1 / 34

Informatie Analyse

Laila Fettah – Associate Sales Engineer SPSS 27 January 2011. Informatie Analyse. Agenda. Government – Challenges Data mining CRISP-DM Example Application. Ongoing Budget Pressures. Lack of Decision-Quality Information. Ongoing Improvement, Less Resources.

kitra
Download Presentation

Informatie Analyse

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. LailaFettah – Associate Sales Engineer SPSS 27 January 2011 Informatie Analyse

  2. Agenda • Government – Challenges • Data mining • CRISP-DM • Example Application

  3. Ongoing Budget Pressures Lack of Decision-Quality Information Ongoing Improvement, Less Resources Transparency & Accountability Demonstrate Effective Public Policy Government faces challenges everyday…

  4. …and must answer critical questions everyday... Have new crime fighting tactics been effective? How have collection strategies impacted budgets? How satisfied do citizens feel? What fraud patterns are emerging? Have job creation programs helped curb benefits applications? What is likely to happen in the long-term?

  5. Executive Leaders Information Technology Workforce/ HR Program Execution Services Delivery Budgeting & Finance Operations/ Readiness Supply Chain …and silos often persist that impact outcomes...

  6. Information Technology Budgeting & Finance Public Safety Staff Supply Chain Management Services Delivery Operations/ Readiness Program Execution …analytics can tear down silos Communities

  7. What is data mining? • Finding patterns in your datathat you can useto do your business better • Business-oriented discovery of patternsproducing insight and a predictive capabilitywhich can be deployedwidely • Process of autonomously retrieving useful information or knowledge (“actionable assets”) from large data stores or set • “Predictive analysis helps connect data to effective action by drawing reliable conclusionsaboutcurrent conditions and future events.”Gareth Herschel, Research Director, Gartner Group

  8. What’s in a name? • Data Mining is not a great metaphor • Would mean people who dig for gold are “rock miners”! • Other early candidates: • Knowledge Discovery in Databases (KDD) • “Torturing the data until it confesses” • “…and if you torture it long enough, it’ll confess to anything!”

  9. Give me the times that crimes where committed Give me a count of the types of crimes Give me the number of males and females within the repeat offenders Traditional analyses What is the profile of the repeatoffenders in my district? What do I do NOW??? By count of crime type First by gender or offender? By time of offence Report 1 Report 2 Report 3

  10. Create profiles of repeat offenders based on gender, time, location, type of crime… Data Mining Youth gangs from cities A and B that are mostly active on Thursday night in the center. Addicts that are mostly active around the central station as pick pockets ……….. What is the profile of the repeatoffenders in my district? Ok, so I need to talk with the railway and with local authorities in city A and B…. There are several profiles for repeat offenders. The most important are…. I know from my understanding of crime that gender, time, place, type of crime, age can be important Let me think…. A descriptive question Make individual profiles Data Mining Technology

  11. Underlying analyses

  12. CRISP-DM • CRoss Industry Standard Process for Data Mining • Funding from European commission • Non-proprietary • Application/Industry neutral • Tool neutral • Focus on business issues as well as technical analysis • www.crisp-dm.org • Process framework for data mining projects • Process Standardization

  13. CRISP-DM phases

  14. Example Application Areas: • Public Safety • Reduce crime • Improve border protection • Proactive disease surveillance • Intrusion and insider threat detection • Customs & Excise, Tax, Social security • Predict & prevent fraud • Improve collections • Focus investigators & inspectors • Defense • Increase battle readiness of assets • Improve employee acquisition, retention & growth • Citizen satisfaction • Implement continuous citizen feedback loop • Improve operational processes • ……

  15. Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Will he become a repeat offender? If YES: advise DA and later parole officer?

  16. Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Will he become a repeat offender? If YES: advise DA and later parole officer? A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to?

  17. Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Will he become a repeat offender? If YES: advise DA and later parole officer? A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to? A Break-in into a shop is reported The perpetrators entered by breaking a window probably between 3am and 5am. Crime was discovered at 6 pm next day Is it likely that they’ll find useful evidence? Does it make sense to send out a CSI team?

  18. Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Will he become a repeat offender? If YES: advise DA and later parole officer? A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to? A Break-in into a shop is reported The perpetrators entered by breaking a window probably between 3am and 5am. Crime was discovered at 6 pm next day Is it likely that they’ll find useful evidence? Does it make sense to send out a CSI team? An organized crime unit wants to bust a drugs ring The detectives are interested in identifying the central players within a narcotics network Who are the key persons? Who are the leaders?

  19. PD uses predictive analytics to profile crimes & criminals to improve solved crime rates and optimize resource usage Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Crime Data Will he become a repeat offender? If YES: advise DA and later parole officer? A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Predictive Modeling for Crime Pattern Detection Crime record notes and call logs Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to? Surveillance Data A Break-in into a shop is reported The perpetrators entered by breaking a window probably between 3am and 5am. Crime was discovered at 6 pm next day Communication Data Is it likely that they’ll find useful evidence? Does it make sense to send out a CSI team? An organized crime unit wants to bust a drugs ring The detectives are interested in identifying the central players within a narcotics network Financial Data Who are the key persons? Who are the leaders?

  20. PD uses predictive analytics to profile crimes & criminals to improve solved crime rates and optimize resource usage Aspiring Repeat Offender profile … If male And age 14-16 And crime =‘car break in’ And motive =‘peer pressure’ Then repeat risk is HIGH  ALERT DA … Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Crime Data Will he become a repeat offender? If YES: advise DA and later parole officer? A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Predictive Modeling for Crime Pattern Detection Crime record notes and call logs Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to? Surveillance Data A Break-in into a shop is reported The perpetrators entered by breaking a window probably between 3am and 5am. Crime was discovered at 6 pm next day Communication Data Is it likely that they’ll find useful evidence? Does it make sense to send out a CSI team? An organized crime unit wants to bust a drugs ring The detectives are interested in identifying the central players within a narcotics network Financial Data Who are the key persons? Who are the leaders?

  21. PD uses predictive analytics to profile crimes & criminals to improve solved crime rates and optimize resource usage Aspiring Repeat Offender profile … If male And age 14-16 And crime =‘car break in’ And motive =‘peer pressure’ Then repeat risk is HIGH  ALERT DA … Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Crime Data Will he become a repeat offender? If YES: advise DA and later parole officer? Crime profile  Team 4 Cluster ‘Bogus Official’ - Burglary, - Visit by city official, - Entry ‘Back door’, - Victim “Elderly’ A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Predictive Modeling for Crime Pattern Detection Crime record notes and call logs Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to? Surveillance Data A Break-in into a shop is reported The perpetrators entered by breaking a window probably between 3am and 5am. Crime was discovered at 6 pm next day Communication Data Is it likely that they’ll find useful evidence? Does it make sense to send out a CSI team? An organized crime unit wants to bust a drugs ring The detectives are interested in identifying the central players within a narcotics network Financial Data Who are the key persons? Who are the leaders?

  22. PD uses predictive analytics to profile crimes & criminals to improve solved crime rates and optimize resource usage Aspiring Repeat Offender profile … If male And age 14-16 And crime =‘car break in’ And motive =‘peer pressure’ Then repeat risk is HIGH  ALERT DA … Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Crime Data Will he become a repeat offender? If YES: advise DA and later parole officer? Crime profile  Team 4 Cluster ‘Bogus Official’ - Burglary, - Visit by city official, - Entry ‘Back door’, - Victim “Elderly’ A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Predictive Modeling for Crime Pattern Detection Crime record notes and call logs Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to? Surveillance Data CS profile  No Deployment … If Break In And Night And report>12hrs And entry =‘broken window’ And object=‘Commercial Property’ Then probability evidence is 6% … A Break-in into a shop is reported The perpetrators entered by breaking a window probably between 3am and 5am. Crime was discovered at 6 pm next day Communication Data Is it likely that they’ll find useful evidence? Does it make sense to send out a CSI team? An organized crime unit wants to bust a drugs ring The detectives are interested in identifying the central players within a narcotics network Financial Data Who are the key persons? Who are the leaders?

  23. PD uses predictive analytics to profile crimes & criminals to improve solved crime rates and optimize resource usage Aspiring Repeat Offender profile … If male And age 14-16 And crime =‘car break in’ And motive =‘peer pressure’ Then repeat risk is HIGH  ALERT DA … Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Crime Data Will he become a repeat offender? If YES: advise DA and later parole officer? Crime profile  Team 4 Cluster ‘Bogus Official’ - Burglary, - Visit by city official, - Entry ‘Back door’, - Victim “Elderly’ A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Predictive Modeling for Crime Pattern Detection Crime record notes and call logs Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to? Surveillance Data CS profile  No Deployment … If Break In And Night And report>12hrs And entry =‘broken window’ And object=‘Commercial Property’ Then probability evidence is 6% … A Break-in into a shop is reported The perpetrators entered by breaking a window probably between 3am and 5am. Crime was discovered at 6 pm next day Communication Data Is it likely that they’ll find useful evidence? Does it make sense to send out a CSI team? • Key Players • Focus on: • Keith Patterson • Colin Wiertz • Markus Haffey An organized crime unit wants to bust a drugs ring The detectives are interested in identifying the central players within a narcotics network Financial Data Who are the key persons? Who are the leaders?

  24. PD uses predictive analytics to profile crimes & criminals to improve solved crime rates and optimize resource usage Aspiring Repeat Offender profile … If male And age 14-16 And crime =‘car break in’ And motive =‘peer pressure’ Then repeat risk is HIGH  ALERT DA … Johnny is arrested for breaking into a car He is 15 years old and confesses that he wanted to belong to a group of friends Management Dashboard Crime Data Will he become a repeat offender? If YES: advise DA and later parole officer? Crime profile  Team 4 Cluster ‘Bogus Official’ - Burglary, - Visit by city official, - Entry ‘Back door’, - Victim “Elderly’ A citizen reports a burglary Reports that her house was burglarized while she was talking to a representative from the city council Predictive Modeling for Crime Pattern Detection Crime record notes and call logs Does this crime resemble others? Is it serial? Do we have a team working on similar crimes that we can assign it to? Surveillance Data CS profile  No Deployment … If Break In And Night And report>12hrs And entry =‘broken window’ And object=‘Commercial Property’ Then probability evidence is 6% … A Break-in into a shop is reported The perpetrators entered by breaking a window probably between 3am and 5am. Crime was discovered at 6 pm next day Communication Data Is it likely that they’ll find useful evidence? Does it make sense to send out a CSI team? • Key Players • Focus on: • Keith Patterson • Colin Wiertz • Markus Haffey An organized crime unit wants to bust a drugs ring The detectives are interested in identifying the central players within a narcotics network Financial Data Who are the key persons? Who are the leaders?

  25. Capture Predict Act Crime Data Crime record notes and call logs Surveillance Data Communication Data Financial Data

  26. Capture Predict Predict Act Act Capture Crime Data Crime record notes and call logs Predictive Modeling for Crime Pattern Detection Surveillance Data Crime Pattern & Hotspot Clustering Profiles & Associations Communication Data Automated Link Analysis Financial Data

  27. Capture Predict Predict Act Act Capture Crime Data Criminal Career Scoring Model Crime record notes and call logs MO Typology Model Predictive Modeling for Crime Pattern Detection Surveillance Data Crime Scene Assessment Model Crime Pattern & Hotspot Clustering Profiles & Associations Communication Data Automated Link Analysis Financial Data

  28. Capture Predict Predict Act Act Capture Alert! Aspiring Repeat Offender Risk HIGH Advise DA and inform parole officer Arresting Officer Crime Data Alert! Serial Crime Profile MO fits Team 4 Criminal Career Scoring Model Crime record notes and call logs Case Assignment Officer MO Typology Model Predictive Modeling for Crime Pattern Detection Alert! Very Low Likelihood Evidence Probability <10%  No Deployment Surveillance Data Crime Scene Assessment Model CSI Resource Planner Crime Pattern & Hotspot Clustering Profiles & Associations Communication Data Automated Link Analysis Financial Data

  29. Capture Predict Predict Act Act Capture Alert! Aspiring Repeat Offender Risk HIGH Advise DA and inform parole officer Arresting Officer Crime Data Alert! Serial Crime Profile MO fits Team 4 Criminal Career Scoring Model Crime record notes and call logs Case Assignment Officer MO Typology Model Predictive Modeling for Crime Pattern Detection Alert! Very Low Likelihood Evidence Probability <10%  No Deployment Surveillance Data Crime Scene Assessment Model CSI Resource Planner • Key Players • Focus on: • Keith Patterson • Colin Wiertz • Markus Haffey Crime Pattern & Hotspot Clustering Profiles & Associations Communication Data Investigating Officer Investigative Model Template Repository Automated Link Analysis Financial Data Feedback results Feedback loop of new data to improve and adapt predictions

  30. Capture Predict Predict Act Act Capture Alert! Aspiring Repeat Offender Risk HIGH Advise DA and inform parole officer Arresting Officer Crime Data Alert! Serial Crime Profile MO fits Team 4 Criminal Career Scoring Model Crime record notes and call logs Case Assignment Officer MO Typology Model Predictive Modeling for Crime Pattern Detection Alert! Very Low Likelihood Evidence Probability <10%  No Deployment Surveillance Data Crime Scene Assessment Model CSI Resource Planner • Key Players • Focus on: • Keith Patterson • Colin Wiertz • Markus Haffey Crime Pattern & Hotspot Clustering Profiles & Associations Communication Data Analytical Process Automation & Optimization Automate prediction & deployment process Analytical Process Management & Control Monitor & manage analytics process Investigating Officer Investigative Model Template Repository Automated Link Analysis Financial Data Feedback results Feedback loop of new data to improve and adapt predictions

  31. Capture Predict Predict Act Act Capture Alert! Aspiring Repeat Offender Risk HIGH Advise DA and inform parole officer Arresting Officer Crime Data Alert! Serial Crime Profile MO fits Team 4 Criminal Career Scoring Model Management Dashboard Crime record notes and call logs Case Assignment Officer MO Typology Model Predictive Modeling for Crime Pattern Detection Alert! Very Low Likelihood Evidence Probability <10%  No Deployment Surveillance Data Crime Scene Assessment Model CSI Resource Planner • Key Players • Focus on: • Keith Patterson • Colin Wiertz • Markus Haffey Crime Pattern & Hotspot Clustering Profiles & Associations Communication Data Analytical Process Automation & Optimization Automate prediction & deployment process Analytical Process Management & Control Monitor & manage analytics process Investigating Officer Investigative Model Template Repository Automated Link Analysis Financial Data Feedback results Feedback loop of new data to improve and adapt predictions

  32. Start from business understanding… not from data or technique…

  33. …and use a methodology!

  34. Van informatie op OrdenaarInformatie van Waarde – 27 januari2011 Questions

More Related