e) A retailer wants for marketing purposes distinguish between costumers younger than 35 and customers older...

 

Transcribed Image Text:

e) A retailer wants for marketing purposes distinguish between costumers younger than 35 and customers older than 35. The following table summarizes the data set in the database of the retailer in an abstract form. The relevant attributes, determined by domain knowledge, are for convenience denoted by A, B and C. The values for A are al, a2 and a3. The values for B are b1 and b2. The values for Care c1 and c2. Assume that the retailer wants to use Decision Trees to classify the costumers in the class "young", denoted by Y, and "old", denoted by O. i) Compute the Classification error for the A attribute. ii) According to the Classification error, which attribute would be chosen as the first splitting attribute? For each attribute, show the contingency table and the corresponding Classification error. iii) Draw the resulting Decision Tree of depth 1, based on your outcome of Part ii. iv) Repeat Part ii for the children of the root node, i.e. the nodes on level 1. A B C al bl cl a2 bl cl a3 bl cl al b2 cl a2 b2 cl a3 b2 cl al bl c2 a2 bl c2 a3 bl c2 al b2 c2 a2 b2 c2 a3 b2 c2 Number of Instances Y 14 O 6 0 6 0 0 NONOO 8 2 2 4 O 4 2 12 4 6 8 O O 4 2 O Figure 5: Marketing data set e) A retailer wants for marketing purposes distinguish between costumers younger than 35 and customers older than 35. The following table summarizes the data set in the database of the retailer in an abstract form. The relevant attributes, determined by domain knowledge, are for convenience denoted by A, B and C. The values for A are al, a2 and a3. The values for B are b1 and b2. The values for Care c1 and c2. Assume that the retailer wants to use Decision Trees to classify the costumers in the class "young", denoted by Y, and "old", denoted by O. i) Compute the Classification error for the A attribute. ii) According to the Classification error, which attribute would be chosen as the first splitting attribute? For each attribute, show the contingency table and the corresponding Classification error. iii) Draw the resulting Decision Tree of depth 1, based on your outcome of Part ii. iv) Repeat Part ii for the children of the root node, i.e. the nodes on level 1. A B C al bl cl a2 bl cl a3 bl cl al b2 cl a2 b2 cl a3 b2 cl al bl c2 a2 bl c2 a3 bl c2 al b2 c2 a2 b2 c2 a3 b2 c2 Number of Instances Y 14 O 6 0 6 0 0 NONOO 8 2 2 4 O 4 2 12 4 6 8 O O 4 2 O Figure 5: Marketing data set

Answer rating: 100% (QA)

i Computing the Classification error ... View the full answer