Improving the accuracy and operational predictability of project cost forecasts: an adaptive combination approach

Conducting an early warning forecast to detect potential cost overrun is essential for timely and effective decision-making in project control. This paper presents a forecast combination model that adaptively identifies the best forecast and optimises various combinations of commonly used project cost forecasting models. To do so, a forecast error simulator is formulated to visualise and quantify likely error profiles of forecast models and their combinations. The adaptive cost combination (ACC) model was applied to a pilot project for numerical illustration as well as to real world projects for practical implementation. The results provide three valuable insights into more effective project control and forecasting. First, the best forecasting model may change in individual projects according to the project progress and the management priority (i.e. accuracy, outperformance or large errors). Second, adaptive combination of simple, index-based forecasts tends to improve forecast accuracy, while mitigating the risk of large errors. Third, a post-mortem analysis of seven real projects indicated that the simple average of two most commonly used cost forecasts can be 31.2% more accurate, on average, than the most accurate alternative forecasts.     

Scenario aggregation in single-resource production planning models with uncertain demand

In this paper we present an application of the scenario aggregation approach proposed by Rockafellar and Wets to a simple standard multi-product multi-period production planning problem with uncertain demand and setup cost modelled by logical zero-one variables. The uncertainty in demand is expressed by a number of demand scenarios. As compared with more traditional approaches that require distributional assumptions and/or estimates of parameters from historical demand data, the scenario approach offers greater flexibility and makes it possible to take subjective information into account. The scenario aggregation principle and the corresponding progressive hedging algorithm offer a theoretically sound basis for generating consistent solutions for production planning models with uncertain demand. Since the production planning problem studied in this paper is of mixed-integer type the original scenario aggregation approach cannot be applied directly. However, since the integer variables in the production planning model are indirectly coupled to the continuous production decisions an alternative method in which only the production quantities are used to couple the different realizations can be used. This paper is a first attempt to perform this form of coupling. We illustrate the ideas on a small example and use this example to demonstrate how the solution can be evaluated in terms of flexibility measures.     

Planning for production in construction: controlling costs in major capital projects

There has been limited research that has examined how the public sector can guarantee their major capital projects are delivered within budget. A Strategic Asset Management Framework (SAMF) developed by the Western Australian State Government, was implemented that ensured their major capital projects were delivered within 5% of their budget. Interviews were conducted with stakeholders who had participated in the delivery of capital projects using the SAMF to understand how it had been used to successfully deliver projects. The interviews highlighted the importance of the SAMF in addressing optimism bias and strategic misrepresentation with the use of independent auditors. The research provides invaluable insights from practice that have been used to control and manage the capital expenditure of assets. Such knowledge is pivotal for ensuring strides are made forward to addressing the cost growth phenomenon that continues to plague major capital projects.     

A multistage approach for production and workforce planning in long-cycle product environments

Aggregate production planning (APP) has been studied extensively for the past two decades. The APP problem, also called production and workforce scheduling, is to determine the optimal workforce and production level in each period of the planning horizon in order to satisfy demand forecasts for these periods. The advantages of the APP are low cost of data collection and computational cost of the running model; the accuracy of data; and, effective managerial understanding of the results. If the product of concern takes longer than one period, it is called a long-cycle product. Examples of long-cycle products are aircraft, ships, buildings and special machines. A detailed model incorporating dynamic productivity and long-cycle products considerations is presented to solve the problem of production and workforce planning. Using a multistage production system approach, a search technique is developed to solve this class of problems where the objective function is linear and some of the constraint coefficients are dynamically nonlinear. The model provides a better solution than an aggregate production planning model, often used to solve these problems.     

How managers decide to use planning models

Recent published reports and surveys have shown that a growing number of corporations and government agencies are using decision models not only for lower level scheduling and resource allocation but also for short-range and long-range planning. Although the literature has described in some detail the types of models used and the ways in which they are used, limited attention has been paid to the ways in which managers decide whether or not to use these models. This paper, which is based on a series of case studies, suggests that the decision to use planning models is made not by performing a comprehensive cost benefit analysis, but by the use of a reference model—that is, an existing model, sometimes in a competitive organization, similar to the one being considered.     

Using Prior Risk‐Related Knowledge to Support Risk Management Decisions: Lessons Learnt from a Tunneling Project

The authors of this article have developed six probabilistic causal models for critical risks in tunnel works. The details of the models' development and evaluation were reported in two earlier publications of this journal. Accordingly, as a remaining step, this article is focused on the investigation into the use of these models in a real case study project. The use of the models is challenging given the need to provide information on risks that usually are both project and context dependent. The latter is of particular concern in underground construction projects. Tunnel risks are the consequences of interactions between site‐ and project‐ specific factors. Large variations and uncertainties in ground conditions as well as project singularities give rise to particular risk factors with very specific impacts. These circumstances mean that existing risk information, gathered from previous projects, is extremely difficult to use in other projects. This article considers these issues and addresses the extent to which prior risk‐related knowledge, in the form of causal models, as the models developed for the investigation, can be used to provide useful risk information for the case study project. The identification and characterization of the causes and conditions that lead to failures and their interactions as well as their associated probabilistic information is assumed to be risk‐related knowledge in this article. It is shown that, irrespective of existing constraints on using information and knowledge from past experiences, construction risk‐related knowledge can be transferred and used from project to project in the form of comprehensive models based on probabilistic‐causal relationships. The article also shows that the developed models provide guidance as to the use of specific remedial measures by means of the identification of critical risk factors, and therefore they support risk management decisions. Similarly, a number of limitations of the models are discussed.     

Financial Innovation and the Transactions Demand for Cash

We document cash management patterns for households that are at odds with the predictions of deterministic inventory models that abstract from precautionary motives. We extend the Baumol–Tobin cash inventory model to a dynamic environment that allows for the possibility of withdrawing cash at random times at a low cost. This modification introduces a precautionary motive for holding cash and naturally captures developments in withdrawal technology, such as the increasing diffusion of bank branches and ATM terminals. We characterize the solution of the model, which qualitatively reproduces several empirical patterns. We estimate the structural parameters using micro data and show that quantitatively the model captures important economic patterns. The estimates are used to quantify the expenditure and interest rate elasticity of money demand, the impact of financial innovation on money demand, the welfare cost of inflation, and the benefit of ATM ownership.     

Optimal and Heuristic Decision Strategies for Integrated Production and Marketing Planning

In this study we examine the effects of integrating production and marketing decisions for a short- to medium-range planning horizon in a profit maximizing firm. We formulate two models for determining price, marketing expenditure, demand or production volume, and lot size for a single product with stable demand when economies of scale are present. The full integration (FI) model simultaneously determines all the decisions involved, while the partial integration (PI) model separates the lot sizing decision from the others, as happens frequently in practice. Geometric programming (GP) techniques and marginal analysis are used to compare FI and PI, and obtain important managerial implications regarding the two models.     

Financial planning for new products: Part I—Basis for model formulation

In a previous paper the author presented a staged approach methodology for the evaluation and selection of R & D projects. The present paper is intended to serve as its complement.The aim is the formulation of a matching overall long range budget planning policy which will attempt to answer the questions of “how many projects to prove” and “how much to fund” on the basis of satisfying the company growth objective.To achieve the above purpose, a staged budget planning model has been developed which recognizes and utilizes the specific attributes of the various R & D stages. Tje project stage survival rate and project stage cost ratio concepts are discussed. A steady flow of projects through the various R & D stage is maintained. The aim of the program is to produce periodically a planned number of new products fro commercial investment.This methodology may apply to R & D program with a sufficient number of moderately sized projects that justify the use of survival rate and cost ratio values. It should be constructed as a tentative effort for possible use within the staged limitations.     

Comparison and Validation of Statistical Methods for Predicting Power Outage Durations in the Event of Hurricanes

This article compares statistical methods for modeling power outage durations during hurricanes and examines the predictive accuracy of these methods. Being able to make accurate predictions of power outage durations is valuable because the information can be used by utility companies to plan their restoration efforts more efficiently. This information can also help inform customers and public agencies of the expected outage times, enabling better collective response planning, and coordination of restoration efforts for other critical infrastructures that depend on electricity. In the long run, outage duration estimates for future storm scenarios may help utilities and public agencies better allocate risk management resources to balance the disruption from hurricanes with the cost of hardening power systems. We compare the out‐of‐sample predictive accuracy of five distinct statistical models for estimating power outage duration times caused by Hurricane Ivan in 2004. The methods compared include both regression models (accelerated failure time (AFT) and Cox proportional hazard models (Cox PH)) and data mining techniques (regression trees, Bayesian additive regression trees (BART), and multivariate additive regression splines). We then validate our models against two other hurricanes. Our results indicate that BART yields the best prediction accuracy and that it is possible to predict outage durations with reasonable accuracy.     

Forecasting lead times with economic data

Procurement lead time estimates are critical factors in production planning; however, they are generally based on a buyer's experience. The Westinghouse Corporation developed a linear model which successfully predicted procurement lead times for hot and cold rolled steel. This paper discusses nine models which use utilization and inventory data to predict lead time planning factors for aluminum, magnesium, steel and titanium products. The Lockheed-Georgia Company, which produces aerospace products, provided data for this research. The functional form of the models is significant and suggests that a nonlinear transformation of utilization based upon simple queueing models is a significant predictor of lead time duration.     

惯性灰色模型及其应用性质研究

研究灰色预测模型建模的演化过程，可以更好地了解模型的本质特征和状态变化。惯性灰色模型主要研究灰色预测模型建模的演化过程，了解系统变化状态。本文根据数据的力学特性，利用矩阵分析方法研究惯性灰色模型的建模步骤，简化文献［1］中惯性模型的结构参数和分量参数形式，总结求解各种数据序列的力学变换式，获取各种惯性灰色模型的建模机理。最后通过实例研究系统状态的演变过程，将惯性灰色GM(1,1)模型应用到交通流状态的判定中，得到三相交通流与三种惯性灰色GM(1,1)模型的对应关系。利用三种惯性模型模拟效果来准确判断交通流的状态，揭示交通系统实时特性，为交通规划、控制和优化提供可靠的理论依据。     

Assessment of aircraft logistics planning models

An assessment of military logistics planning models offers a great deal of information about the modelling state of art. Such tools include both analytic and simulation model types. They can deal with both static and dynamic characteristics of the environment. They require highly detailed data for their operation and can compute over a large number of interacting variables. Unfortunately, these models do not satisfy adequately the requirements of the particular logistics issue for which they were assessed, which is whether such models can be used in early logistics planning for new weapon systems. One difficulty is that such planning must make extensive use of tradeoffs and sensitivity analysis to take account of the flexibility and uncertainties existing at the early stages. Another is that the existent models call for detailed data which is usually not available at that time. Therefore, although the models do fulfill a particular useful planning function, they must be replaced or augmented by a new class of models that will much more closely satisfy the planning need. This new capability requires a serious research effort that will benefit not only the military logistics planners, but also other planners dealing with large capital development programs.     

Structure and Parameterization of Pharmacokinetic Models: Their Impact on Model Predictions

There has been an increasing interest in physiologically based pharmacokinetic (PBPK)models in the area of risk assessment. The use of these models raises two important issues: (1)How good are PBPK models for predicting experimental kinetic data? (2)How is the variability in the model output affected by the number of parameters and the structure of the model? To examine these issues, we compared a five-compartment PBPK model, a three-compartment PBPK model, and nonphysiological compartmental models of benzene pharmacokinetics. Monte Carlo simulations were used to take into account the variability of the parameters. The models were fitted to three sets of experimental data and a hypothetical experiment was simulated with each model to provide a uniform basis for comparison. Two main results are presented: (1)the difference is larger between the predictions of the same model fitted to different data se1ts than between the predictions of different models fitted to the dame data; and (2)the type of data used to fit the model has a larger effect on the variability of the predictions than the type of model and the number of parameters.     

Assessing the impact of uncertainty and the level of aggregation in case mix planning

In this article, we present a framework for evaluating the impact of uncertainty and the use of different aggregation levels in case mix planning on the quality of strategic decisions regarding the case mix of a hospital. In particular, we analyze the effect of modeling (i) demand, (ii) resource use, and (iii) resource availability as stochastic input parameters on the performance of case mix planning models. In addition, the consequences of taking the weekly structure with inactive days without surgeries into account are assessed (iv). The purpose of this paper is to provide a guideline for the decision-maker planning the case mix on the consideration of stochastic aspects and different aggregation levels. We formulate a mixed integer programming model for case mix planning along with different stochastic and deterministic extensions. The value of the different extensions is analyzed using a factorial design. The resulting stochastic models are solved using sample average approximation. Simulation is used to evaluate the strategies derived by the different models using real-world data from a large German hospital. We find that highly aggregated basic case mix planning models can overestimate the objective value by up to 10% and potentially lead to biased results. Refining the problem decreased the gap between projected case mix planning results and simulated results considerably and led to improved solutions.     

A model for new product planning

A model is proposed for long term budget planning of new products. The model makes use of the Project Stage Survival Rate and Project Stage Cost Rate concepts discussed previously in Part I of this paper. published in our August edition.

The methodology utilizes the special attributes of the stages encountered during the R & D process. For this purpose, the project stage is used as a budgeting module. The model is oriented to satisfy the company growth objective by considering a continuous flow of new projects. The process aims at the successful completion of a planned number of projects within given time periods.

A hypothetical application of the model is presented in the form of a Budget Planning Chart.     

A robust optimization model for stochastic aggregate production planning

The aggregate production planning (APP) problem considers the medium-term production loading plans subject to certain restrictions such as production capacity and workforce level. It is not uncommon for management to often encounter uncertainty and noisy data, in which the variables or parameters are stochastic. In this paper, a robust optimization model is developed to solve the aggregate production planning problems in an environment of uncertainty in which the production cost, labour cost, inventory cost, and hiring and layoff cost are minimized. By adjusting penalty parameters, decision-makers can determine an optimal medium-term production strategy including production loading plan and workforce level while considering different economic growth scenarios. Numerical results demonstrate the robustness and effectiveness of the proposed model. The proposed model is realistic for dealing with uncertain economic conditions. The analysis of the tradeoff between solution robustness and model robustness is also presented.     

Cost models for lot streaming in a multistage flow shop

Lot streaming is a technique used to split a processing batch into several transfer batches. In this way, overlapping operations can be performed in different manufacturing stages, and production can be accelerated. This paper proposes two cost models for solving lot streaming problems in a multistage flow shop. The purpose is to determine the optimal processing batch size and the optimal number of transfer batches that minimize the total annual cost in each model. In the first model, a more complete and accurate method is developed to compute the costs of raw materials, work-in-process, and finished-product inventories. The total cost includes the setup cost, the transfer batch movement cost, the three-type inventory holding cost, and the finished-product shipment cost. The second model contains not only the four costs in the first model, but also the imputed cost associated with the makespan time. The total annual cost functions in both models are shown to be convex, and two solution approaches are suggested. An experiment consisting of three phases was conducted to explore the effect on the optimal solution when changing the value of one parameter at a time. The results indicate that three parameters have significant effects on the optimal solution.     

Understanding the planner’s role in lookahead construction planning

Capacity planning is instrumental in production planning as the variability witnessed in construction projects complicates the planner’s role in achieving a balance between weekly task load and available resources. The purpose of this article is to assess the effects of capacity planning on a project’s time and cost performance and to inform planners on the pitfalls of uninformed capacity planning. A simulation model is developed to test several project scenarios against different capacity planning methods. Cost, time and planning quality measures are developed to track project’s performance throughout the construction period. Results show that the planner’s choice of capacity planning method and the type of project both affect a project’s cost and duration. Interestingly, informed planners who are aware of a project’s characteristics are able to achieve the best balance between weekly load and capacity. They are able to reduce incurred costs wasted on idle resources without significantly affecting the construction period.     

Investment Appraisal and Measures of Performance in Italian Divisionalised Companies

The aim of this study was to describe and analyse the current practice and trends in the development of management control practice as regards divisional investments in large Italian firms, using a survey questionnaire method. Some comparison with top North-American and German international manufacturing units were also made.The findings of the study supported two theoretical propositions. In the identification stage, firms tend to decentralise the process of capital budgeting and the control mechanism ensuring the link between corporate strategic objectives and capital expenditure projects at divisional level is based on guidelines produced by headquarters. In the selection stage firms which perceive a high interface level with the corporate strategic objectives in divisional capital expenditure tend to use discounted cash flow techniques when choosing one or more investment projects. When an economic approach is used to provide a comprehensive measure of performance, the theoretical framework fails to predict the relationship between corporate control and performance evaluation system in divisionalised companies. Essentially, financial control combines non-financial measures, used to understand manufacturing operations, with traditional accounting measures, used to understand the effects of manufacturing activities on the level of operating cash flow and operating income, as a comprehensive measures of performance in the medium-term of divisional investments.