Applied Data Mining for Forecasting Using SAS. Tim Rey

Applied Data Mining for Forecasting Using SAS - Tim Rey


Скачать книгу

       3.3.1 Data Collection Software

       3.3.2 Data Preparation Software

       3.3.3 Data Mining Software

       3.3.4 Forecasting Software

       3.3.5 Software Selection Criteria

       3.4 Data Infrastructure

       3.4.1 Internal Data Infrastructure

       3.4.2 External Data Infrastructure

       3.5 Organizational Infrastructure

       3.5.1 Developers Infrastructure

       3.5.2 Users Infrastructure

       3.5.3 Work Process Implementation

       3.5.4 Integration with IT

       Chapter 4 Issues with Data Mining for Forecasting Application

       4.1 Introduction

       4.2 Technical Issues

       4.2.1 Data Quality Issues

       4.2.2 Data Mining Methods Limitations

       4.2.3 Forecasting Methods Limitations

       4.3 Nontechnical Issues

       4.3.1 Managing Forecasting Expectations

       4.3.2 Handling Politics of Forecasting

       4.3.3 Avoiding Bad Practices

       4.3.4 Forecasting Aphorisms

       4.4 Checklist “Are We Ready?”

       Chapter 5 Data Collection

       5.1 Introduction

       5.2 System Structure and Data Identification

       5.2.1 Mind-Mapping

       5.2.2 System Structure Knowledge Acquisition

       5.2.3 Data Structure Identification

       5.3 Data Definition

       5.3.1 Data Sources

       5.3.2 Metadata

       5.4 Data Extraction

       5.4.1 Internal Data Extraction

       5.4.2 External Data Extraction

       5.5 Data Alignment

       5.5.1 Data Alignment to a Business Structure

       5.5.2 Data Alignment to Time

       5.6 Data Collection Automation for Model Deployment

       5.6.1 Differences between Data Collection for Model Development and Deployment

       5.6.2 Data Collection Automation for Model Deployment

       Chapter 6 Data Preparation

       6.1 Overview

       6.2 Transactional Data Versus Time Series Data

       6.3 Matching Frequencies

       6.3.1 Contracting

       6.3.2 Expanding

       6.4 Merging

       6.5 Imputation

       6.6 Outliers

       6.7 Transformations

       6.8 Summary

       Chapter 7 A Practitioner's Guide of DMM Methods for Forecasting

       7.1 Overview

       7.2 Methods for Variable Reduction

       Traditional Data Mining

       Time Series Approach

       7.3 Methods for Variable Selection

       Traditional Data Mining

       Example for Variable Selection

       Variable Selection Based on Pearson Product-Moment Correlation Coefficient

       Variable Selection Based on Stepwise Regression

       Variable Selection Based on the SAS Enterprise Miner Variable Selection Node

       Variable Selection Based on the SAS Enterprise Miner Partial Least Squares Node

       Variable Selection Based on Decision Trees

       Variable Selection Based on Genetic Programming

       Comparison of Data Mining Variable Selection Results

       7.4 Time Series Approach

       7.5 Summary

       Chapter 8 Model Building: ARMA Models

       Introduction

       8.1 ARMA Models

       8.1.1 AR Models: Concepts and Application

       8.1.2 Moving Average Models: Concepts and Application

       8.1.3 Auto Regressive Moving Average (ARMA) Models

       Appendix 1: Useful Technical Details

       Appendix 2: The “I” in ARIMA

       Chapter 9 Model Building: ARIMAX or Dynamic Regression Modes

       Introduction

       9.1 ARIMAX Concepts

       9.2 ARIMAX Applications

       Appendix: Prewhitening and Other Topics Associated with Interval-Valued Input Variables

       Chapter 10 Model Building: Further Modeling Topics

       Introduction

       10.1 Creating Time Series Data and Data Hierarchies Using Accumulation and Aggregation Methods

       Introduction


Скачать книгу