Successfully reported this slideshow.

Data mining

1,210 views

Published on

  • Be the first to comment

Data mining

  1. 1. Ahmed Moussa 30-Feb-2010
  2. 2. What is Data Mining?
  3. 3. The Evolution of Data Analysis
  4. 4. Enabling Product Evolutionary Step Business Question Characteristics Technologies Providers "What was my total Computers, tapes, Retrospective, static data Data Collection (1960s) revenue in the last IBM, CDC disks delivery five years?" Relational databases Oracle, Sybase, Retrospective, dynamic "What were unit sold (RDBMS), Data Access (1980s) Informix, IBM, data delivery at record last March?" Structured Query Microsoft level Language (SQL), ODBC On-line analytic "What were unit processing (OLAP), SPSS, Comshare, Retrospective, dynamic Data Warehousing & Decision sales in last March? multidimensional Arbor, Cognos, data delivery at multiple Support (1990s) Drill down to databases, data Microstrategy,NCR levels Other." warehouses Advanced SPSS/Clementine, "What’s likely to algorithms, Lockheed, IBM, Prospective, proactive Data Mining (Emerging Today) happen to unit sales multiprocessor SGI, SAS, NCR, information delivery next month? Why?" computers, massive Oracle, numerous databases startups - RDBMS: A relational database management system - - ODBC: Open Database Connectivity (ODBC) provides a standard software API method for using database management systems (DBMS). - OLAP : Online analytical processing, is an approach to quickly answer multi-dimensional analytical queries. - SPSS: Statistical Package for the Social Sciences (formerly SPSS) is a computer program used for statistical analysis. Before 2009 it was called SPSS, but in 2009 it was re- branded as PASW.
  5. 5. Results of Data Mining Include
  6. 6. Results of Data Mining Include • Forecasting what may happen in the future • Classifying people or things into groups by recognizing patterns. • Clustering people or things into groups based on their attributes. • Associating what events are likely to occur together. • Sequencing what events are likely to lead to later events.
  7. 7. Results of Data Mining Include • Forecasting what may happen in the future • Classifying people or things into groups by recognizing patterns. • Clustering people or things into groups based on their attributes. • Associating what events are likely to occur together. • Sequencing what events are likely to lead to later events.
  8. 8. Results of Data Mining Include • Forecasting what may happen in the future • Classifying people or things into groups by recognizing patterns. • Clustering people or things into groups based on their attributes. • Associating what events are likely to occur together. • Sequencing what events are likely to lead to later events.
  9. 9. Results of Data Mining Include • Forecasting what may happen in the future • Classifying people or things into groups by recognizing patterns. • Clustering people or things into groups based on their attributes. • Associating what events are likely to occur together. • Sequencing what events are likely to lead to later events.
  10. 10. Results of Data Mining Include • Forecasting what may happen in the future • Classifying people or things into groups by recognizing patterns. • Clustering people or things into groups based on their attributes. • Associating what events are likely to occur together. • Sequencing what events are likely to lead to later events.
  11. 11. Data mining is not • Crunching of bulk data • “Blind” application of algorithms • Going to find relationships where none exist • Presenting data in different ways • A database intensive task • A difficult to understand technology requiring an advanced degree in computer science
  12. 12. Data Mining Is • A class of techniques that find patterns in data. • A user-centric, interactive process which leverages analysis technologies and computing power. • A group of techniques that find relationships that have not previously been discovered. • Not reliant on an existing database. • A relatively easy task that requires knowledge of the business problem/subject matter expertise.
  13. 13. Data Mining Is • A class of techniques that find patterns in data. • A user-centric, interactive process which leverages analysis technologies and computing power. • A group of techniques that find relationships that have not previously been discovered. • Not reliant on an existing database. • A relatively easy task that requires knowledge of the business problem/subject matter expertise.
  14. 14. Data Mining Is • A class of techniques that find patterns in data. • A user-centric, interactive process which leverages analysis technologies and computing power. • A group of techniques that find relationships that have not previously been discovered. • Not reliant on an existing database. • A relatively easy task that requires knowledge of the business problem/subject matter expertise.
  15. 15. Data Mining Is • A class of techniques that find patterns in data. • A user-centric, interactive process which leverages analysis technologies and computing power. • A group of techniques that find relationships that have not previously been discovered. • Not reliant on an existing database. • A relatively easy task that requires knowledge of the business problem/subject matter expertise.
  16. 16. Data Mining Is • A class of techniques that find patterns in data. • A user-centric, interactive process which leverages analysis technologies and computing power. • A group of techniques that find relationships that have not previously been discovered. • Not reliant on an existing database. • A relatively easy task that requires knowledge of the business problem/subject matter expertise.
  17. 17. Examples of What People are Doing with Data Mining: • Fraud/Non-Compliance Anomaly detection • Isolate the factors that lead to fraud, waste and abuse • Target auditing and investigative efforts more effectively • Credit/Risk Scoring • Intrusion detection • Parts failure prediction • Recruiting/Attracting customers • Maximizing profitability (cross selling, identifying profitable customers) • Service Delivery and Customer Retention • Build profiles of customers likely to use which services
  18. 18. Examples of What People are Doing with Data Mining: • Fraud/Non-Compliance Anomaly detection • Isolate the factors that lead to fraud, waste and abuse • Target auditing and investigative efforts more effectively • Credit/Risk Scoring • Intrusion detection • Parts failure prediction • Recruiting/Attracting customers • Maximizing profitability (cross selling, identifying profitable customers) • Service Delivery and Customer Retention • Build profiles of customers likely to use which services
  19. 19. Examples of What People are Doing with Data Mining: • Fraud/Non-Compliance Anomaly detection • Isolate the factors that lead to fraud, waste and abuse • Target auditing and investigative efforts more effectively • Credit/Risk Scoring • Intrusion detection • Parts failure prediction • Recruiting/Attracting customers • Maximizing profitability (cross selling, identifying profitable customers) • Service Delivery and Customer Retention • Build profiles of customers likely to use which services
  20. 20. Examples of What People are Doing with Data Mining: • Fraud/Non-Compliance Anomaly detection • Isolate the factors that lead to fraud, waste and abuse • Target auditing and investigative efforts more effectively • Credit/Risk Scoring • Intrusion detection • Parts failure prediction • Recruiting/Attracting customers • Maximizing profitability (cross selling, identifying profitable customers) • Service Delivery and Customer Retention • Build profiles of customers likely to use which services
  21. 21. Examples of What People are Doing with Data Mining: • Fraud/Non-Compliance Anomaly detection • Isolate the factors that lead to fraud, waste and abuse • Target auditing and investigative efforts more effectively • Credit/Risk Scoring • Intrusion detection • Parts failure prediction • Recruiting/Attracting customers • Maximizing profitability (cross selling, identifying profitable customers) • Service Delivery and Customer Retention • Build profiles of customers likely to use which services
  22. 22. Examples of What People are Doing with Data Mining: • Fraud/Non-Compliance Anomaly detection • Isolate the factors that lead to fraud, waste and abuse • Target auditing and investigative efforts more effectively • Credit/Risk Scoring • Intrusion detection • Parts failure prediction • Recruiting/Attracting customers • Maximizing profitability (cross selling, identifying profitable customers) • Service Delivery and Customer Retention • Build profiles of customers likely to use which services
  23. 23. Examples of What People are Doing with Data Mining: • Fraud/Non-Compliance Anomaly detection • Isolate the factors that lead to fraud, waste and abuse • Target auditing and investigative efforts more effectively • Credit/Risk Scoring • Intrusion detection • Parts failure prediction • Recruiting/Attracting customers • Maximizing profitability (cross selling, identifying profitable customers) • Service Delivery and Customer Retention • Build profiles of customers likely to use which services
  24. 24. Examples of What People are Doing with Data Mining: • Fraud/Non-Compliance Anomaly detection • Isolate the factors that lead to fraud, waste and abuse • Target auditing and investigative efforts more effectively • Credit/Risk Scoring • Intrusion detection • Parts failure prediction • Recruiting/Attracting customers • Maximizing profitability (cross selling, identifying profitable customers) • Service Delivery and Customer Retention • Build profiles of customers likely to use which services
  25. 25. Examples of What People are Doing with Data Mining: Right offer for the right customer throw the right channel in the right time
  26. 26. How Can We Do Data Mining? •A standard process •Existing data •Software technologies •Situational expertise
  27. 27. How Can We Do Data Mining? •A standard process The data mining process must be reliable and repeatable by people with little data mining background. •Existing data •Software technologies •Situational expertise
  28. 28. Phases and Tasks Business Data Data Modeling Evaluation Deployment Understanding Understanding Preparation Determine Collect Initial Data Data Set Select Modeling Evaluate Results Plan Deployment Business Objectives Initial Data Collection Data Set Description Technique Assessment of Data Deployment Plan Background Report Modeling Technique Mining Results w.r.t. Business Objectives Select Data Modeling Assumptions Business Success Plan Monitoring and Business Success Describe Data Rationale for Inclusion / Criteria Maintenance Criteria Data Description Report Exclusion Generate Test Design Approved Models Monitoring and Test Design Maintenance Plan Situation Assessment Explore Data Clean Data Review Process Inventory of Resources Data Exploration Report Data Cleaning Report Build Model Review of Process Produce Final Report Requirements, Parameter Settings Final Report Assumptions, and Verify Data Quality Construct Data Models Determine Next Steps Final Presentation Constraints Data Quality Report Derived Attributes Model Description List of Possible Actions Risks and Contingencies Generated Records Decision Review Project Terminology Assess Model Experience Costs and Benefits Integrate Data Model Assessment Documentation Merged Data Revised Parameter Determine Settings Data Mining Goal Format Data Data Mining Goals Reformatted Data Data Mining Success Criteria Produce Project Plan Project Plan Initial Asessment of Tools and Techniques
  29. 29. Phases and Tasks
  30. 30. Phases and Tasks
  31. 31. Phases and Tasks A) Business Understanding Determine Business Determine Data Objectives Mining Goal Background Data Mining Goals Business Objectives Data Mining Success Business Success Criteria Criteria Situation Assessment Produce Project Plan Inventory of Resources Project Plan Requirements, Initial Asessment of Assumptions, and Tools and Techniques Constraints
  32. 32. Phases and Tasks
  33. 33. Phases and Tasks B) Data Understanding Explore Data Data Exploration Report Verify Data Quality Data Quality Report Collect Initial Data Initial Data Collection Report Describe Data Data Description Report
  34. 34. Phases and Tasks
  35. 35. Phases and Tasks C) Data Preparation Data Set Integrate Data Data Set Description Merged Data Select Data Format Data Rationale for Reformatted Data Inclusion/Exclusion Construct Data Clean Data Derived Attributes Data Cleaning Report Generated Records
  36. 36. Phases and Tasks
  37. 37. Phases and Tasks D) Modeling Select Modeling Modeling Technique Modeling Assumptions Generate Test Design Test Design Build Model Parameter Settings Models and Model Description Assess Model Model Assessment Revised Parameter
  38. 38. Phases and Tasks
  39. 39. Phases and Tasks D) Evaluation Evaluate Results Assessment of Data Mining Results w.r.t. Business Success Criteria Approved Models Review Process Review of Process Determine Next Steps List of Possible Actions Decision
  40. 40. Phases and Tasks
  41. 41. Phases and Tasks E) Deployment Plan Deployment Deployment Plan Plan Monitoring and Maintenance Monitoring and Maintenance Plan Produce Final Report Final Report Final Presentation Review Project Experience and Documentation
  42. 42. Data mining success story The US Internal Revenue Service needed to improve customer service and... Scheduled its workforce to provide faster, more accurate answers to questions.
  43. 43. Data mining success story The US Drug Enforcement Agency needed to be more effective in their drug “busts” and analyzed suspects’ cell phone usage to focus investigations.
  44. 44. Data mining success story HSBC need to cross-sell more effectively by identifying profiles that would be interested in higher yielding investments and... Reduced direct mail costs by 30% while garnering 95% of the campaign’s revenue.
  45. 45. Final Comments
  46. 46. Data Mining can be utilized in any organization that needs to find patterns or relationships in their data.
  47. 47. Data Mining can be utilized in any organization that needs to find patterns or relationships in their data. By using the DM methodology, analysts can have a reasonable level of assurance that their Data Mining efforts will render useful, repeatable, and valid results.

×