代写Data Exploration、代做R程序语言、R代写、代做Visualization

日期：2019-04-08 10:32

USE CASE STUDY REPORT

Group No.: Group XX

Student Names: Student A and Student B

Executive Summary: This should be written when the study has concluded. State the goal of the study, the origin of the data, data processing, and data mining techniques. Summarize the findings and recommendations. Please always use “Times New Roman” font throughout with size14pt for headings and size 12pt for body text. There will be a deduction if report does not follow this template and guidelines. The length of your  report should NOT exceed 15 pages (excluding R code which can be put in Appendix)!

I. Background and Introduction

Provide a brief introduction to the opportunity and significance (why you study the particular use case).

Provide background information to the use case study, including:

The problem

The goal of your study

The possible solution

II. Data Exploration and Visualization

Provide brief description of techniques used to explore the data including: basic charts, distribution plots, correlations, missing values, rescaling, aggregation, hierarchies, zooming, filtering, etc.

III. Data Preparation and Preprocessing

Provide information on data summary, dimension reduction, correlation analysis, PCA analysis, variable converting, variable selection, etc.

IV. Data Mining Techniques and Implementation

You are expected to explore multiple data mining techniques as appropriate to your problem. Clearly state the problem in data mining context (e.g., classification, prediction, supervised/unsupervised learning, etc.). It is desirable to have a flowchart for the entire process from data cleaning/manipulation/variable selection and transformation to specific techniques/algorithms implemented in R.

V. Performance Evaluation

Present performance evaluation for all data mining techniques explored in your study, and select the best approach and explain why it is the best. Please ALWAYS divide your data into training set and validation set, and use validation set to evaluate the performance. If using pruned decision trees, please separate your data set into training, validation, and test. You should use performance measures such as lift chart, ROC curve, confusion matrix, prediction accuracy measures (MAE, Mean Error, MPE, MAPE, RMSE), classification accuracy measures (error rate, accuracy, sensitivity, specificity, false discovery rate, false omission rate, etc.).

VI. Discussion and Recommendation

Provide discussion of the overall approach, including advantages and shortcomings. Based on your results, make recommendations for solution, potential improvement, etc.

VII. Summary

Summarize your use case study.

Appendix: R Code for use case study

Please show the R code you generated for the use case study. Please do not show results here, only the code.