consumption facing multiple risky-assets and proportional transaction costs in the presence of return predictability. With the presence of transaction costs, this problem is very difficult to solve even numerically due to the curse of dimensionality. In this paper, we propose first several suboptimal rebalancing policies that are based on optimizing simple quadratic programs for a mean-variance investor who faces proportional transaction costs. Then, we propose some feasible rebalancing and consumption policies that can be easily computed even for many risky assets, for an investor with power utility, based on the proposed suboptimal policies. Finally, we show how to compute upper bounds and use them to study how the certainty equivalent losses of consumption, associated when using the approximate policies, depend on different problem parameters.

We investigate how transaction costs change the number of characteristics that are jointly significant for an investor’s optimal portfolio, and hence, how they change the dimension of the cross section of stock returns. We find that transaction costs increase the number of significant characteristics from six to 15. The explanation is that, as we show theoretically and empirically, combining characteristics reduces transaction costs because the trades in the underlying stocks required to rebalance different characteristics often cancel out. Thus, transaction costs provide an economic rationale for considering a larger number of characteristics than that in prominent asset-pricing models.

In this article, we focus on the estimation of a high-dimensional inverse covariance (i.e., precision) matrix. We propose a simple improvement of the graphical Lasso (glasso) framework that is able to attain better statistical performance without increasing significantly the computational cost. The proposed improvement is based on computing a root of the sample covariance matrix to reduce the spread of the associated eigenvalues. Through extensive numerical results, using both simulated and real datasets, we show that the proposed modification improves the glasso procedure. Our results reveal that the square-root improvement can be a reasonable choice in practice. Supplementary material for this article is available online. Andrés M. Alonso gratefully acknowledges financial support from CICYT Grants ECO2012-38442 and CO2015-66593. Francisco J. Nogales and Vahe Avagyan were supported by the Spanish Government through project MTM2013-44902-P.

The Split Delivery Vehicle Routing Problem (SDVRP) is a variant of the classical Capacitated Vehicle Routing Problem where multiple visits to each customer are allowed. It is an NP-hard problem where exact solutions are difficult to obtain in a reasonable time. This paper shows a tabu search heuristic with granular neighborhood called Randomized Granular Tabu Search that uses a tabu search technique in a bounded neighborhood (granular) defined by the most promising arcs and introduces some new local operators in the local granular tabu search. The algorithm also uses a random selection of the move to be introduced at the current solution. In addition, the local search procedures can explore infeasible neighborhoods in terms of vehicle capacity. These two ideas help to escape from local optima. After the local search process, the algorithm solves one traveling salesman problem per route to improve the solution. Finally, a computational study shows that the proposed method improves many of the best-known solutions for the benchmark instances of the SDVRP literature.

We analyze the optimal portfolio policy for a multiperiod mean–variance investor facing multiple risky assets in the presence of general transaction costs. For proportional transaction costs, we give a closed-form expression for a no-trade region, shaped as a multi-dimensional parallelogram, and show how the optimal portfolio policy can be efficiently computed for many risky assets by solving a single quadratic program. For market impact costs, we show that at each period it is optimal to trade to the boundary of a state-dependent rebalancing region. Finally, we show empirically that the losses associated with ignoring transaction costs and behaving myopically may be large.

We provide a general framework for finding portfolios that perform well out-of-sample in the presence of estimation error. This framework relies on solving the traditional minimum-variance problem but subject to the additional constraint that the norm of the portfolio-weight vector be smaller than a given threshold. We show that our framework nests as special cases the shrinkage approaches of Jagannathan and Ma (Jagannathan, R., T. Ma. 2003. Risk reduction in large portfolios: Why imposing the wrong constraints helps. J. Finance 58 1651–1684) and Ledoit and Wolf (Ledoit, O., M. Wolf. 2003. Improved estimation of the covariance matrix of stock returns with an application to portfolio selection. J. Empirical Finance 10 603–621, and Ledoit, O., M. Wolf. 2004. A well-conditioned estimator for large-dimensional covariance matrices. J. Multivariate Anal. 88 365–411) and the 1/N portfolio studied in DeMiguel et al. (DeMiguel, V., L. Garlappi, R. Uppal. 2009. Optimal versus naive diversification: How inefficient is the 1/N portfolio strategy? Rev. Financial Stud. 22 1915–1953). We also use our framework to propose several new portfolio strategies. For the proposed portfolios, we provide a moment-shrinkage interpretation and a Bayesian interpretation where the investor has a prior belief on portfolio weights rather than on moments of asset returns. Finally, we compare empirically the out-of-sample performance of the new portfolios we propose to 10 strategies in the literature across five data sets. We find that the norm-constrained portfolios often have a higher Sharpe ratio than the portfolio strategies in Jagannathan and Ma (2003), Ledoit and Wolf (2003, 2004), the 1/N portfolio, and other strategies in the literature, such as factor portfolios.

We study two different decomposition algorithms for the general (nonconvex) partially separable nonlinear program (PSP): bilevel decomposition algorithms (BDAs) and Schur interior-point methods (SIPMs). BDAs solve the problem by breaking it into a master problem and a set of independent subproblems, forming a type of bilevel program. SIPMs, on the other hand, apply an interior-point technique to solve the problem in its original (integrated) form, but then use a Schur complement approach to solve the Newton system in a decentralized manner. Our first contribution is to establish a theoretical relationship between these two types of decomposition algorithms. This is a first step toward closing the gap between the incipient local convergence theory of BDAs and the mature local convergence theory of interior-point methods. Our second contribution is to show how SIPMs can be modified to solve problems for which the Schur complement matrix is not invertible in general. The importance of this contribution is that it substantially enlarges the class of problems that can be addressed with SIPMs.

We study the impact of parameter uncertainty in multiperiod portfolio selection with trading costs. We analytically characterize the expected loss of a multiperiod investor, and we find that it is equal to the product of two terms. The first term corresponds with the single-period utility loss in the absence of transaction costs, as characterized by Kan and Zhou (2007), whereas the second term captures the multiperiod effects on the overall utility loss. To mitigate the impact of parameter uncertainty, we propose two multiperiod shrinkage portfolios. The first multiperiod shrinkage portfolio combines the Markowitz portfolio with a target portfolio. This method diversifies the effects of parameter uncertainty and reduces the risk of taking inefficient positions. The second multiperiod portfolio shrinks the investor's trading rate. This novel technique smooths the investor trading activity and it also may help to considerably reduce the impact of parameter uncertainty. Finally, we test the out-of-sample performance of our considered portfolio strategies with simulated and empirical datasets, and we find that ignoring transaction costs, parameter uncertainty, or both, results into large losses in the investor's performance

We devise a novel approach to combine predictions of high dimensional conditional covariance matrices using economic criteria based on portfolio selection. The combination scheme takes into account not only the portfolio objective function but also the portfolio characteristics in order to define the mixing weights. Three important advantages are that i) it does not require a proxy for the latent conditional covariance matrix, ii) it does not require optimization of the combination weights, and iii) it holds the equally-weighted model combination as a particular case. Empirical applications involving three large data sets from different markets show that the proposed economic-based combinations of multivariate GARCH forecasts leads to mean-variance portfolios with higher risk-adjusted performance in terms of Sharpe ratio as well as to minimum variance portfolios with lower risk on an out-of-sample basis with respect to a number of benchmark specifications.

We propose a relaxation scheme for mathematical programs with equilibrium constraints (MPECs). In contrast to previous approaches, our relaxation is two-sided: both the complementarity and the nonnegativity constraints are relaxed. The proposed relaxation update rule guarantees (under certain conditions) that the sequence of relaxed subproblems will maintain a strictly feasible interior---even in the limit. We show how the relaxation scheme can be used in combination with a standard interior-point method to achieve superlinear convergence. Numerical results on the MacMPEC test problem set demonstrate the fast local convergence properties of the approach.

This paper addresses the self-scheduling problem of a price-taker power producer. It focuses on risk modeling, emphasizing the tradeoff existing between maximum profit and minimum risk. The paper analyzes a self-scheduling model that considers simultaneously profit and risk. This model is formulated as a mixed-integer quadratic programming problem, which is solved using commercially available software. Relevant results from a realistic case study are discussed.

Price forecasting is becoming increasingly relevant to producers and consumers in the new competitive electric power markets. Both for spot markets and long-term contracts, price forecasts are necessary to develop bidding strategies or negotiation skills in order to maximize benefit. This paper provides a method to predict next-day electricity prices based on the ARIMA methodology. ARIMA techniques are used to analyze time series and, in the past, have been mainly used for load forecasting, due to their accuracy and mathematical soundness. A detailed explanation of the aforementioned ARIMA models and results from mainland Spain and Californian markets are presented.

This paper describes a decomposition methodology applied to the multi-area optimal power flow problem in the context of an electric energy system. The proposed procedure is simple and efficient, and presents some advantages with respect to other common decomposition techniques such as Lagrangian relaxation and augmented Lagrangian decomposition. The application to the multi-area optimal power flow problem allows the computation of an optimal coordinated but decentralized solution. The proposed method is appropriate for an Independent System Operator in charge of the electric energy system technical operation. Convergence properties of the proposed decomposition algorithm are described and related to the physical coupling between the areas. Theoretical and numerical results show that the proposed decentralized methodology has a lower computational cost than other decomposition techniques, and in large large-scale cases even lower than a centralized approach.

This paper provides a framework to obtain the optimal bidding strategy of a price-taker producer. An appropriate forecasting tool is used to estimate the probability density functions of next-day hourly market-clearing prices. This probabilistic information is used to formulate a self-scheduling profit maximization problem that is solved taking advantage of its particular structure. The solution of this problem allows deriving a simple yet informed bidding rule. Results from a realistic case study are discussed in detail.

In the framework of competitive electricity markets, power producers and consumers need accurate price forecasting tools. Price forecasts embody crucial information for producers and consumers when planning bidding strategies in order to maximize their benefits and utilities, respectively. This paper provides two highly accurate yet efficient price forecasting tools based on time series analysis: dynamic regression and transfer function models. These techniques are explained and checked against each other. Results and discussions from real-world case studies based on the electricity markets of mainland Spain and California are presented.

This article compares multivariate and univariate Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models to forecast portfolio value-at-risk (VaR). We provide a comprehensive look at the problem by considering realistic models and diversified portfolios containing a large number of assets, using both simulated and real data. Moreover, we rank the models by implementing statistical tests of comparative predictive ability. We conclude that multivariate models ou tperform their univariate counterparts on an out-of-sample basis. In particular, among the models considered in this article, the dynamic conditional correlation model with Student's t errors seems to be the most appropriate specification when implemented to estimate the VaR of the real portfolios analyzed A. A. P. S. acknowledges financial support from research Projects CNPq Universal 481719/2011-3 and UFSC-Funpesquisa 2010/2011 from the Brazilian Government. F. J. N. is supported by the Spanish Government through Project MTM2010-16519. E. R. is supported by the Spanish Government ECO2009-08100

We study whether investors can exploit stock return serial dependence to improve out-of- sample portfolio performance. To do this, we first show that a vector-autoregressive (VAR) model estimated with ridge regression captures daily stock return serial dependence in a stable manner. Second, we characterize (analytically and empirically) expected returns of VAR-based arbitrage portfolios, and show that they compare favorably to those of existing arbitrage portfolios. Third, we evaluate the performance of VAR-based investment (positive-cost) portfolios. We show that, subject to a suitable norm constraint, these portfolios outperform the traditional (unconditional) portfolios for transaction costs below 10 basis points.

We analyze the optimal portfolio policy for a multiperiod mean-variance investor facing a large number of risky assets in the presence of general transaction cost. For proportional transaction costs, we give a closed-form expression for a no-trade region, shaped as a multi-dimensional parallelogram, and show how the optimal portfolio policy can be efficiently computed by solving a single quadratic program. For market impact costs, we show that at each period it is optimal to trade to the boundary of a state-dependent rebalancing region. Finally, we show empirically that the utility loss associated with ignoring transaction costs may be large.

We study the impact of parameter uncertainty on the expected utility of a multiperiod investor subject to quadratic transaction costs. We characterize the utility loss associated with ignoring parameter uncertainty, and show that it is equal to the product between the single-period utility loss and another term that captures the effects of the multiperiod mean-variance utility and transaction cost losses. To mitigate the impact of parameter uncertainty, we propose two multiperiod shrinkage portfolios and demonstrate with simulated and empirical datasets that they substantially outperform portfolios that ignore parameter uncertainty, transaction costs, or both.

We devise a novel approach to combine predictions of high-dimensional conditional covariance matrices using economic criteria based on portfolio selection. The combination scheme takes into account not only the portfolio objective function but also the portfolio characteristics in order to define the mixing weights. Three important advantages are that i) it does not require a proxy for the latent conditional covariance matrix, ii) it does not require optimization of the combination weights, and iii) can be calibrated in order to adjust the influence of the best performing models. Empirical application involving a data set with 50 assets over a 10-year time span shows that the proposed economic-based combinations of multivariate volatility forecasts leads to mean–variance portfolios with higher risk-adjusted performance in terms of Sharpe ratio as well as to minimum variance portfolios with lower risk on an out-of-sample basis with respect to a number of benchmark specifications.

We propose a novel approach to active risk management based on the recent Basel II regulations to obtain optimal portfolios with minimum capital requirements. In order to avoid regulatory penalties due to an excessive number of Value-at-Risk (VaR) violations, capital requirements are minimized subject to a given number of violations over the previous trading year. Capital requirements are based on the recent Basel II amendments to account for the ‘stressed’ VaR, that is, the downside risk of the portfolio under extreme adverse market conditions. An empirical application for two portfolios involving different types of assets and alternative stress scenarios demonstrates that the proposed approach delivers an improved balance between capital requirement levels and the number of VaR exceedances. Furthermore, the riskadjusted performance of the proposed approach is superior to that of minimum-VaR and minimumstressed VaR portfolios. André A. P. Santos acknowledges financial support from research Projects CNPq 481719/2011 3 and UFSC Funpesquisa 2010/2011 from the Brazilian Government. Francisco J. Nogales is supported by the Spanish Government through Project MTM 2010 16519. Esther Ruiz is supported by the Spanish Government ECO2009 08100 Publicado

We carry out a comprehensive investigation of shrinkage estimators for asset allocation, and we find that size matters —the shrinkage intensity plays a significant role in the performance of the resulting estimated optimal portfolios. We study both portfolios computed from shrinkage estimators of the moments of asset returns ( shrinkage moments ), as well as shrinkage portfolios obtained by shrinking the portfolio weights directly. We make several contributions in this field. First, we propose two novel calibration criteria for the vector of means and the inverse covariance matrix. Second, for the covariance matrix we propose a novel calibration criterion that takes the condition number optimally into account. Third, for shrinkage portfolios we study two novel calibration criteria. Fourth, we propose a simple multivariate smoothed bootstrap approach to construct the optimal shrinkage intensity. Finally, we carry out an extensive out-of-sample analysis with simulated and empirical datasets, and we characterize the performance of the different shrinkage estimators for portfolio selection.

We propose a novel approach to active risk management based on the recent Basel II regulations to obtain optimal portfolios with minimum capital requirements. In order to avoid regulatory penalties due to an excessive number of Value-at-Risk (VaR) violations, capital requirements are minimized subject to a given number of violations over the previous trading year. Capital requirements are based on the recent Basel II amendments to account for the ‘stressed’ VaR, that is, the downside risk of the portfolio under extreme adverse market conditions. An empirical application for two portfolios involving different types of assets and alternative stress scenarios demonstrates that the proposed approach delivers an improved balance between capital requirement levels and the number of VaR exceedances. Furthermore, the risk adjusted performance of the proposed approach is superior to that of minimum-VaR and minimum stressed VaR portfolios.

We study whether investors can exploit serial dependence in stock returns to improve out-of-sample portfolio performance. We show that a vector-autoregressive (VAR) model captures stock return serial dependence in a statistically significant manner. Analytically, we demonstrate that, unlike contrarian and momentum portfolios, an arbitrage portfolio based on the VAR model attains positive expected returns regardless of the sign of asset return cross-covariances and autocovariances. Empirically, we show, however, that both the arbitrage and mean-variance portfolios based on the VAR model outperform the traditional unconditional portfolios only for transaction costs below ten basis points.

In this paper, we provide a general framework for determining the portfolio that has superior out-of-sample performance even in the presence of estimation error. This general framework relies on solving the traditional minimum-variance problem (based on the sample covariance matrix) but subject to the additional constraint that the norm of the portfolio weight vector must be smaller than a given threshold. We show that our general framework nests as special cases the shrinkage approaches of Jagannathan and Ma (2003) and Ledoit and Wolf (2004b), and the 1/N policy studied in DeMiguel, Garlappi, and Uppal (2007), and that all these policies can be interpreted as those of a Bayesian investor who has a certain prior belief on portfolio weights. We also use our general framework to propose several new portfolio strategies. Finally, we compare empirically (in terms of portfolio variance, Sharpe ratio, and turnover), the out-of-sample performance of the new polices we propose to ten strategies in the existing literature across ten datasets. We find that the new policies we propose can outperform the policies proposed in Jagannathan and Ma (2003) and Ledoit and Wolf (2004b), the 1/N policy evaluated in DeMiguel, Garlappi, and Uppal (2007), and also other strategies in the literature such as Brandt, Santa-Clara, and Valkanov (2005).

Organized trading for electricity includes both the pool and the futures market. Pool prices are volatile while the prices of the futures-market products are comparatively more stable. Thus, futures-market products constitute hedging instruments to reduce the risk suffered by any market agent. Electricity market agents engage in both pool and futures market transactions seeking to maximize their respective profits/utilities for a given risk level on profit variability. To make informed decisions, the market agent must gather as much accurate information as possible on the pool prices covering the whole time horizon spanned by the futures-market product. This paper provides a novel technique to represent conveniently the uncertainty associated with pool prices during long- or medium-term horizons through a set of scenarios, that is, pool price realizations. The proposed technique uses the prices of the futures-market products as long-term explanatory variables and exploits the short-term structure of the pool prices.