Page 211 - Ai_417_V3.0_C9_Flipbook
P. 211

Let us understand about decision trees with the help of an example, where you need to identify the person is male
                 or female based on the height, weight, and foot size.

                                                        height > 5.9

                                                    Yes            No



                                             Male                      weight <= 150

                                                                    No              Yes


                                                       foot size >= 10                  Female


                                                    Yes            No


                                               Male                    Female


                 Following are some of the important points to consider while designing a decision tree:
                    • There can be a possibility of multiple decision trees that lead to correct prediction for a single dataset. The
                   simplest one should be chosen.
                    • The dataset might contain redundant data at times, which does not have any reference while creating a decision
                   tree. Therefore, only those parameters that affect the output directly must be included.
                    • While making decision trees, one should take a look at the dataset given to them and try to figure out what
                   pattern the output leaf follows. Try selecting any one output and on its basis, find out the common links that all
                   the similar outputs have.



                                 Task                                                #Experiential Learning


                     1.   The following is a dataset comprising 4 parameters which lead to the prediction of a student choosing
                        a Science stream in senior secondary school. Make a decision tree for this dataset:
                           Aptitude     Logical Skills  Analytical Skills  Reasoning    Stream Selection: Science
                             High           High             High             High                 Yes
                             High           Low               Low             Low                  No
                              Low           High             High             High                 Yes
                              Low           Low               Low             High                 No
                              Low           High             High             Low                  No

                     2.  Make a decision tree to choose a book from the library based on the following selections.
                        Choice 1: Fiction—Sci-Fi, Mystery, Classics.
                        Choice 2: No Fiction—Travel Diaries, Autobiographies, History, Travelogues.
                     3.   Using the given data, create a Decision Tree to help spot the elephant! Classify the animals based on
                        the following characteristics:
                        Choice 1: Large size and long trunk.

                        Choice 2: Not large size and no trunk.
                        Collaborate in your groups and present your Decision Trees!


                                                                         AI Reflection, Project Cycle and Ethics  209
   206   207   208   209   210   211   212   213   214   215   216