Data Mining and data-based operation practices: ideas, methods, skills and Applications

Author of basic information of "Data Mining and data-based operation practice: ideas, methods, skills and Applications": luhui series name: Big Data Technology series Press: Machinery Industry Press ISBN: 9787111426509 Release Date: 276-6-4 published on: July 4,: 16 webpage: 1-1: more about computers: Data Mining and data-based operation practices: overview of ideas, methods, techniques, and applications: Data Mining and data-based operations: ideas, methods, techniques, and applications is a comprehensive and systematic work on data mining in the field of data operation practice, it is also one of the few books on Data Mining that are interspersed with a large number of real practical application cases and scenarios. It is also creative in targeting different types of analysis and mining topics in data-driven operations, A one-to-one collection of corresponding analysis ideas and corresponding analysis skills will be introduced to provide readers with the Book of practical tips for "Menu customization. Based on a large amount of project experience in data-driven operation practices, the author uses easy-to-understand non-technical languages and a large number of lively and vivid cases to focus on the ideas, methods, techniques, and applications of data analysis and mining, it comprehensively organizes, summarizes, and shares data to help readers deeply understand and master the data mining practices and application book "focusing on business, focusing on ideas, and assisting with analysis technology. Chapter 19 Data Mining and data-based operation practices: ideas, methods, skills, and applications is divided into three parts: BASICS (1st ~ Chapter 4) systematically introduces the background of data analysis and mining and data operation, the core of "coordination and cooperation" in data operation, and common analysis project types in practice ~ Chapter 13) describes the practical skills of common analysis and Mining Techniques in practice, and shares and displays a large number of practical cases throughout the process. Chapter 13: Ideology ~ Chapter 19) summarizes and explores the responsibility, consciousness, and thinking training and improvement of data analysts, as well as some effective project quality control systems and classic methodologies. Directory "Data Mining and data-based operation practices: ideas, methods, skills and Applications" recommendation preface chapter 1st what is data-based operation 1.1 Development History of Modern Marketing Theory 1.1.1 from 4p to 4C1. 1.2 from 4c to 3p3c1. 2. Data-driven operations 1.3 why data-driven operations 1.4 prerequisites for data-driven operations 1.4.1 enterprise-level massive data storage implementation 1.4.2 requirements for refined operations 1.4.3 effective application of data analysis and data mining technologies 1.4.4 advocacy and continuous support of enterprise decision-making layer new phenomena and new developments of 1.5 data-driven operations 1.6 latest data on Internet and e-commerce Chapter 1 Data Mining overview 2nd development history of Data Mining 2.1 Statistical analysis and data main differences of Data Mining 2.3 mature data mining technologies and their main applications in data-driven operations. 2.3.1 decision tree 2.3.2 Neural Network 2.3.3 regression 2.3.4 association rule 2.3.5 clustering 2.3.6 Bayesian classification method 2.3.7 Support Vector Machine 2.3.8 Principal Component Analysis 2.3.9 hypothesis test 2.4 characteristics of data mining applications in the Internet industry chapter 3rd data operation is common data analysis project type 3.1 feature analysis of target customers 3.2 prediction of target customers (response and classification) model 3.3 activity of operation groups Definition 3.4 User path analysis 3.5 cross-sales model 3.6 Information Quality Model 3.7 service guarantee model 3.8 user (buyer, seller) Hierarchical Model 3.9 seller (buyer) transaction Model 3.10 Credit Risk Model 3.11 commodity recommendation model 3.11.1 commodity recommendation introduction 3.11.2 association rule 3.11.3 collaborative filtering algorithm 3.11.4 commodity recommendation model summary 3.12 data product 3.13 decision support chapter 4th data-based operation is cross-disciplinary and cross-region team Coordination and Cooperation 4.1 division of labor between the data analysis team and the business team and positioning 4.1.1 propose business analysis requirements and be competent for basic data analysis 4.1.2 provide business experience and reference suggestions 4.1.3 plan and implement refinement operation solution 4.1.4 tracking operation results, feedback and summary 4.2 data-based operation is truly multi-team and multi-professional collaboration 4.3 Examples demonstrate cross-professional and cross-team coordination and cooperation in data-driven operations chapter 2 common analysts incorrect ideas and Governance Management Strategies 5.1 despise business theory 5.2 technology theory 5.3 technology cutting-edge theory 5.4 modeling and Application 2 segment theory 5.5 machine universal theory 5.6 happy families are similar, unfortunately, each family has its own misfortune. Chapter 1 data mining project full application case demonstration 6th project background and business analysis requirement proposal 6.1 data analysts participate in demand discussion 6.2 requirement analysis framework and analysis Plan 6.3 sample Data Extraction, familiarity with data, data cleansing, and bottom-up 6.5 initial construction of the Mining Model as planned 6.6 preliminary conclusion of the model discussed with the business side, propose new ideas and model optimization solutions. 6.7 extract samples and model again based on the optimization solution, extract conclusions and verify model 6.8 complete analysis report and implementation application suggestions 6.9 formulate specific implementation application solutions and evaluation solutions 6.10 business parties implement implementation application solutions and track and evaluate results 6.11 landing application solutions after the actual effect is evaluated, continuously revise and improve 6.12 evaluation, summary and feedback of different operation schemes 6.13 summary and reflection after project application chapter 1 Optimization of Data Mining modeling and limit 7th Optimization of data mining models should follow effective and, moderate principle 7.2 how to effectively optimize the model 7.2.1 optimizing the business thinking 7.2.2 optimizing the modeling technical thinking 7.2.3 optimizing the modeling technical skills 7.3 how to think about the optimization limit 7.4 model Effects evaluation main indicator system 7.4.1 Evaluation Model Accuracy and accuracy series indicators 7.4.2 ROC curve 7.4.3 Ks value 7.4.4 lift value 7.4.5 Model Stability Evaluation Chapter 2 common data processing techniques 8th data extraction should be correct reflecting business needs 8.2 Data Sampling 8.3 what are the specific requirements for data analysis 8.4 how to deal with missing values and abnormal values 8.4.1 common handling methods for missing values 8.4.2 how to judge and process abnormal values 8.5 data conversion 8.5.1 generate derivative variable 8.5.2 improve variable distribution transformation 8.5.3 binning conversion 8.5.4 data standardization 8.6 filter valid input variable 8.6.1 why filter valid input variable 8.6.2 first filter 8.6.3 use linear correlation index preliminary screening 8.6.4 R square 8.6.5 chi-square test 8.6.6 IV and woe8.6.7 filtering functions of some modeling algorithms 8.6.8 Dimensionality Reduction Method 8.6.9 final criterion 8.7 collinearity problem 8.7.1 how to find collinearity 8.7.2 how to deal with typical application and technical tips of cluster analysis chapter 9th typical application scenarios of cluster analysis chapter 9.1 classification of main clustering algorithms 9.2.1 classification method 9.2.2 hierarchical method 9.2.3 density-Based Method 9.2.4 grid-Based Method 9.3 key notes for Cluster Analysis in practical applications 9.3.1 how to handle data noise and outliers 9.3.2 data standardization 9.3.3 how to reduce cluster variables and refine 9.4 extended application of cluster analysis 9.4.1 core metrics of clustering complement non-clustering business indicators 9.4.2 data exploration and cleaning tools 9.4.3 application of Personalized recommendations 9.5 Advantages and Disadvantages of cluster analysis in practical application 9.6 evaluation system and evaluation indicators of cluster analysis results 9.6.1 business expert Evaluation 9.6.2 clustering technical evaluation indicators 9.7 case studies on a typical clustering analysis subject 9.7.1 case studies 9.7.2 basic data analysis 9.7.3 preliminary conclusions of user sample-based clustering analysis Chapter 10th prediction response (classification) typical application and technology tips 10.1 Neural Network Technology Practices and precautions 10.1.1 Neural Network principles and core elements 10.1.2 advantages of neural network application 10.1.3 disadvantages and precautions of Neural Network Technology 10.2 practical application and precautions of decision tree technology 10.2.1 principles and core elements of decision tree 10.2.2 chaid algorithm 10.2.3 cart algorithm 10.2.4 ID3 algorithm 10.2.5 Application Advantages of decision tree 10.2.6 disadvantages and precautions of decision tree 10.3 logical Regression technical Practice and precautions 10.3.1 principles of Logistic regression and core elements 10.3.2 variable screening methods in regression 10.3.3 advantages of Logistic Regression 10.3.4 considerations in logistic regression 10.4 practical applications and precautions 10.4.1 principles and core elements of linear regression 10.4.2 advantages of linear regression 10.4.3 considerations in Linear Regression applications 10.5 over-fitting models and Countermeasures 10.6 A typical predictive Response Model case studies: 10.6.1 case studies: 10.6.2 basic data basics: 10.6.3 modeling data extraction and cleaning 10.6.4 preliminary correlation tests and a total of linear troubleshooting 10.6.5 distribution of potential independent variables conversion 10.6.6 screening of independent variables 10.6.7 Response Model constructing and optimizing the 10.6.8 champion model determination and main analysis conclusions 10.6.9 operating scheme based on the model and analysis conclusions 10.6.10 model implementation application results tracking feedback Chapter 1 typical application of user feature analysis and technical tips 11.1 typical business scenarios applicable to user Feature Analysis 11.1.1 find target users 11.1.2 find operational starting points