Using decision trees

The approaches to risk analysis discussed previously rather assume that we are passive bystanders allowing nature to take its own course - the best we can do is to reject over-risky projects or choose those with the best risk profile. There are many situations, however, where we can evaluate whether a risk is important and. if it is. indicate a suitable course of action.

Many such decisions will limit or affect future options and. at any point, it is important to be able to see into the future to assess how a decision will affect the future profitability of the project.

Prior to giv ing Amanda the job of extending their invoicing system. IOE must consider the alternative of completely replacing the existing system - which they

All three projects have the same expected profitability.

The profitability of project A is unlikely to depart greatly from its expected value (indicated by the vertical axis) compared to the likely variations for project B Project A is therefore less risky than project B

expected profitability profitability

Figure 3.4 A risk analysis profile.

will have to do at some point in the future. The decision largely rests upon the rate at which their equipment maintenance business expands - if their market share significantly increases (which they believe will happen if rumours of a competitor's imminent bankruptcy are fulfilled) the existing system might need to be replaced within 2 years. Not replacing the system in time could be an expensive option as it could lead to lost revenue if they cannot cope with the increase in invoicing demand. Replacing it immediately will, however, be expensive as it will mean deferring other projects that have already been scheduled.

They have calculated that extending the existing system will have an NPV of £57,(XX). although if the market expands significantly, this will be turned into a loss with an NPV of -£I(X).(XX) due to lost revenue. If the market does expand, replacing the system now has an NPV of £250.(XX) due to the benefits of being able to handle increased sales and other benefits such as improved management information. If sales do not increase, however, the benefits will be severely reduced and the project will suffer a loss with an NPV of -£50.(XX).

The company estimate the likelihood of the market increasing significantly at 20ft - and. hence, the probability that it will not increase as 80ft. This scenario can be represented as a tree structure as shown in Figure 3.5.

The analysis of a decision tree consists of evaluating the expected benefit of taking each path from a decision point (denoted by I) in Figure 3.5). The expected value of each path is the sum of the value of each possible outcome multiplied by its probability of occurrence. The expected value of extending the system is therefore £40.000 (75.000 x 0.8 - 100.000 x 0.2) and the expected value of replacing the system £ I O.(XX) (250,000 x 0.2 - 50.000 x 0.8). IOE should therefore choose the option of extending the existing system.

litis example illustrates the use of a decision tree to evaluate a simple decision at the start of a project. One of the great advantages of using decision trees to

Expansion 0.2

Extend

Extend

75.000

250.000

No expansion -50.000

Figure 3.5 A decision tree.

75.000

250.000

No expansion -50.000

model and analyse problems is the ease with which they can be extended. Figure 3.6 illustrates an extended version of Amanda's decision tree, which includes the possibility of a later decision should they decide to extend the system and then find there is an early market expansion.

The net present values shown in italic are those identified in Amanda's original decision tree shown in Figure 3.5.

Furth« expansion

Continue extension

Extend

Replace

Early market expansion

80,000 200.000

-30.000 100.000

Furth« expansion

Continue extension

Extend

Early market expansion

80,000 200.000

-30.000 100.000

Replace

No expansion

-50.000

Figure 3.6 An extension to Amanda's decision tree.

No expansion

-50.000

Figure 3.6 An extension to Amanda's decision tree.

Project Management Made Easy

Project Management Made Easy

What you need to know about… Project Management Made Easy! Project management consists of more than just a large building project and can encompass small projects as well. No matter what the size of your project, you need to have some sort of project management. How you manage your project has everything to do with its outcome.

Get My Free Ebook


Post a comment