A fuzzy approach to R&D project portfolio selection

A major advance in the development of project selection tools came with the application of options reasoning in the field of Research and Development (R&D). The options approach to project evaluation seeks to correct the deficiencies of traditional methods of valuation through the recognition that managerial flexibility can bring significant value to projects. Our main concern is how to deal with non-statistical imprecision we encounter when judging or estimating future cash flows. In this paper, we develop a methodology for valuing options on R&D projects, when future cash flows are estimated by trapezoidal fuzzy numbers. In particular, we present a fuzzy mixed integer programming model for the R&D optimal portfolio selection problem, and discuss how our methodology can be used to build decision support tools for optimal R&D project selection in a corporate environment.     

A survey of data envelopment analysis in energy and environmental studies

Data envelopment analysis has gained great popularity in energy and environmental (E&E) modeling in recent years. In this paper, we present a literature survey on the application of data envelopment analysis (DEA) to E&E studies. We begin with an introduction to the most widely used DEA techniques, which is followed by a classification of 100 publications in this field. The main features observed are summarized. Issues related to the selection of DEA models in E&E studies are discussed.     

A multiobjective evolutionary approach for linearly constrained project selection under uncertainty

In the project selection problem a decision maker is required to allocate limited resources among an available set of competing projects. These projects could arise, although not exclusively, in an R&D, information technology or capital budgeting context. We propose an evolutionary method for project selection problems with partially funded projects, multiple (stochastic) objectives, project interdependencies (in the objectives), and a linear structure for resource constraints. The method is based on posterior articulation of preferences and is able to approximate the efficient frontier composed of stochastically nondominated solutions. We compared the method with the stochastic parameter space investigation method (PSI) and illustrate it by means of an R&D portfolio problem under uncertainty based on Monte Carlo simulation.     

Technical note: a systematic procedure based on CALIBRA and the Nelder & Mead algorithm for fine-tuning metaheuristics

The problem of setting the parameter values of a metaheuristic algorithm that optimise its performance is complex and time-consuming. Although the performance of a metaheuristic can be very sensitive to the parameter values, it is usual in the literature that the selection of the value parameters is not enough justified. There are in the literature two procedures that facilitate the task of fine-tuning: CALIBRA and the Nelder & Mead (N&M) algorithm. We propose a hands-off systematic procedure for fine-tuning metaheuristics that takes the advantages of CALIBRA and the N&M algorithm.     

R&D pipeline management: Task interdependencies and risk management

Maintaining a rich research and development (R&D) pipeline is the key to remaining competitive in many industrial sectors. Due to its nature, R&D activities are subject to multiple sources of uncertainty, the modeling of which is compounded by the ability of the decision maker to alter the underlying process. In this paper, we present a multi-stage stochastic programming framework for R&D pipeline management, which demonstrates how essential considerations can be modeled in an efficient manner including: (i) the selection and scheduling of R&D tasks with general precedence constraints under pass/fail uncertainty, and (ii) resource planning decisions (expansion/contraction and outsourcing) for multiple resource types. Furthermore, we study interdependencies between tasks in terms of probability of success, resource usage and market impact. Finally, we explore risk management approaches, including novel formulations for value at risk and conditional value at risk.     

A mixed R&D projects and securities portfolio selection model

The business environment is full of uncertainty. Allocating the wealth among various asset classes may lower the risk of overall portfolio and increase the potential for more benefit over the long term. In this paper, we propose a mixed single-stage R&D projects and multi-stage securities portfolio selection model. Specifically, we present a bi-objective mixed-integer stochastic programming model. Moreover, we use semi-absolute deviation risk functions to measure the risk of mixed asset portfolio. Based on the idea of moments approximation method via linear programming, we propose a scenario generation approach for the mixed single-stage R&D projects and multi-stage securities portfolio selection problem. The bi-objective mixed-integer stochastic programming problem can be solved by transforming it into a single objective mixed-integer stochastic programming problem. A numerical example is given to illustrate the behavior of the proposed mixed single stage R&D projects and multi-stage securities portfolio selection model.     

Optimizing Omega

This paper considers the Omega function, proposed by Cascon, Keating & Shadwick as a performance measure for comparing financial assets. We discuss the use of Omega as a basis for portfolio selection. We show that the problem of choosing portfolio weights in order to maximize Omega typically has many local solutions and we describe some preliminary computational experience of finding the global optimum using a NAG library implementation of the Huyer & Neumaier MCS method.     

ThrEEBoost: Thresholded Boosting for Variable Selection and Prediction via Estimating Equations

Most variable selection techniques for high-dimensional models are designed to be used in settings, where observations are independent and completely observed. At the same time, there is a rich literature on approaches to estimation of low-dimensional parameters in the presence of correlation, missingness, measurement error, selection bias, and other characteristics of real data. In this article, we present ThrEEBoost (Thresholded EEBoost), a general-purpose variable selection technique which can accommodate such problem characteristics by replacing the gradient of the loss by an estimating function. ThrEEBoost generalizes the previously proposed EEBoost algorithm (Wolfson 2011 Wolfson, J. (2011), “EEBoost: A General Method for Prediction and Variable Selection Based on Estimating Equations,” Journal of the American Statistical Association, 106, 296–305.[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) by allowing the number of regression coefficients updated at each step to be controlled by a thresholding parameter. Different thresholding parameter values yield different variable selection paths, greatly diversifying the set of models that can be explored; the optimal degree of thresholding can be chosen by cross-validation. ThrEEBoost was evaluated using simulation studies to assess the effects of different threshold values on prediction error, sensitivity, specificity, and the number of iterations to identify minimum prediction error under both sparse and nonsparse true models with correlated continuous outcomes. We show that when the true model is sparse, ThrEEBoost achieves similar prediction error to EEBoost while requiring fewer iterations to locate the set of coefficients yielding the minimum error. When the true model is less sparse, ThrEEBoost has lower prediction error than EEBoost and also finds the point yielding the minimum error more quickly. The technique is illustrated by applying it to the problem of identifying predictors of weight change in a longitudinal nutrition study. Supplementary materials are available online.     

Bandwidth selection for the local polynomial estimator under dependence: A simulation study

Summary  Seven of the most popular methods for bandwidth selection in regression estimation are compared by means of a thorough simulation study, when the local polynomial estimator is used and the observations are dependent. The study is completed with two plug-in bandwidths for the generalized local polynomial estimator proposed by Vilar-Fernandez & Francisco-Fernández (2002).     

Cyclotomic polynomials whose orders contain many prime factors

Let &PHgr; n (z) = ∑ ϕ (n) m=0 a (m, n) z m be the n th cyclonomic polynomial and set A(n) = max 0≤m≤ϕ(n) |a=(m, n)|. In previous papers the author has shown that for almost all integers A(n)≤ n &PHgr;(n) ; whenever lim n→∞ &PHgr;(n) = ∞ . In this paper we show that for most integers n with at least C log log n prime factors ( C > 2/log 2) this inequality is wrong.     

An investigation of model selection criteria for neural network time series forecasting

Artificial neural networks (ANNs) have received more and more attention in time series forecasting in recent years. One major disadvantage of neural networks is that there is no formal systematic model building approach. In this paper, we expose problems of the commonly used information-based in-sample model selection criteria in selecting neural networks for financial time series forecasting. Specifically, Akaike’s information criterion (AIC) and Bayesian information criterion (BIC) as well as several extensions have been examined through three real time series of Standard and Poor’s 500 index (S&P 500 index), exchange rate, and interest rate. In addition, the relationship between in-sample model fitting and out-of-sample forecasting performance with commonly used performance measures is also studied. Results indicate that the in-sample model selection criteria we investigated are not able to provide a reliable guide to out-of-sample performance and there is no apparent connection between in-sample model fit and out-of-sample forecasting performance.     

Mean values of multiplicative functions

Let f(n) be a totally multiplicative function such that | ƒ (n)|⪯ 1 for all n, and let F(s) = ∑ ∞ n=1 ƒ(n)n —∞ be the associated Dirichlet series. A variant of Halász"s method is developed, by means of which estimates for ∑ N n=1 ƒ(n)/n are obtained in terms of the size of | F(s) | for s near 1 with ℜs >1. The result obtained has a number of consequences, particularly concerning the zeros of the partial sum U N (s) =∑ N n=1 n-s s of the series for the Riemann zeta function.     

On the existence of bubble-type solutions of nonlinear singular problems

Considered in this paper is a class of singular boundary value problem, arising in hydrodynamics and nonlinear field theory, when centrally bubble-type solutions are sought: \((p(t)u0)0 = c(t)p(t)f(u); u0(0) = 0; u(+1) = L > 0\) in the half-line \([0;+1)\), where \(p(0) = 0\). We are interested in strictly increasing solutions of this problem in \([0;1)\) having just one zero in \((0;+1) \)and finite limit at zero, which has great importance in applications or pure and applied mathematics. Su±cient conditions of the existence of such solutions are obtained by applying the critical point theory and by using shooting argument [9,10] to better analysis the properties of certain solutions associated with the singular di®erential equation. To the authors' knowledge, for the first time, the above problem is dealt with when f satis¯es non-Lipschitz condition. Recent results in the literature are generalized and signi¯cantly improved.     

Pattern search ranking and selection algorithms for mixed variable simulation-based optimization

The class of generalized pattern search (GPS) algorithms for mixed variable optimization is extended to problems with stochastic objective functions. Because random noise in the objective function makes it more difficult to compare trial points and ascertain which points are truly better than others, replications are needed to generate sufficient statistical power to draw conclusions. Rather than comparing pairs of points, the approach taken here augments pattern search with a ranking and selection (R&S) procedure, which allows for comparing many function values simultaneously. Asymptotic convergence for the algorithm is established, numerical issues are discussed, and performance of the algorithm is studied on a set of test problems.     

Probabilistic Networks and R & D Portfolio Selection

Mathematical programming methods have been suggested and used as an aid to R & D project portfolio selection. One of the main criticisms of the use of such models is that the stochastic nature of the problem has been largely ignored. This paper presents a method which takes into account the stochastic nature of resource requirements and project benefits, using a combination of probabilistic networks, simulation and mathematical programming. A case study based on data from an industrial R & D laboratory is presented and compared with the use of expected value methods. The results of the study indicate that in this particular case the deterministic linear programming solution is robust.     

On a repeated game without a recursive structure

The solution is given here for the infinitely repeated two-person zero-sum games of incomplete information characterized by 2×2 games, with information matrices $\left( {{*{20}c} a & b \\ b & b \\ } \right)$\left( {\begin{array}{*{20}c} a & b \\ b & b \\ \end{array} } \right) for the first game and $\left( {{*{20}c} b & b \\ b & a \\ } \right)$\left( {\begin{array}{*{20}c} b & b \\ b & a \\ \end{array} } \right) for the second game.     

Evans functions and bifurcations of standing wave solutions in delayed synaptically coupled neuronal networks

Consider the following nonlinear singularly perturbed system of integral differential equations &\frac{\partial u}{\partial t}+f(u)+w\\ =&(\alpha-au)\int^{\infty}_0\xi(c)\left[\int_{\mathbb R}K(x-y) H\left(u\left(y,t-\frac1c|x-y|\right)-\theta\right){\rm d}y\right]{\rm d}c\\ &+(\beta-bu)\int^{\infty}_0\eta(\tau)\left[\int_{\mathbb R}W(x-y)H\big(u(y,t-\tau)-\Theta\big){\rm d}y\right]{\rm d}\tau,\\ &\frac{\partial w}{\partial t}=\varepsilon[g(u)-w], and the scalar integral differential equation &\frac{\partial u}{\partial t}+f(u)\\ =&(\alpha-a u)\int^{\infty}_0\xi(c)\left[\int_{\mathbb R}K(x-y) H\left(u\left(y,t-\frac1c|x-y|\right)-\theta\right){\rm d}y\right]{\rm d}c\\ &+(\beta-bu)\int^{\infty}_0\eta(\tau)\left[\int_{\mathbb R}W(x-y)H\big(u(y,t-\tau)-\Theta\big){\rm d}y\right]{\rm d}\tau. There exist standing wave solutions to the nonlinear system. Similarly, there exist standing wave solutions to the scalar equation. The author constructs Evans functions to establish stability of the standing wave solutions of the scalar equation and to establish bifurcations of the standing wave solutions of the nonlinear system.     

A Study of a Decision Model for R & D Project Selection

This paper reports a study made during 1966 within the Bristol Works of the British Aircraft Corporation, Guided Weapons Division into the evaluation and selection of company-funded R & D projects. After identifying the objectives and selection criteria used by the decision-makers involved in the selection process an attempt was made to establish the relative importance of and interactions between the various factors, with a view to deriving a model based on a project scoring system using a weighted sum of factor scores. However, analysis of the results obtained showed that each decision-maker had a different perception of the relevance and importance of the various factors to the objectives, so that insufficient data were obtained to achieve a fully representative model. It was shown that for such a model to usefully represent the real situation the interdependence of the selection criteria and objectives must be explicitly established.     

Decay Rates for Solutions of an Integral System of Wolff Type

In this paper, we study the asymptotic behavior of the positive solutions of the following system of involving Wolff potentials in R ⁿ

Pairs trading and outranking: The multi-step-ahead forecasting case

Pairs trading is a popular speculation strategy. Several implementation methods are proposed in the literature: they can be based on a distance criterion or on co-integration. This article extends previous research in another direction: the combination of forecasting techniques (Neural Networks) and multi-criteria decision making methods (Electre III). The key contribution of this paper is the introduction of multi-step-ahead forecasts. It leads to major changes in the trading system and raises new empirical and methodological questions. The results of an application based on S&P 100 Index stocks are promising: this methodology could be a powerful tool for pairs selection in a highly non-linear environment.