Decision tree- System analysis and design
Download as PPTX, PDF1 like3,801 views
This document discusses decision trees, including: - Decision trees present conditions and actions sequentially in a graphical format. Each condition can have multiple possible nodes. - They are useful for expressing logic involving variable values or actions dependent on other decisions. This helps analysts identify the actual decisions to be made. - While decision trees are good for representing a few complex conditional decisions, they can become confusing with too many branches and paths. The lack of additional context in their format is also a limitation.
Decision tree- System analysis and design
- 1. Decision Tree Prof.Nilesh Magar, MIT-WPU
- 2. Decision Tree: • Decision tree is a graphical representation that presents conditions and actions sequentially • It is a method of showing the relationship of each condition & its permissible actions • The route of the tree is starting point and it proceeds towards the various possible nodes • The size of the tree will depend upon the number of conditions & actions • Each condition is expressed in two ways True/False or Yes/No Prof.Nilesh Magar, MIT-WPU
- 3. 1. It expresses the logic of if then else in pictorial form 2. It is useful to express the logic when a value is variable or an action is dependent on nested decision i.e. the outcome of another decision 3. It helps analyst to identify the actual decision to be made 4. It is useful to verify logic and problem that involve a few complex limited number of action Advantages of Decision tree Prof.Nilesh Magar, MIT-WPU
- 4. Disadvantages of Decision tree 1. The lack of decision tree is that there is absence of information in its format to take what other combinations of conditions to test. 2. A large number of branches with many paths will confuse rather than help in analysis. Prof.Nilesh Magar, MIT-WPU
- 5. USES OF DECISION TREE • Decision trees are commonly used in operations research, specifically in decision analysis, to help identify a strategy most likely to reach a goal. • Another use of decision trees is as a descriptive means for calculating conditional probabilities Prof.Nilesh Magar, MIT-WPU
- 6. • Imagine you only ever do four things at the weekend: go shopping, watch a movie, play tennis or just stay in. • What you do depends on three things: the weather (windy, rainy or sunny); how much money you have (rich or poor) and whether your parents are visiting. • You say to your yourself: 1) if my parents are visiting, we'll go to the cinema. 2) If they're not visiting and it's sunny, then I'll play tennis, 3) If it's windy, and I'm rich, then I'll go shopping. 4) If they're not visiting, it's windy and I'm poor, then I will go to the cinema. 5) If they're not visiting and it's rainy, then I'll stay in. EXAMPLE:- Prof.Nilesh Magar, MIT-WPU
- 8. Draw a decision tree for policy followed by a company in giving discount to its customers as follows. 1. If transaction is on credit and customer’s record is good the order will be accepted but do not give any discount. If customer’s record is not good do not accept any order. 2. If transaction is on cash and sells amount is more than 100 rupees discount will be given 20%. 3. If transaction is on cash and sells amount is between 50 & 100 rupees than discount will be given 10%. 4. If transaction is on cash and sells amount is less than 50 rupees, order is accepted but no discount will be made. Example: : Prof.Nilesh Magar, MIT-WPU