Ask a question from expert

Ask now

BUS5PA - Predictive Analytics Assignment

25 Pages3024 Words434 Views
   

La Trobe University

   

Predictive Analytics (BUS5PA)

   

Added on  2020-02-24

About This Document

The below document discusses the Building and Evaluating Predictive Models. The various concepts which have been discussed related to the above-mentioned topic are as Decision tree based modeling and analysis,  and Regression based modeling and analysis.

BUS5PA - Predictive Analytics Assignment

   

La Trobe University

   

Predictive Analytics (BUS5PA)

   Added on 2020-02-24

BookmarkShareRelated Documents
Building and Evaluating Predictive ModelsAssignment 1 (BUS5PA Predictive Analytics – Semester 2, 2017)By<Student Name>(18752031) La Trobe Business School Australia
BUS5PA - Predictive Analytics  Assignment_1
Table of Contents1.Setting up the project and exploratory analysis12.Decision tree based modeling and analysis23.Regression based modeling and analysis34.Open ended discussion55.Extending current knowledge with additional reading6References8Appendixi
BUS5PA - Predictive Analytics  Assignment_2
List of FiguresFig. 1 Creation of project: BUS5PA_Assignment1_18752031......................................................................................iFig. 2 Creation of Library................................................................................................................................................iFig. 3 Organics data source............................................................................................................................................iiFig. 4 Roles of variables.................................................................................................................................................iiFig. 5 Distribution of Organics purchase indicator.......................................................................................................iiiFig. 6 Organics data source in Organics diagram workspace........................................................................................iiiFig. 7 Addition of Data partition...................................................................................................................................ivFig. 8 Data set Allocations.............................................................................................................................................ivFig. 9 Data set Allocations.............................................................................................................................................ivFig. 10 Interactive method has not been selected..........................................................................................................ivFig. 11 Use average square error as Assessment measure..............................................................................................vFig. 12 Subtree Assessment Plot.....................................................................................................................................vFig. 13 Decision Tree Model.........................................................................................................................................viFig. 14 Decision Tree after adding Tree 2.....................................................................................................................viFig. 15 Three-way Split.................................................................................................................................................viFig. 16 Assessment Measure for Decision Tree 2.........................................................................................................viFig. 17 Average square error for the model with Tree 2..............................................................................................viiFig. 18 StatExplore tool with ORGANICS data source...............................................................................................vii
BUS5PA - Predictive Analytics  Assignment_3
Fig. 19 Default input method of class and interval variables......................................................................................viiiFig. 20 Imputation indicators for all imputed inputs...................................................................................................viiiFig. 21 Addition of Regression node...........................................................................................................................viiiFig. 22 Model Selection.................................................................................................................................................ixFig. 23 Regression Result..............................................................................................................................................ixFig. 24 Summary of Stepwise Selection.........................................................................................................................xFig. 25 Odd ratio Estimates............................................................................................................................................xFig. 26 Average squared error (ASE)............................................................................................................................xiFig. 27 Model Comparison Process...............................................................................................................................xiFig. 28 Model Comparison Result................................................................................................................................xiiFig. 29 ROC Chart........................................................................................................................................................xiiFig. 30 Cumulative Lift...............................................................................................................................................xiiiFig. 31 Fit Statistics.....................................................................................................................................................xiiiList of TablesTable 1 Model performance comparison5
BUS5PA - Predictive Analytics  Assignment_4
1.Setting up the project and exploratory analysisa)A new project has been created, named BUS5PA_Assignment1_18752031, this has beenshown in Fig. 1.a.1)SAS Library, has been created named Project, and data source has been created using SASdataset ORGANICS which has been shown it Fig. 2 and Fig. 3.a.2)As mentioned in the business case assignment, roles have been set for the analysisvariables., all the roles have also been defined for the data source ORGANICS, which hasbeen shown in Fig. 4.a.3)TargetBuy” has been defined as target variable. In percentage terms, 24.77% individualshave purchased organic products and rest i.e.75.23% have not purchased organic products.Percentage distribution has been shown in Fig. 5.a.4)Demcluster has been set rejected, which has been shown in Fig. 4.a.5)In Fig. 3, data source named ORGANICS has been defined.a.6)In Fig. 6, it has been shown that ORGANICS data source has been added to Organicsdiagram workspace.b)TargetAmt can never be used as the predictor of TargetBuy. The individuals have purchasedthe organic item or not, that is indicated by TargetBuy, whereas TargetAmt indicates thenumber of organic amounts bought. TargetAmt will only be recorded when Targetbuy is Yesi.e. for those who have purchased any organic products. Hence, in this model, to predictTargetBuy, TargetAmt cannot be used as an input. The objective of supermarket’s is todevelop a loyalty model by understanding whether customers have purchased any of theorganic products. So, TargetBuy is the perfectly appropriate as target variable.-1-
BUS5PA - Predictive Analytics  Assignment_5
2.Decision tree based modeling and analysisa)From Sample Tab, data partition node has been added to the diagram and it has beenconnected to the data source node (ORGANICS). As mentioned in the assignment, 50% ofthe data for training and 50% for validation have been assigned (Fig. 7 and Fig. 8.)b)In Fig. 9, it has been shown that the Decision Tree node has been added to the workspace andit has been connected to the Data partition node.c)Decision Tree model has been created autonomously, and sub tree model assessment criteriahas been chosen by using average square error which has been depicted in Fig. 10 and 11.c.1)Using average square error method, there are 29 leaves in the optimal tree, which has beenshown in Fig. 12.c.2)For the first split, age variable has been used. It has divided the training data in two parts,first subset was for the age less than 44.5. In this subset, TargetBuy = 1 has higher thanaverage concentration. Second subset is for age greater than or equals to 44.5, In this subset,TargetBuy = 0 has higher than average concentration. Using average square error assessment,Decision Tree model has been created autonomously, which has been shown in Fig. 13.d)Second Decision Tree node has been added to the diagram, and it has been connected to theData Partition node, which has been depicted in Fig. 14. d.1)In the Properties panel of the new Decision Tree node, maximum number of branches havebeen set to 3 to allow three-way splits, which has been shown in Fig. 15.d.2)Decision tree model has been created using average square error, which has been depictedin Fig. 16.-2-
BUS5PA - Predictive Analytics  Assignment_6

End of preview

Want to access all the pages? Upload your documents or become a member.

Related Documents
BUS5PA: Building and Evaluating Predictive Models | Assignment
|25
|2918
|37

BUS5PA - Predictive Analytics- Assignment
|31
|3683
|461

BUS5PA : Assignment on Predictive Analytics
|27
|3467
|420

BUS5PA Predictive Analysis: Building and Evaluating Predictive Models Using SAS Enterprise Miner Assignment 2
|25
|4729
|392

Implementation of Healthcare Information System: Management Issues and Recommendations
|64
|20042
|415

Carbon Neutrality and NEPIs
|55
|14178
|404