Logion is a Netherlands-based consultancy that specializes in transportation, distribution, and inventory management. Its consultants and implementation managers use decision support models to improve the effectiveness and efficiency of their clients’ logistics operations. By slashing analysis time and enhancing model accuracy, the DecisionTools Suite has become critical to the firm’s strategy and competitive position.
Logion uses the DecisionTools Suite to optimize client functions such as transportation planning, new product introduction, and to set inventory levels. For instance, TopRank is used to determine which input parameters—such as delivery arrivals—affect warehouse efficiency the most. Then, @RISK’s distribution fitting takes data such as truck arrivals to determine the probability distributions which best represent the most important variables identified by TopRank. Next, @RISK simulates a distribution process to see the chances of meeting client service requirements. By allowing models to dynamically represent uncertainty, DecisionTools has enabled Logion to provide a much more realistic picture of possible outcomes—and provide better service to its clients.
According to Logion’s Rolf van Lingen, “This software is really amazing. No more stressful late nights working with static Excel spreadsheets in order to meet my clients’ deadlines. The DecisionTools Suite really makes it easier for me to do my work in less time and with much more fun, too!”
» Read the full case study
Procter & Gamble
P&G’s Corporate Finance department has been using @RISK since 1993 when it was first introduced for evaluating cross-border siting options. These decisions required them to take into account not only uncertainties involving the capital and cost aspects of plant location, but fluctuations in exchange rates as well. The company has since come to rely on @RISK for its entire range of investment decisions including new products, extensions of product lines, geographical expansions into new countries, and manufacturing savings projects.
The department also uses PrecisionTree for real options analysis in complex decisions which often involve multiple, sequential steps. The company found that decision trees are the only tool that can correctly value multiple sequential decisions where uncertainty is private risk. PrecisionTree has been useful in helping P&G break complex projects down into individual decision options, helping understand the uncertainties, and ultimately helping them make superior decisions that enhance shareholder value.
» Read the full case study
DecisionTools Suite 5.0
PrecisionTree 5.0: Oil Drilling
This oil drilling example is a classic decision tree problem. Our first decision is whether to run geological tests on the prospective site. Then, depending on the test results, the next decision is whether to drill for oil. The final chance event is the amount of oil found. The tree progresses from left to right – the decision to test is always made before the decision to drill.
» Download example model: Oil.xls
PrecisionTree 5.0 and @RISK 5.0: Oil Drilling
The results of finding oil in the oil drilling decision tree Oil.xls are divided into three discrete outcomes - Dry, Wet and Soaking. But, in reality, the amount of oil found should be described with a continuous distribution. @RISK is used in this model to describe the uncertainty of this chance event. By adding @RISK probability distribution functions to decision trees, you gain more accurate modeling and can simulate more possible outcomes.
» Download example model: OilSimulationWithRISK.xls
TopRank 5.0 and @RISK 5.0: Product Launch
TopRank recognizes @RISK distribution functions and incorporates them in What-If analyses. This ability provides more flexibility and accuracy in modeling the possible input values in your What-If analysis.
In this example, Jupiter Corporation is building a new model of 4-door sedan. Assuming that the car will generate sales for the next 5 years, management has identified 5 factors that can influence the total revenue during that period. Several of these factors have probability distributions associated with them. During a What-If analysis, TopRank sees the probability distributions associated with these items and performs a smart sensitivity analysis using them, stepping through the range of the distribution while spacing the steps such that each interval encompasses equal amounts of probability.
» Download example model: ProductLaunchTopRankRISK.xls
NeuralTools 5.0 and Evolver 5.0: Auto Loans
NeuralTools can be used to predict unknown values of a category dependent variable from known values of numeric and category independent variables. In this example, the neural net has learned to predict whether an auto loan applicant will be making timely payments, late payments, or default on the loan. Evolver can be used to find the loan amount that will raise the probability that this applicant falls in the "timely payments" category to a target value of 90%.
» Download example model: AutoLoansWithEvolver.xls
@RISK 5.0: Discounted Cash Flow (DCF)
Discounted cash flow (DCF) calculations are a frequent example of the use of @RISK. In the example model, the sources of risk are the revenue growth rate and the variable costs as a percentage of sales. After taking into account the assumed investment, and applying a discount factor, the DCF is derived. Following the simulation, the average (mean) of the DCF is known as the net present value (NPV). The decision as to whether to proceed or not with this project will depend on the risk perspective or tolerance of the decision-maker. This example has also been extended to calculate the distribution of bonus payments on the assumption that a bonus is paid whenever the net DCF is larger than a fixed amount. It also uses the @RISK Statistics functions RiskMean, RiskTarget, and RiskTargetD to work out the average net DCF, the probability that the net DCF is negative and the probability that a bonus is paid.
» Download example model: CashFlow.xls
@RISK 5.0: Insurance Claims with RiskCompound
@RISK’s RiskCompound function uses two distributions to create a single new input distribution, streamlining insurance models that must account for frequency and severity of claims. This model illustrates how the RiskCompound function is created, and shows properties such as mean, standard deviation, and a target value of the resulting RiskCompound function.
» Download example model: RiskCompound.xls
RISKOptimizer 5.0: Product Mix
A manufacturing plant is trying to find the optimal quantities of each of four products to manufacture to maximize the mean of total revenues. The demand for each product is uncertain, and represented with probability distribution functions. The quantity of each product produced must meet constraints related to the resources available for manufacturing each product. Here, all constraints are specified in one step, using RISKOptimizer's ability to define constraint limits as ranges. RISKOptimizer will vary the amount of each product produced, subject to the constraints of resources, to maximize revenues.
» Download example model: ProductMix.xls
More Example Models online:
» Six Sigma
» Oil & Gas