The document discusses the use of predictive analytics in state government. It describes how predictive analytics has become mainstream due to decreasing technology costs, increased data availability, and the need for fairness and flexibility. The document outlines several applications of predictive analytics in the public sector, including tax delinquency modeling, Medicaid fraud detection, and unemployment insurance overpayment recovery. It provides examples of how predictive analytics could help improve outcomes in areas like child support case management and child welfare systems.
It has been said that Mobiles +Cloud + Social + Big Data = Better Run The World. IBM has invested over $20 billion since 2005 to grow its analytics business, many companies will invest more than $120 billion by 2015 on analytics, hardware, software and services critical in almost every industry like ; Healthcare, media, sports, finance, government, etc.
It has been estimated that there is a shortage of 140,000 – 190,000 people with deep analytical skills to fill the demand of jobs in the U.S. by 2018.
Decoding the human genome originally took 10 years to process; now it can be achieved in one week with the power of Analytic and BI (Business Intelligence). This lecture’s Key Messages is that Analytics provide a competitive edge to individuals , companies and institutions and that Analytics and BI are often critical to the success of any organization.
Methodology used is to teach analytic techniques through real world examples and real data with this goal to convince audience of the Analytics Edge and power of BI, and inspire them to use analytics and BI in their career and their life.
Predictive marketing extracts information from existing datasets allowing marketers to predict which actions are more likely to succeed and lets marketers determine future outcomes and trends.
This presentation introduces big data and explains how to generate actionable insights using analytics techniques. The deck explains general steps involved in a typical analytics project and provides a brief overview of the most commonly used predictive analytics methods and their business applications.
Predictive Analytics enables organisations to forecast future events, analyse risks and opportunities, and automate decision making processes by analysing historic data.
It has been said that Mobiles +Cloud + Social + Big Data = Better Run The World. IBM has invested over $20 billion since 2005 to grow its analytics business, many companies will invest more than $120 billion by 2015 on analytics, hardware, software and services critical in almost every industry like ; Healthcare, media, sports, finance, government, etc.
It has been estimated that there is a shortage of 140,000 – 190,000 people with deep analytical skills to fill the demand of jobs in the U.S. by 2018.
Decoding the human genome originally took 10 years to process; now it can be achieved in one week with the power of Analytic and BI (Business Intelligence). This lecture’s Key Messages is that Analytics provide a competitive edge to individuals , companies and institutions and that Analytics and BI are often critical to the success of any organization.
Methodology used is to teach analytic techniques through real world examples and real data with this goal to convince audience of the Analytics Edge and power of BI, and inspire them to use analytics and BI in their career and their life.
Predictive marketing extracts information from existing datasets allowing marketers to predict which actions are more likely to succeed and lets marketers determine future outcomes and trends.
This presentation introduces big data and explains how to generate actionable insights using analytics techniques. The deck explains general steps involved in a typical analytics project and provides a brief overview of the most commonly used predictive analytics methods and their business applications.
Predictive Analytics enables organisations to forecast future events, analyse risks and opportunities, and automate decision making processes by analysing historic data.
This presentation introduces big data and explains how to generate actionable insights using analytics techniques. The deck explains general steps involved in a typical analytics project and provides a brief overview of the most commonly used predictive analytics methods and their business applications.
Vijay Adamapure is a Data Science Enthusiast with extensive experience in the field of data mining, predictive modeling and machine learning. He has worked on numerous analytics projects ranging from healthcare, business analytics, renewable energy to IoT.
Vijay presented these slides during the Internet of Everything Meetup event 'Predictive Analytics - An Overview' that took place on Jan. 9, 2015 in Mumbai. To join the Meetup group, register here: http://bit.ly/1A7T0A1
This slide discuss predictive data analytics models and their applications in broader content. It gives simple examples of regression and classification.
PoT - probeer de mogelijkheden van datamining zelf uit 30-10-2014Daniel Westzaan
IBM Proof of Technology
Probeer de Mogelijkheden van Datamining zelf uit
30-10-2014 Amsterdam, IBM Client Center
Presentatie van Laila Fettah & Robin van Tilburg
Predictive and prescriptive analytics: Transform the finance function with gr...Grant Thornton LLP
As all businesses continue to collect, store and analyze more data than ever before, they face growing data challenges to support decision-making. Those who can leverage predictive and prescriptive analytics will differentiate themselves in the marketplace and gain a competitive advantage. In this report by Financial Executives Research Foundation Inc. and Grant Thornton LLP, we highlight insights from in-depth interviews with senior-level executives. These organizations use advanced analytics in their businesses to gain significant profit improvements. See more at - http://gt-us.co/1vv2KU9
Gather the required information from the data and predict future outcomes and trends. Use content-ready Predictive Analysis PowerPoint Presentation Slides to forecast future probabilities. Majorly applied in the business field, predictive analysis PPT templates will help you evaluate current data and historical facts to understand customers, products, services, partners, and to identify potential risks and opportunities for an organization. This deck comprises of templates such as research methodology, consumer insights consumption, need for consumer insights, key stats, data collection and processing, consumer insight capabilities, These templates are completely customizable. You can edit the templates as per your need. Change color, text, icon and font size as per your requirement. Add or remove the content, if needed. Get access to the predictive analysis PowerPoint presentation slideshow to predict future outcomes for various business topics such as customer relationship management, health care, collection analytics, fraud detection, risk management, direct marketing, industry applications, etc. Get access to the professionally designed ready-made predictive analysis PowerPoint presentation slides for your business to interpret big data for your benefit. Maintain your demeanour with our Predictive Analysis Powerpoint Presentation Slides. They will help you keep your cool.
Predictive analytics can take you from guesswork to prediction by showing you where you are now, and where you can go next. It empowers you to analyze trends, patterns and relationships in your structured and unstructured data, apply those insights to predict future events, and act to achieve your desired outcomes.
Predictive Analytics: An Executive PrimerRyan Withop
An Executive Overview of what Predictive Analytics is and where it can benefit SaaS businesses, with concrete examples of how we actually used these techniques at YouSendIt. Very handy set I've used to introduce new C-level Execs to optimizing their business based on actionable analytics.
Predictive analytics in uae government organizationsSaeed Al Dhaheri
This presentation is to create awareness of the use the use of predicative analytics in public sector organizations with emphasis on UAE government organizations.
Ibm ofa ottawa_analytics_in_gov _campbell_robertsondawnrk
Opportunity for Analytics Ottawa event. Presentation by Campbell Robertson, Analytics in Government. Results based outcomes with IBM Predictive Analysis for Cost Avoidance and Beyond.
This presentation introduces big data and explains how to generate actionable insights using analytics techniques. The deck explains general steps involved in a typical analytics project and provides a brief overview of the most commonly used predictive analytics methods and their business applications.
Vijay Adamapure is a Data Science Enthusiast with extensive experience in the field of data mining, predictive modeling and machine learning. He has worked on numerous analytics projects ranging from healthcare, business analytics, renewable energy to IoT.
Vijay presented these slides during the Internet of Everything Meetup event 'Predictive Analytics - An Overview' that took place on Jan. 9, 2015 in Mumbai. To join the Meetup group, register here: http://bit.ly/1A7T0A1
This slide discuss predictive data analytics models and their applications in broader content. It gives simple examples of regression and classification.
PoT - probeer de mogelijkheden van datamining zelf uit 30-10-2014Daniel Westzaan
IBM Proof of Technology
Probeer de Mogelijkheden van Datamining zelf uit
30-10-2014 Amsterdam, IBM Client Center
Presentatie van Laila Fettah & Robin van Tilburg
Predictive and prescriptive analytics: Transform the finance function with gr...Grant Thornton LLP
As all businesses continue to collect, store and analyze more data than ever before, they face growing data challenges to support decision-making. Those who can leverage predictive and prescriptive analytics will differentiate themselves in the marketplace and gain a competitive advantage. In this report by Financial Executives Research Foundation Inc. and Grant Thornton LLP, we highlight insights from in-depth interviews with senior-level executives. These organizations use advanced analytics in their businesses to gain significant profit improvements. See more at - http://gt-us.co/1vv2KU9
Gather the required information from the data and predict future outcomes and trends. Use content-ready Predictive Analysis PowerPoint Presentation Slides to forecast future probabilities. Majorly applied in the business field, predictive analysis PPT templates will help you evaluate current data and historical facts to understand customers, products, services, partners, and to identify potential risks and opportunities for an organization. This deck comprises of templates such as research methodology, consumer insights consumption, need for consumer insights, key stats, data collection and processing, consumer insight capabilities, These templates are completely customizable. You can edit the templates as per your need. Change color, text, icon and font size as per your requirement. Add or remove the content, if needed. Get access to the predictive analysis PowerPoint presentation slideshow to predict future outcomes for various business topics such as customer relationship management, health care, collection analytics, fraud detection, risk management, direct marketing, industry applications, etc. Get access to the professionally designed ready-made predictive analysis PowerPoint presentation slides for your business to interpret big data for your benefit. Maintain your demeanour with our Predictive Analysis Powerpoint Presentation Slides. They will help you keep your cool.
Predictive analytics can take you from guesswork to prediction by showing you where you are now, and where you can go next. It empowers you to analyze trends, patterns and relationships in your structured and unstructured data, apply those insights to predict future events, and act to achieve your desired outcomes.
Predictive Analytics: An Executive PrimerRyan Withop
An Executive Overview of what Predictive Analytics is and where it can benefit SaaS businesses, with concrete examples of how we actually used these techniques at YouSendIt. Very handy set I've used to introduce new C-level Execs to optimizing their business based on actionable analytics.
Predictive analytics in uae government organizationsSaeed Al Dhaheri
This presentation is to create awareness of the use the use of predicative analytics in public sector organizations with emphasis on UAE government organizations.
Ibm ofa ottawa_analytics_in_gov _campbell_robertsondawnrk
Opportunity for Analytics Ottawa event. Presentation by Campbell Robertson, Analytics in Government. Results based outcomes with IBM Predictive Analysis for Cost Avoidance and Beyond.
Analytics is a critical tool that allows business owners to make
fact-based decisions about taxonomies. Taxonomy management involves capturing terms and concepts, analyzing their usefulness, and managing the employment of the concepts and terms within different contexts.
This presentation offers best practices on design and maintenance of taxonomies, as well as discusses the role of the governance plan.
The presentation covers broad areas of design methodology, with sustainable methods for maintaining taxonomies and integrating changes into their systems design processes.
Preventing Tax Evasion & Benefits Fraud Through Predictive AnalyticsCapgemini
Today's tax and welfare agencies are increasingly facing new and sophisticated methods of tax evasion and welfare fraud. Increasing digitization means that fraudsters are becoming faster and new types of fraud, such as ID theft, are growing.
However, with more and better data available, agencies now have the ability to sharpen their insights at higher speeds.
Capgemini’s TROUVE solution, powered by SAS, helps Tax & Welfare agencies harness digital to achieve better, faster and cheaper compliance results.
Presented by Capgemini's Ian Pretty at SAS Analytics 2014.
Big Data & Analytics for Government - Case StudiesJohn Palfreyman
This presentation explains the future challenges that Governments face, and illustrates how Big Data & Analytics technologies can help address these challenges. Four case studies - based on recent customer projects - are used to show the value that the innovative application of these technologies can bring.
Imagine … internal auditors identifying risks + opportunities from data. Internal auditors can + need to grasp this opportunity to transform their role and industry. More >> grantthornton.com/data-analytics
Big Data Analytics: Reference Architectures and Case Studies by Serhiy Haziye...SoftServe
BI architecture drivers have to change to satisfy new requirements in format, volume, latency, hosting, analysis, reporting, and visualization. In this presentation delivered at the 2014 SATURN conference, SoftServe`s Serhiy and Olha showcased a number of reference architectures that address these challenges and speed up the design and implementation process, making it more predictable and economical:
- Traditional architecture based on an RDMBS data warehouse but modernized with column-based storage to handle a high load and capacity
- NoSQL-based architectures that address Big Data batch and stream-based processing and use popular NoSQL and complex event-processing solutions
- Hybrid architecture that combines traditional and NoSQL approaches to achieve completeness that would not be possible with either alone
The architectures are accompanied by real-life projects and case studies that the presenters have performed for multiple companies, including Fortune 100 and start-ups.
Predictive Analytics: Context and Use Cases
Historical context for successful implementation of predictive analytic techniques and examples of implementation of successful use cases.
Predictive Analytics has stopped being an advanced analytics project that is done to gain competitive advantage. It is now the mainstay of every business and requires the ability to handle a wide variety of intricate types of problems, day in and day out, at an ever increasing pressure of RoI, at a scale previously unimagined and at speed previously unconceivable. As the current analytics maturity curves evolves to consider Machine Learning & Artificial Intelligence as integral components that an organization should aspire for, it requires predictive analyze imbibe the best of product practices- agility of development, iterative learning & developing, inter-operability and a simpler interface aka API. Having an API like framework helps Predictive Analytics seamlessly integrate with other analytical practices like A/B Testing, Research, fit within the final product offering and also help complement power of predictive analytics to answer what could happen based on not only what happened in the past, why it happened, the motivations/aspirations of customers and the engagement of customers with competitive offerings. This leads to a virtuous cycle of enhanced predictive power, easier integration with prescriptive framework, better actionability of insights and ability to tweak actions via Test & Learn Framework.
Predictive Hiring: Find Candidates Who Will Succeed in Your OrganizationHuman Capital Media
The facts are clear: Most companies today need to do a better job selecting talent. Recent survey data collected by the Corporate Executive Board indicates that nearly a quarter of all new hires leave their companies within a year, and that hiring managers wish they never extended an offer to one of every five members of their team. And a recent Gallup survey found that 52 percent of American workers were “not engaged” with their work.
Can you afford to miss an opportunity to learn how best-in-class organizations are using new technologies to scientifically assess talent before hiring, resulting in lower turnover, higher job performance and greater employee engagement?
In this presentation, you will:
Learn about new solutions that predict candidate success.
Discover how best-in-class organizations are incorporating these new solutions into their hiring process.
See the bottom-line results realized by these best-in-class practitioners.
How can you deliver real value with healthcare data analytics? Four things can help:
Tighten how you deliver information and insights.
Loosen the reins on who can be part of the conversation and contribute.
Create transparency into how data management and analytics works.
Paint a picture and tell a story with your insights.
...
And go do it! Don't just say you're going to do it.
Slide share Hyper-Decision Making - Short VersionDr. Ted Marra
The new imperative for organisational success will be 'hyper-decision making'. Gain insights into executive research around decision making; the concept of 'optimal' decision; the costs of lost opportunity associated with decision making; the factors that determine your organisation's 'decision intelligence quotient'; the drivers of 'risk'; what a systematic, integrated and comprehensive decision making process looks like; and more! Enjoy!
In the fast-changing world of corporate recruiting, it’s important to be aware of and prepared for the problems and opportunities that you will soon face. In short, because it’s “better to be prepared than surprised”, both recruiting and hiring managers must find a way to be “proactive” in planning for these upcoming events, rather than being “reactive”. The most effective way to identify trends and to predict upcoming recruiting issues is through the use of analytics and predictive metrics This advanced webinar will be led by long time ERE.net author and global metrics expert Dr. John Sullivan. He will guide you through the goals, the action steps and the best emerging corporate practices in predictive recruiting metrics.
Giving Organisations new capabilities to ask the right business questions 1.7OReillyStrata
This presentation takes the seminal work structured analytic techniques work pioneered within US intelligence, and proposes adaptions and simplifications for use within commercial enterprises
Enabling Success With Big Data - Driven Talent AcquisitionDavid Bernstein
Adopting an evidence-based recruitment marketing strategy is not just reserved for large employers. In fact, a targeted sourcing strategy can in some ways have a greater impact on small and mid-size businesses who need to allocate already-limited resources to the areas that will provide the most value. Ultimately, hiring the right candidate means profitability for your business. How can talent acquisition professionals gain the insights their organizations need to make better-informed decisions about their recruitment marketing efforts?
5 Ways to Build Employee Trust for Less Turnover and Fewer IncidentsCase IQ
Over the past few months, we’ve seen employees quit in record numbers. While there are many reasons for “The Great Resignation”, a standout is employee trust. A study from Gallup suggests that only one in three employees strongly agree that they trust the leadership of their organization.
Employees want to trust the companies they work at and the people they work with. They want to feel comfortable coming to HR with their complaints and concerns. But building trust takes time, and effort. As organizations are planning their post-pandemic strategies, now is a perfect time to place an intentional emphasis on building trust.
Innovation and economic growth depends on company's ability to gain insight into data. However, data is growing exponentially, but our ability to make use of it is not. Untapped economic value resides in this unutilized data, called "dark data." This presentation looks at some of the causes for the explosion of data, some of the impediments preventing exploring and creating business value from dark data; and some ideas for ways around those impediments.
Why should we care about integrating data? What should we be trying to achieve? Population Health. The Softer, Human Side of Being “Data Driven” not “Driven By Data." The New Era of Decision Support in Healthcare. Top 10 Challenges To Integrating External Data.
What is the point of small housing associations.pptxPaul Smith
Given the small scale of housing associations and their relative high cost per home what is the point of them and how do we justify their continued existance
Russian anarchist and anti-war movement in the third year of full-scale warAntti Rautiainen
Anarchist group ANA Regensburg hosted my online-presentation on 16th of May 2024, in which I discussed tactics of anti-war activism in Russia, and reasons why the anti-war movement has not been able to make an impact to change the course of events yet. Cases of anarchists repressed for anti-war activities are presented, as well as strategies of support for political prisoners, and modest successes in supporting their struggles.
Thumbnail picture is by MediaZona, you may read their report on anti-war arson attacks in Russia here: https://en.zona.media/article/2022/10/13/burn-map
Links:
Autonomous Action
http://Avtonom.org
Anarchist Black Cross Moscow
http://Avtonom.org/abc
Solidarity Zone
https://t.me/solidarity_zone
Memorial
https://memopzk.org/, https://t.me/pzk_memorial
OVD-Info
https://en.ovdinfo.org/antiwar-ovd-info-guide
RosUznik
https://rosuznik.org/
Uznik Online
http://uznikonline.tilda.ws/
Russian Reader
https://therussianreader.com/
ABC Irkutsk
https://abc38.noblogs.org/
Send mail to prisoners from abroad:
http://Prisonmail.online
YouTube: https://youtu.be/c5nSOdU48O8
Spotify: https://podcasters.spotify.com/pod/show/libertarianlifecoach/episodes/Russian-anarchist-and-anti-war-movement-in-the-third-year-of-full-scale-war-e2k8ai4
ZGB - The Role of Generative AI in Government transformation.pdfSaeed Al Dhaheri
This keynote was presented during the the 7th edition of the UAE Hackathon 2024. It highlights the role of AI and Generative AI in addressing government transformation to achieve zero government bureaucracy
Many ways to support street children.pptxSERUDS INDIA
By raising awareness, providing support, advocating for change, and offering assistance to children in need, individuals can play a crucial role in improving the lives of street children and helping them realize their full potential
Donate Us
https://serudsindia.org/how-individuals-can-support-street-children-in-india/
#donatefororphan, #donateforhomelesschildren, #childeducation, #ngochildeducation, #donateforeducation, #donationforchildeducation, #sponsorforpoorchild, #sponsororphanage #sponsororphanchild, #donation, #education, #charity, #educationforchild, #seruds, #kurnool, #joyhome
Jennifer Schaus and Associates hosts a complimentary webinar series on The FAR in 2024. Join the webinars on Wednesdays and Fridays at noon, eastern.
Recordings are on YouTube and the company website.
https://www.youtube.com/@jenniferschaus/videos
Jennifer Schaus and Associates hosts a complimentary webinar series on The FAR in 2024. Join the webinars on Wednesdays and Fridays at noon, eastern.
Recordings are on YouTube and the company website.
https://www.youtube.com/@jenniferschaus/videos
Presentation by Jared Jageler, David Adler, Noelia Duchovny, and Evan Herrnstadt, analysts in CBO’s Microeconomic Studies and Health Analysis Divisions, at the Association of Environmental and Resource Economists Summer Conference.
1. Predictive Analytics in
State Government
Turning insights into action
Margot Bean, David Duden, and B.J. Walker
Deloitte Consulting LLP
September 30, 2014
2. Analytics has gone mainstream
“Perhaps the most important cultural trend today: the explosion of data about
every aspect of our world and the rise of applied math gurus who know how to
use it.”
-- Chris Anderson, editor-in-chief of Wired
“In the past, one could get by on intuition and experience. Times have changed.
Today, the name of the game is data.”
-- Steven Levitt, University of Chicago Economist
and author of Freakonomics
2
3. 3
Analytics enabling factors
Reasons why analytics is now possible:
Technology
• Moore’s Law
• Cost of storage and computing power has
decreased exponentially
Data
• Third-party & lifestyle data is becoming increasingly
available
• Companies are learning to do more with their
internal data
Software and Algorithms
• Innovative analytic ideas continually coming from
statistics, economics, machine learning, marketing,
etc.
• Widespread availability of advanced analytic tools
4. 4
Analytics for the masses
Reasons why analytics is now mainstream:
Need for Fairness
• Effective implementation of predictive models enables
agencies to more effectively deploy reduced resources
Flexibility, Accuracy, Scalability
• Analytics replaces “the broad brush” with “the long tail”
• Mass customization: targeted offers/messages can be
crafted for millions of citizens, employees, etc.
Competing on Analytics
• Innovative companies in all sizes and in all industries
are finding ways of fashioning core competitive
strategies around the use of analytics
5. Increasing applications for analytics
Growing recognition in cognitive psychology & behavioral economics: Predictive
models help human experts make decisions more accurately, objectively,
and economically.
Academic / psychological research dates back to the 1950’s.
Now a growing consensus in the worlds of business, education, law,
government, medicine, entertainment, … and professional sports.
Predictive modelling is the ultimate “transferable skill” – it applies in domains
where experts must make decisions by judgmentally synthesizing information.
“Human judges are not merely worse than optimal regression equations; they are
worse than almost any regression equation.”
-- Richard Nesbitt & Lee Ross, Human Inference: Strategies and Shortcomings of
5
Social Judgment
6. Bringing an objective lens to society’s issues
6
Think of it this way:
Probably due to some quirk in evolution, many of us are nearsighted.
So eyeglasses were invented to help us see better.
Behavioral economics teaches us that probably due to some quirk in evolution,
our minds are not equipped to weigh evidence in an unbiased way
Heuristics and Biases: the mental “heuristics” (or rules of thumb) that we use
to make decisions are biased in surprising ways
We aren’t stupid… it’s just that we are Humans, not Vulcans
So predictive models are built to help us think better.
7. Predictive analytics in the Public Sector
7
Proven Success in the
Private Sector
Applied to the Public Sector
Property & Casualty Insurance
Predicted Loss Ratio Modeling
Soft Fraud Detection Modeling
Financial Services
Credit Scoring
Credit Card Delinquency Modeling
Health Insurance
Insured Segmentation Modeling
Clinical Utilization Modeling
Provider Fraud Detection
Predicted Loss Ratio Modeling
Claimant Severity/Duration Modeling
Tax Payer Delinquency Modeling
Tax Payer Non-filer Discovery Modeling
Government Sponsored Health
Insurance Member Retention Modeling
Medicaid Fraud Detection
Unemployment Insurance Overpayment
8. • Reduce user guesswork and “cherry picking”
• Prioritize workload based on high impact
• Incorporate historical experience to drive future activities
• Eliminate a one size fits all approach
• Efficiency of customer service interactions
• Over time reduce future workload
• Change from a sequential process to a “smart” work queue
• Shift from reactive enforcement to early intervention
• Learning component for new case management approaches
• Assign high risk cases to case workers sooner
• Different approaches for different regions and different case types
• Automate certain research processes
8
Benefits to the State
• Better estimates of delinquencies, child support collections
• Increased revenue, reduced fraud, waste and Abuse
• Fewer child support and cases in arrears
• Model results can be used to quantify historical process inefficiencies
• Significant marketing value – “We Know Our Citizens”
• Create unified view across all regions and business processes
Improved
Workforce
Effectiveness
Increased
Resource
Allocation
Efficiency
Improved
Outcomes
10. Current challenges for child support case management
Working the Right Cases Information Overload Visible Results
Next Appropriate Action Case Worker Management
Lack of a targeted
case management strategy
10
11. Predictive modeling child support strategy
Child support case management has traditionally been a reactive
process
Shift focus to predicting which Noncustodial Parents are most
likely to fail to pay in the near future through regression analysis
11
Anticipated outcomes:
Prevent growth of child support arrears
Decrease custodial parent complaints
Reliable payments each month
Increased worker efficiency by taking the right action on a case at the right
time
Ability to assign the right case workers to the right cases
Improve performance on federal child support measures – increased
incentives for the state
Use analytics to make smarter decisions, do more with less, and
improve people’s lives
12. 12
Using the scores
Prioritize
Cases
Suggest
Actions
See
Results
• Predict which cases
likely to fall into
delinquency
• Identify the top reasons
the case is predicted to
fall into delinquency
• Provide child support
workers with information
needed to proactively
reduce likelihood case
will fall into delinquency
• Focus on cases most
likely to respond to
targeted worker actions
• Identify opportunities for
proactive enforcement
activities
• Tailor customer
engagement actions on
each case based on top
reasons for predicted
delinquency
• Provide the right service
at the right time to the
case to encourage
compliance with the
order
• More effective case
assignment by matching
worker skills with case
difficulty
• Increased quantity and
frequency of collections
in 2 state child support
agencies
• More productive
meetings with
noncustodial parents
• Decreased enforcement
costs by focusing action
where it will be most
productive
13. Critical adoption success factors
Effective Change Management
Business Process Changes
13
Shift in Worker’s Mindset
Worker Buy-In
Communicating Strategic Intent of Predictive Analytics
Organizational Readiness
People Readiness
More touch-points
with users
Site visits pre and post
implementation
Increased presence to
discuss business
process changes
Regular follow-up
activities ( Onsite and
WebEx meetings,
conference calls, etc.)
SME support for
counties
14. Child Welfare
How predictive analytics can help us make decisions
that really are in the “best interests of the child”
15. Some inconvenient truths about the child welfare system
Most typical ways to hold child welfare systems accountable – media
scrutiny, consent decrees, federal reporting – are too little, too late
Policy, procedures and even evidence-based practice models offer false
comfort in a harsh and unpredictable business
The people and systems who manage the data and reporting in your
organization are not the people doing the work
Tracking and reporting on metrics is not enough – unless you know
why people are making the decisions they do and impact of those
decisions real time
The standard response to tragedy and crisis is to explain what
happened, not why it happened
15
REACTIVE VS.
PROACTIVE
POLICY VS.
PRACTICE
ADMINISTRATIVE
VS. OPERATIONAL
EFFECT VS.
CAUSE
“WHAT” VS.
“WHY”
16. Making the case for predictive analytics in child welfare
You have plenty of data, but time and time again you find yourself not being able
to use it to stop bad things from happening or to prevent them from happening
again. The information lurking deep under the surface of wrong work and lack of
results is a game changer – but you get it too late (and sometimes not at all).
First, it starts with getting the
questions right – ask them early
and often ?
Second, get the analysis right
Third, use what you learn to expect
different behaviors and better
decisions
16
17. Asking the right questions helps set the context and put
us into an analytics frame of mind
Good business questions are the tail that wags the
predictive analytics dog– it is about what you need to
know, when you need to know it, what you do about
it, and your willingness to keep asking yourself if it is
effective.
In the past, we focused on the Federal measures but:
Lag measures alone offer few insights into why
17
situations occurred.
These metrics – without context – do not pay us
back in changed systems (ones where people
consistently make better decisions and exhibit
more effective behaviors)
Current metrics tracked in
child welfare:
initial response time in a
hotline call
amount of time it takes to
complete an investigation
time it takes to file a
termination of parental
rights (TPR), finalize
adoptions, or reunify
children with their parents
rate of recurrence of
maltreatment or re-entry
into care
In a dangerous business, knowing what just happened is only
useful if it helps you predict and shape what will happen next
18. Performing the right analyses
Realize that algorithms are only as good as your questions. But once you get the
questions right -- then you need to make sure that you get the math right.
Even when you think a statistical formula is
telling you something – you need to put it
into context to make any sense out of it.
18
How many times has this situation
happened before?
Were the contextual factors the same?
Has it happened this way before enough
times for you to rely on the pattern as being
predictable?
Challenges
• We can get lost in statistical
jargon (coefficients, cluster
analysis, regression to the
mean??)
• Those performing the
analysis may want to
emphasize the math over
the meaning
None of this is pure science – that’s why the outputs from
predictive analytics are called insights instead of answers
19. Putting results into action = different behaviors and
better decisions
The question is not simply “can you predict something?” Sure you can. But “what
can you do about it?” Real change requires organizations to generate different
behaviors and better decisions based on the analytics outputs
19
SIGNIFICANT:
Focusing on what
really matters versus
what is simply
interesting
ALIGNED WITH
MISSION: Connecting
what the data tells you
to a set of values
(imperatives) about the
work, especially when
the work is hard and
dangerous
ACTIONABLE:
Empowering people to
make better decisions
and to have the
courage to do
something different
20. Using data to “profile” a problem you need to fix
Example: Placement Disruptions
• Length of time child has been in care
• Reason child came into care
• Allegations of maltreatment by child while in care
• Length of time child has been with provider
• Proximity of provider to child’s parent/removal home
• Placement with /without siblings
• Number of substantiated or unsubstantiated reports of abuse
• Number of children served by the provider
• Adult/child ratio at the child’s placement home/facility
• Timeliness and content of case reviews
• Number of moves child has had in foster care
• Age, gender, gender preference, race, ethnicity of child
20
CHILD WELFARE/SACWIS DATA SOURCES
and neglect by provider
EXTERNAL SOURCES
• School absence
• School academic and behavioral performance
• School changes and disruptions
• Neighborhood social and economic factors
• Caregiver characteristics (single parent, parent with prior child
welfare contact, homelessness, substance abuse, domestic
violence, involvement with criminal justice; education level)
Potential Impacts
• Better, more stable initial
placements
• Increase in number of
successful reunifications
• Decrease in time children
spend in care
…and ultimately an
improved ability to provide
what is best for the child
21. Using Analytics and Predictive Modeling to Move
From Data to Insight to Action to Impact
We know what a good “end to end” process looks like:
21
Describe
See current
outcomes and
trends, and
understand more
clearly what the
problem looks like
Pursue
Track actions taken and
measure the change in
risk based on
implementation of
prescribed interventions
Predict
Use data mining
techniques and predictive
analysis to better
understand patterns and
help diagnose what,
where, and who needs
intervention
Prescribe
View the high risk
groups, review where
and what the problems
are and system will help
prescribe best-fit
interventions to mitigate
risk
Data Visualization
Descriptive Analytics – what happened and why? What
are the trends? The hotspots?
Predictive Analytics – what factors are driving
performance? What might happen if you make certain
changes/if you do not?
Prescriptive Analytics -- what you can do to move the
needle /where should you put your resources/what
impact are you having?
Business
Questions
• Identify
business
questions tied
to lack of
performance
•Determine
what
variables are
causing the
problem?
Data
Sources
•Use data
sources to
identify and
track Key
Performance
Indicators
Data
Mining
• Use
analytical
tools to mine
historical data
for key
variables
(factors)
related to
child
outcomes
Federal goals
State goals
Program and
child level goals
22. Using Visualization Tools to better communicate with
your front line – put insights in front of your people
Example: Children at High Risk for Maltreatment in Care
22
Drill Down to Every Level:
• Given our history, which
children are most likely to be
at risk of maltreatment in
care?
• Which counties and case
workers have children in their
caseload who are most likely
to be at risk?
• Given our history, which
children are most likely to
remain in care for long periods
of time?
• Who are those children and
what factors are likely to keep
them in care?
Value Delivered:
• Tracks outcomes at the level of individuals – by caseworker, by child, by family
• Allows for immediate identification of children at high risk for maltreatment and long stays
in care and their associated drivers – allowing us to identify points of intervention sooner.
As used in this presentation, “Deloitte” means Deloitte Consulting LLP, a subsidiary of Deloitte LLP. Please see www.deloitte.com/us/about for a detailed description of the legal structure of Deloitte LLP and its subsidiaries. Certain services may not be available to attest clients under the rules and regulations of public accounting.