Resources
This model uses NeuralTools to classify a large number of email messages as spam or not spam, based on a large number of characteristics of the messages. It also uses the Variable Impact tool in NeuralTools to screen for predictors that might not be useful.
This oil drilling example is a classic decision tree problem, it demonstrates the use of PrecisionTree to analyze a multi-stage decision process. 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 Ð the decision to test is always made before the decision to drill.
You will find five versions of this model:
1. Oil Drilling
2. Oil Drilling with Formulas
3. Oil Drilling Influence Diagram
4. Oil Drilling with Linked Trees
5. Oil Drilling using @RISK
Two versions of a model which illustrates the daily output of a combination of solar and wind energy units.
1. The @RISK outputs include hourly and total daily output values for solar, wind, and combined solar and wind.
2. Extends the model above to use RISKOptimizer to find the best combination of solar and wind units to match energy uncertain demands for a 100-day period.
This model is based on Roy L. Nersesian's book Energy Risk Modeling.
A gold mining project is divided into five separate mines, each with unique geological characteristics and cost variables. These variables (input costs, declination rates, plateau length, etc.) are all uncertain, and the price of gold is also uncertain. What is the optimal strategy for maximizing the project profits, given so many unknown variables and possible strategies?
RISKOptimizer is used to optimize this problem to determine when, and in what order, each of the mines should be exploited.
A manufacturer of fuel efficient cars believes that demand for this type of cars might increase in the next few years, so it wants to expand its capacity. To finance this, the company plans to divert profits from car sales to a fund for eventual expansion. The model uses RISKOptimizer to find an optimal plan for doing this
This model illustrates a portfolio optimization model which uses detailed financial calculations on a number of project worksheets to obtain project NPVs and present values of project costs. The goal is to select the projects for the portfolio that maximize the mean portfolio NPV, but to ensure with 95% confidence that the total present value of costs stays below the budget of $1.5 million.
Two examples files to illustrate the "conditional value at risk" concept from finance.
1. A model to illustrate how to find the VaR and the CVaR for a portfolio of correlated investments.
2. A new version of the model above using RISKOptimizer to maximize the CVaR by choosing the portfolio weights appropriately. In other words, it is used to make the "bad" conditional mean as least bad as possible.
This model illustrates the newsvendor ordering model in a multiple-product setting with the possibility of demand diversion. This means that if supply of product A, say, is not sufficient to satisfy demand for product A, some customers (but not all of them) who wanted product A but couldn't get it are willing to purchase another product instead.
An optimization model for deciding which of sequential house offers to accept.
A set of @RISK example models for E-Commerce Service.
1. A deterministic model to get started.
2. A basic @RISK model with demand uncertainty.
3. A version with demand uncertainty and uncertainty in price and cost.
4. A version that illustrates the RiskSimtable function for different values of the capacity decision variable.
5. A version that illustrates @RISK's Goal Seek feature for forcing mean profit to a specified value.
6. A model for finding the capacity in an e-commerce system that maximizes the 10th percentile of profit.
Click here to see a video of this example.
An optimization model for deciding how to invest over a multi-year horizon to achieve a retirement goal.
An optimization model for determining how to invest over a time horizon to accumulate a down payment for a house.
