Efficient frontier cutoff policies in credit portfolios

Historically, account acquisition in scored retail credit and loan portfolios has focused on risk management in the sense of minimizing default losses. We believe that acquisition policies should focus on a broader set of business measures that explicitly recognize tradeoffs between conflicting objectives of losses, volume and profit. Typical business challenges are: ‘How do I maximize portfolio profit while keeping acceptance rate (volume, size) at acceptable levels?’ ‘How do I maximize profit without incurring default losses above a given level?’ ‘How do I minimize the risk of large loss exposures for a given market share?’ In this paper we are not concerned with which combination of objectives are appropriate, but rather focus on the cutoff policies that allow us to capture a number of different portfolio objectives. When there are conflicting objectives we show that optimal policies yield meaningful tradeoffs and efficient frontiers and that optimal shadow prices allow us to develop risk-adjusted tradeoffs between profit and market share. Some of the graphical solutions that we obtain are simple to derive and easy to understand without explicit mathematical formulations but even simple constraints may require formal use of non-linear programming techniques. We concentrate on models and insights that yield decision strategies and cutoff policies rather than the techniques for developing good predictors.     

Linear-quadratic efficient frontiers for portfolio optimization

Finding portfolios with given mean return and minimal lower partial mean or variance, two risk criteria of interest in the theory of optimal portfolio selection, is a stochastic linear-quadratic program that can be converted to a large-scale linear or quadratic program when the asset returns are finitely distributed. These efficient frontiers can be computed on presently available platforms for problems of reasonable size; we discuss our experience with a problem involving one thousand assets. Asymptotic statistics for stochastic programs can be applied to justify sampling as a means to approximate continuous distributions by finite distributions.     

Computing efficient frontiers using estimated parameters

The mean-variance model for portfolio selection requires estimates of many parameters. This paper investigates the effect of errors in parameter estimates on the results of mean-variance analysis. Using a small amount of historical data to estimate parameters exposes the model to estimation errors. However, using a long time horizon to estimate parametes increasers the possibility of nonstationarity in the parameters. This paper investigates the tradeoff between estimation error and stationarity. A simulation study shows that the effects of estimation error can be surprisingly large. The magnitude of the errors increase with the number of securities in the analysis. Due to the error maximization property of mean-variance analysis, estimates of portfolio performance are optimistically biased predictors of actual portfolio performance. It is important for users of mean-variance analysis to recognize and correct for this phenomenon in order to develop more realistic expectations of the future performance of a portfolio. This paper suggests a method for adjusting for the bias. A statistical test is proposed to check for nonstationarity in historical data.     

Optimal sequential inspection policies

We consider the problem of combining a given set of diagnostic tests into an inspection system to classify items of interest (cases) with maximum accuracy such that the cost of performing the tests does not exceed a given budget constraint. One motivating application is sequencing diagnostic tests for container inspection, where the diagnostic tests may correspond to radiation sensors, document checks, or imaging systems. We consider mixtures of decision trees as inspection systems following the work of Boros et al. (Nav. Res. Logist. 56:404?C420, 2009). We establish some properties of efficient inspection systems and characterize the optimal classification of cases, based on some of their test scores. The measure of performance is the fraction of all cases in a specific class of interest, which are classified correctly. We propose a dynamic programming algorithm that constructs more complex policies by iteratively prefixing devices to a subset of policies and thereby enumerating all of the efficient (i.e., undominated) inspection policies in the two dimensional cost-detection space. Our inspection policies may sequence an arbitrary number of tests and are not restricted in the branching factor. Our approach directly solves the bi-criterion optimization problem of maximizing detection and minimizing cost, and thus supports sensitivity analysis over a wide range of budget and detection requirements.     

Optimal myopic policies and index policies for stochastic scheduling problems

Stochastic scheduling problems are considered by using discounted dynamic programming. Both, maximizing pure rewards and minimizing linear holding costs are treated in one common Markov decision problem. A sufficient condition for the optimality of the myopic policy for finite and infinite horizon is given. For the infinite horizon case we show the optimality of an index policy and give a sufficient condition for the index policy to be myopic. Moreover, the relation between the two sufficient conditions is discussed.     

Optimal pricing policies for perishable products

In many industrial settings, managers face the problem of establishing a pricing policy that maximises the revenue from selling a given inventory of items by a fixed deadline, with the full inventory of items being available for sale from the beginning of the selling period. This problem arises in a variety of industries, including the sale of fashion garments, flight seats, and hotel rooms. We present a family of continuous pricing functions for which the optimal pricing strategy can be explicitly characterised and easily implemented. These pricing functions are the basis for a general pricing methodology which is particularly well suited for application in the context of an increasing role for the Internet as a means to market goods and services.     

Optimal policies in stochastic shop scheduling

In this paper a survey is presented of some of the recent results in stochastic open shop, flow shop and job shop scheduling. The distributions of the processing times of the jobs are known in advance, but the actual processing times are not known in advance. The jobs may have due dates. Optimal preemptive and nonpreemptive policies are determined for the minimization of various objective functions, such as the expected makespan, the expected flow time and the expected number of late jobs. The effect of various degrees of dependence between the processing times of any given job on the various machines is investigated. Under given conditions bounds are obtained for the expected makespan in the different models.Partially supported by the National Science Foundation (NSF), under grant ECS-8115344 with the Georgia Institute of Technology.     

Optimal dynamic equilibrium in insurance policies

Insurance companies sell contracts of various types each of them having a specific probability of return. Insurers may also own, at the same time, several insurance contracts which evolve through time. In this context, expectation and variance of the free reserves appear as functions of the number of customers in different classes as well as their evolution. Assuming that the customer system can be formulated as an open Markov one characterized by free entry, it is interesting to seek the optimal new customer distribution over the different customer classes j, which permits the minimization of the variance of free reserves for a desired average level of free reserves at a given time horizon. It is shown that, under some conditions, the customer system converges to an optimal growth steady state.     

Optimal control policies for ambulance diversion

Ambulance diversion (AD) is used by emergency departments (EDs) to relieve congestion by requesting ambulances to bypass the ED and transport patients to another facility. We study optimal AD control policies using a Markov Decision Process (MDP) formulation that minimizes the average time that patients wait beyond their recommended safety time threshold. The model assumes that patients can be treated in one of two treatment areas and that the distribution of the time to start treatment at the neighboring facility is known. Assuming Poisson arrivals and exponential times for the length of stay in the ED, we show that the optimal AD policy follows a threshold structure, and explore the behavior of optimal policies under different scenarios. We analyze the value of information on the time to start treatment in the neighboring hospital, and show that optimal policies depend strongly on the congestion experienced by the other facility. Simulation is used to compare the performance of the proposed MDP model to that of simple heuristics under more realistic assumptions. Results indicate that the MDP model performs significantly better than the tested heuristics under most cases. Finally, we discuss practical issues related to the implementation of the policies prescribed by the MDP.     

Optimal production and abatement policies of a firm

A pollution control problem from the employment and environmental policy point of view for a profit maximizing firm is studied. Two versions of the model are considered: model A with emission certificates and model B with environmental standards. The nature of the optimal solution for both a static and a dynamic model is analyzed and an economic interpretation is given. Using the theory of optimal control it can be shown that along the optimal path the increasing expenditure in pollution control is accompanied by an increasing stock of employees. The saddle point property of the equilibrium is established and the relation between the level of pollution in the stationary state and the charge per unit of effluents is derived. A sensitivity analysis of equilibrium values with respect to the changes in the parameters of the model is presented.     

Optimal policies for playing variable wager HI-LO

Use of the HI-LO procedure by the gaming industry is ubiquitous—hence playing strategies of interest to gamblers and machine providers alike. Players’ tactics necessarily depend on goals being pursued and consistent with these, a variety of schemes ranging from the ‘aggressive’ to the ‘timid’ have evolved. Characteristics of the some of the best known of these—as far as they are applicable to a variable wager version of the HI-LO routine—are considered and contrasted. Of interest, results for a relatively risk-aversive scheme, played over a finite number of rounds are reconciled with those obtained asymptotically when maximizing capital growth is the priority.     

Optimal greedy policies for stochastic control models

We introduce the notion of a greedy policy for general stochastic control models. Sufficient conditions for the optimality of the greedy policy for finite and infinite horizon are given. Moreover, we derive error bounds if the greedy policy is not optimal. The main results are illustrated by Bayesian information models, discounted Bayesian search problems, stochastic scheduling problems, single-server queueing networks and deterministic dynamic programs.     

Optimal harvesting policies for periodic Gompertz systems

In this paper, we study the periodic Gompertz system with harvesting. First, we analyze the system with continuous harvesting and obtain the maximum annual-sustainable yield, the optimal harvesting effort and the optimal population level for such a system. Then, the harvesting is assumed to occur at fixed moments every year, and we establish the Gompertz system with impulsive perturbation. And we investigate the impulsive harvesting policy to maximize the annual yield and to keep the population sustainable development. At last, the optimal results of the impulsive harvesting system are compared with those of the continuous harvesting system.     

Optimal ordering policies with convertible lead times

A firm receives orders that will be required at an uncertain time given by an Erlang distribution, and over time observes the associated independent exponential events. The firm, in turn, places orders at a linear cost from a supplier with fixed lead time l and has the option of converting (expediting) each order, at a cost, over a certain time interval after the order is originally placed. A converted order arrives l_e < l units of time after it is converted. We show that a threshold policy is optimal. Under such a policy the firm places an order after a certain number of exponential events have been observed. An order is converted the first time, if any, when the residual lead time exceeds a time threshold related to the number of exponential events realized since the order was placed.     

Optimal dynamic advertising policies for hereditary processes

In this paper, the Nerlove-Arrow model of optimal dynamic advertising policies is generalized by assuming a general probability distribution of the forgetting time, rather than the exponential one. A control problem with integrodifferential equations of motion is defined for which the transitory and steady-state properties of the optimal advertising policy are examined. The effects of assumptions like IHR-distributions and DHR-distributions, the existence of an upper bound for the forgetting time, etc., are explained. It is shown that there are two (in the case of an exponential distribution even three) different current-value adjoint functions associated with the problem, and relations between the two (three) are established. Also provided is a sensitivity analysis.Thanks are due to G. Feichtinger and S. Jorgensen for useful discussions.     

Optimal time-consistent investment and reinsurance policies for mean-variance insurers

This paper investigates the optimal time-consistent policies of an investment-reinsurance problem and an investment-only problem under the mean-variance criterion for an insurer whose surplus process is approximated by a Brownian motion with drift. The financial market considered by the insurer consists of one risk-free asset and multiple risky assets whose price processes follow geometric Brownian motions. A general verification theorem is developed, and explicit closed-form expressions of the optimal polices and the optimal value functions are derived for the two problems. Economic implications and numerical sensitivity analysis are presented for our results. Our main findings are: (i) the optimal time-consistent policies of both problems are independent of their corresponding wealth processes; (ii) the two problems have the same optimal investment policies; (iii) the parameters of the risky assets (the insurance market) have no impact on the optimal reinsurance (investment) policy; (iv) the premium return rate of the insurer does not affect the optimal policies but affects the optimal value functions; (v) reinsurance can increase the mean-variance utility.     

Optimal employment and wage policies of a monopolistic firm

This paper deals with the problem of finding optimal hiring/firing and wage policies for a profit-maximizing monopolistic firm. The crucial assumptions of the model are convex shortage costs permitting shortages in output capacity, nonlinear hiring and firing costs, and the wage rate as control variable being restricted by a minimal level. Due to the nonsmoothness of the revenue function occurring in the objective functional, a generalized maximum principle is required to analyze the optimal control problem. The resulting phase-diagram analysis provides an insight into the optimal recruitment, wage, and pricing policies.The authors would like to thank R. Hartl, E. Fehr, F. Hof, S. Jørgensen, R. Leban, N. Van Long, and R. Neck for helpful suggestions and comments to this and earlier versions of the paper.     

Optimal inspection and replacement policies for multi-state deteriorating systems

In this paper, a phase-type approach is proposed to derive optimal inspection and replacement policies for semi-Markovian deteriorating systems. In this approach, the general sojourn time distributions of a semi-Markovian maintenance model are approximated by acyclic phase-type distributions. Using the approximation, a semi-Markovian maintenance model can be transformed into a Markovian maintenance model such that the analytical tractability of Markov processes can be preserved. Based on the Markovian model, algorithms are provided to derive the optimal state-dependent and state-age-dependent inspection and replacement policies such that the expected long-run cost rate is minimized. Furthermore, procedures are developed to implement the optimal policies on semi-Markovian deteriorating systems. The implementation of the optimal policies are illustrated by numerical examples.     

Optimal replacement policies with minimal repair and age-dependent costs

In this paper, we study a modified minimal repair/replacement problem that is formulated as a Markov decision process. The operating cost is assumed to be a nondecreasing function of the system's age. The specific maintenance actions for a manufacturing system to be considered are whether to have replacement, minimal repair or keep it operating. It is shown that a control limit policy, or in particular a (t, T) policy, is optimal over the space of all possible policies under the discounted cost criterion. A computational algorithm for the optimal (t, T) policy is suggested based on the total expected discounted cost.