Dirty Data Processing for Machine Learning 1st Edition by Zhixin Qi, Hongzhi Wang, Zejiao Dong ISBN 9789819976560 9819976561

Dirty Data Processing for Machine Learning 1st Edition by Zhixin Qi, Hongzhi Wang, Zejiao Dong – Ebook PDF Instant Download/Delivery: 9789819976560 ,9819976561
Full download Dirty Data Processing for Machine Learning 1st Edition after payment

Product details:

ISBN 10: 9819976561
ISBN 13: 9789819976560
Author: Zhixin Qi, Hongzhi Wang, Zejiao Dong

In both the database and machine learning communities, data quality has become a serious issue which cannot be ignored. In this context, we refer to data with quality problems as “dirty data.” Clearly, for a given data mining or machine learning task, dirty data in both training and test datasets can affect the accuracy of results. Accordingly, this book analyzes the impacts of dirty data and explores effective methods for dirty data processing.
Although existing data cleaning methods improve data quality dramatically, the cleaning costs are still high. If we knew how dirty data affected the accuracy of machine learning models, we could clean data selectively according to the accuracy requirements instead of cleaning all dirty data, which entails substantial costs. However, no book to date has studied the impacts of dirty data on machine learning models in terms of data quality. Filling precisely this gap, the book is intended for a broad audience ranging from researchers inthe database and machine learning communities to industry practitioners.
Readers will find valuable takeaway suggestions on: model selection and data cleaning; incomplete data classification with view-based decision trees; density-based clustering for incomplete data; the feature selection method, which reduces the time costs and guarantees the accuracy of machine learning models; and cost-sensitive decision tree induction approaches under different scenarios. Further, the book opens many promising avenues for the further study of dirty data processing, such as data cleaning on demand, constructing a model to predict dirty-data impacts, and integrating data quality issues into other machine learning models. Readers will be introduced to state-of-the-art dirty data processing techniques, and the latest research advances, while also finding new inspirations in this field.

Dirty Data Processing for Machine Learning 1st Edition Table of contents:

1 Introduction
1.1 Why Dirty Data Processing for Machine Learning?
1.2 Summary of Related Work
1.2.1 Data Cleaning and Noise Reduction
1.2.2 Impacts of Noise
1.2.3 Noise-Robust Models
1.2.4 Cost-Sensitive Decision Tree Induction
1.3 Overview of the Book
References
2 Impacts of Dirty Data on Classification and Clustering Models
2.1 Motivation
2.2 How to Evaluate Dirty-Data Impacts on Classification and Clustering Models?
2.2.1 Data Sets, Models, and Setup
2.2.2 Dimensions of Data Quality
2.2.3 Evaluation Measures
2.3 How Dirty Data Affects Classification and Clustering Models?
2.3.1 Results and Analysis of Classification Models
2.3.1.1 Varying Missing Rate
2.3.1.2 Varying Inconsistent Rate
2.3.1.3 Varying Conflicting Rate
2.3.2 Results and Analysis of Clustering Models
2.3.2.1 Varying Missing Rate
2.3.2.2 Varying Inconsistent Rate
2.3.2.3 Varying Conflicting Rate
2.4 What Do We Learn from Evaluation Results?
2.4.1 Lessons Learned from Evaluation on ClassificationModels
2.4.2 Guidelines of Classification Model Selectionand Data Cleaning
2.4.3 Lessons Learned from Evaluation on Clustering Models
2.4.4 Guidelines of Clustering Model Selectionand Data Cleaning
2.4.5 Suggestions for Future Work
2.5 Summary
References
3 Dirty Data Impacts on Regression Models
3.1 Motivation
3.2 How to Evaluate Dirty Data Impacts on Regression Models?
3.3 How Dirty Data Affects Regression Models?
3.3.1 Data Sets, Models, and Setup
3.3.2 Varying Missing Rate
3.3.3 Varying Inconsistent Rate
3.3.4 Varying Conflicting Rate
3.3.5 Lessons Learned
3.4 Summary
References
4 Incomplete Data Classification with View-Based Decision Tree
4.1 Motivation
4.2 How to Organize Tree-Structured Views?
4.3 How to Select Views?
4.4 Evaluation of Incomplete Data Classification with View-Based Decision Tree
4.4.1 Comparison Experiments
4.4.2 Influence of Parameters
4.5 Summary
References
5 Density-Based Clustering for Incomplete Data
5.1 Motivation
5.2 Background Knowledge
5.2.1 Definitions in DBSCAN
5.2.2 DBSCAN Algorithm
5.2.2.1 Eps-Neighborhood Searching
5.2.2.2 Cluster Searching
5.3 Approach of Concurrently Imputation Clustering
5.3.1 Method Design
5.3.2 Algorithm Description
5.4 Approach of Local Imputation Clustering
5.4.1 Problem Definition
5.4.2 Method Design
5.4.3 Algorithm Description
5.5 Evaluation of Density-Based Clustering for Incomplete Data
5.5.1 Experimental Setup
5.5.2 Evaluation Results
5.6 Summary
References
6 Feature Selection on Inconsistent Data
6.1 Motivation
6.2 Background Knowledge
6.2.1 Mutual Information
6.2.2 Consistency Rules
6.3 How to Select Features on Inconsistent Data?
6.3.1 Problem Definition
6.3.2 Our Solution
6.4 Evaluation of Feature Selection on Inconsistent Data
6.4.1 Experimental Setup
6.4.2 Efficiency of FRIEND
6.4.3 Accuracy of Machine Learning Models
6.4.4 Parameters of SFS Algorithm
6.5 Summary
References
7 Cost-Sensitive Decision Tree Induction on Dirty Data
7.1 Motivation
7.2 How to Define the Problem of Cost-Sensitive Decision Tree Induction on Dirty Data?
7.2.1 Decision Trees
7.2.2 Misclassification Cost and Testing Cost
7.2.3 Detection Cost and Repair Cost
7.2.4 Cost-Sensitive Decision Tree Building Problem on Poor Quality Data
7.3 Cost-Sensitive Decision Tree Induction Methods Integrated with Data Cleaning Algorithms
7.3.1 Cost-Sensitive Decision Tree Building Method Incorporating Stepwise Cleaning Algorithm Based on Split Attribute Gain
7.3.2 Cost-Sensitive Decision Tree Building Method Incorporating One-time Cleaning Algorithm Based on Split Attribute Gain and Cleaning Cost
7.3.3 Cost-Sensitive Decision Tree Building Method Incorporating Stepwise Cleaning Algorithm Based on Split Attribute Gain and Cleaning Cost
7.3.4 Applicability Discussion and Time ComplexityComparison
7.4 Evaluation of Cost-Sensitive Decision Tree Induction on Dirty Data
7.4.1 Total Cost Incurred by the Classification Task
7.4.2 Accuracy of Classification Tasks
7.4.3 Efficiency of Classification Tasks
7.5 Summary

People also search for Dirty Data Processing for Machine Learning 1st Edition:

    
machine learning data quality checks
    
machine learning data quality assessment
    
dirty data problems in r
    
is data mining machine learning
    
udacity machine learning course

Tags: Zhixin Qi, Hongzhi Wang, Zejiao Dong, Dirty Data Processing, Machine Learning