• This field is for validation purposes and should be left unchanged.
Guidance and results for the data-rich, yet information-poor.


Transforming Data to Goal-Driven Insight

for the Data-Rich yet Information-Poor

Two Days
$1,495 USD
INFORMS Professional Development Units: 18


This two-day course will prepare functional managers and analytic practitioners to finally make sense of data analytics and take control of the analytic process. “Data Analytics for Action & Impact” develops core skills for data analytics and lays the foundation for data-intensive analytic projects that deliver insight, clarity, confidence and actionable decision support.

Attendees will learn the four major types of problems encountered in commercial and public sector applications, and walk through a structured development process to grasp key issues they will face for each problem type. Unlike any other analytic or statistical training, this course maintains a decision strategy focus supported by work-along exercises on multiple data sets. The exercises allow attendees to experience and organize the natural messiness of data analytics while reinforcing the skills to effectively drive their own projects. Participants return with a rich set of course notes, analytic process guides, workshop session files and follow-on resources.


The density of material establishes an aggressive pace in the presentation of content. Statistical background is helpful, but not required.  Read the Series Overview to understand this event’s place and function within the full course series progression.


This course 1) builds core capabilities for those who are new to data analytics; 2) provides a more functional, streamlined and strategic mindset for those with classical statistical training; and 3) serves as a structured platform for those wishing to proceed into more advanced analytics projects with greater confidence. “Data Analytics for Action & Impact” is suited for the following roles:

    • Functional Managers – who desire a practical appreciation of core analytic methods in a fast-paced, impact-focused course in order to interact more effectively with analysts and IT staff on departmental data analysis projects, regardless of their prior statistical background.
    • Organizational Analysts – who need to transform their quantitative capabilities into a purposeful approach to impactful decision analytics by letting go of ad hoc statistical techniques and focusing specifically on a framework of core analytic strategies most appropriate for tackling common goal-driven problems.
    • Experienced Statisticians – who may be statistical wizards at the quantitative level, but realize they will be far more valuable to the organization upon learning how to adapt their classical training into more of a goal-driven mindset for streamlined, agile and targeted data analytics that translate into measurable impact for leadership.
    • IT Specialists – who wish to gain a better appreciation of the overall analytic process in order to more effectively prepare resources for data analysis and integrate resulting decision models within the infrastructure of today’s sophisticated data storage and access environments.
    • Business Intelligence Team Members – who realize the need to take a step back and reinforce their essential core analytic capabilities in order to gain solid traction when proceeding into more advanced analytics fields such as data mining, predictive modeling, machine learning, knowledge discovery, unstructured text analysis, and data-driven decision support.


    • Focus on core analytic issues, strategies, methods and techniques most appropriate for organizational decision making
    • Understand in plain English what the algorithms do, and how true descriptive analytics relate to decision support
    • Unify project teams – from statisticians to leadership – in order to establish a common strategy, framework and process for greater coordination, efficiency, clarity and impact
        • For analysts to obtain clear direction on analytic goals and delivery requirements
        • For leadership to better understand and trust what the analyst delivers
    • Leave ad hoc, esoteric and academic statistical exercises behind in lieu of targeted, insightful and understandable analytic outcomes that drive decision models with residual benefit
    • View content through an organized series of live work-along exercises in order to directly experience strategic issues as well as how to tactically implement at the project-level
    • Leave with the resources, contacts and actionable plans to substantially increase analytic capabilities while minimizing dead ends


The ability to make effective and timely decisions driven by valuable information hidden within a rapidly increasing mass of data is critical to the success of modern organizations and managers. The advancement of analytic and reporting options, along with the proliferation of big data delivery platforms and analytic software suites create an environment where functional managers must rely heavily upon their analysts and IT staff for critical insight.

It is typically not the responsibility of analysts and IT specialists to focus on strategic-level decision processes. Yet, analytics will fall short of its potential without adequate context, sound problem definition and results translation. At the same time, statisticians and IT professionals are often misguided by managers who lack core analytic skills to effectively communicate their needs, or fully understand the results.

The gap between these roles leaves the manager to subjectively interpret results from analytical models that emphasize quantitative sophistication and artificial metrics instead of objective, data-driven solutions. And in business, the product of data analysis is not the analysis. The real products of the analysis are the insights gained and the impact measured.

The intent of this course is to bridge the critical translation gap between team members that cause the vast majority of analytic projects to fall short of their potential. Managers who attend this class will establish a stronger appreciation of core analytic methods and process to better interpret, evaluate and trust what the analyst delivers. Statisticians, IT professionals and analysts will learn how to approach data analysis in a structured and purposeful way that translates well for leadership, and directly impacts business performance.


    • Discover, monitor and clearly report the primary analytic contributors that affect strategic decision processes and their impact on performance metrics that are important to leadership
    • Classify the four major types of analysis projects and match the best suited core analytic methods
    • Develop a six-phase methodology for evaluating and validating business insights
    • Structure and organize a wide range of data analysis topics from a project-oriented, decision-process perspective
    • Identify critical characteristics of available data fields and leverage treatments to significantly enhance their contribution to the decision making process
    • Maneuver a structured process to evaluate the effectiveness of individual attributes and their value to enhancing a predefined objective
    • Establish a solid foundation for more advanced analytic practices such as predictive modeling and data mining


Participants are welcome but not required to bring laptop computers. Live application Illustrations will be conveyed in the form of work-along sessions. Attendees may either watch the instructor work through the exercises, or take their own approach in parallel. Consider whether you learn better by watching or doing. Completed worksheets will be given to all attendees at the end of the class. All other course materials will be available at the training site.


This course directly addresses the critical yet common lack of effective coordination and hand-off between analysts, IT professionals and management. While each may be fully effective in their own domain, there is a significant loss of translation between roles in which critical context is lost. “Data Analytics for Action & Impact” targets this costly gap and enables all players to execute effectively across roles.

Unlike training that drills into various analytic techniques and leaves it to the attendee to figure out how to use them effectively, this intensive two-day course conveys analytics-in-action through work-along sessions. The sessions convey the four types of problems that dominate commercial and public sector implementations:

    • Value Estimation
        • Estimating a value given specific conditions
        • Projecting the next step in a sequence
    • Classification
        • Identifying a category given specific conditions
        • Identifying groups in large, complex environments

Attendees learn how to apply core analytic methods to defined problem types in order to reveal insights critical to organizational success. Participants then reference a seven-phase analytic development methodology to act as an analytic framework from which team members may collectively stand up a purposeful data analysis practice.

TMA’s Modeling Practice Framework™

To best convey and reinforce the analytic model development process, each exercise is labeled in a supporting process guide as “Challenge, Approach and Solution”:

magnifying-glass Challenge
The application context, strategic objective and functional target of the exercise is presented in the Challenge section.
gear Approach
The actual problem approach and specific steps required to solve the exercise are itemized in the Approach section.
light-bulb Results
The intended results are presented in the Results section and expressed in terms that were defined in the Challenge section.


This course follows a formal analytic model development process through four basic project types with reinforcement cycles. As such, the following outline is a topic list only; not an ordered schedule.

    • Introduction
        • Core concepts
        • Using technology effectively
        • Big Data versus fat data for analytics
    • The Four Basic Project Types
        • Predicting a value given specific conditions
        • Identifying a category given specific conditions
        • Predicting the next step in a sequence
        • Identifying groups
    • The Motivation for Analytic Modeling
        • Enhanced performance: An incremental strategy
        • You will never have a perfect model
        • Think of business as a game
        • Performance metrics: Your compass to progress
        • A ‘Rear View Window’ perspective makes it hard to drive forward
        • Conditional decision-making given expected circumstances
        • The critical combination: Information & Strategy
    • Mathematical Modeling
        • Formulas and their parts
        • Anticipating outcomes from environmental conditions
        • Projecting profit
        • How you think about an outcome is essential
        • People are inconsistent, unreliable and messy
        • There is never enough data
        • Samples and populations
    • Model Development in Three Steps
        • Training
        • Testing
        • Validation
    • A Basic Guide to the Modeling Practice Framework
        • Assess
            • Who is on the project team?
            • What is the attitude of leadership and the team toward analytics?
            • What is the current practice for analytics?
            • What are all candidate projects?
            • What are objectives, requirements and qualifyers for each candidate project?
            • What is the current baseline level of performance?
            • What are cost-benefit thresholds?
            • What are existing and desired performance benchmarks?
            • Where are all the data sources?
        • Plan
            • What are the roles and experience required for each team member?
            • What’s involved in a data reconnaisance?
            • What is the quality of the data sources?
            • Does the environment, resources and situation support each modeling objective?
            • Define data sufficiency and scope
            • How should a data sandbox be developed?
            • What will the operational environment be?
            • What are options and specifications for model deployment?
            • Which projects are truly viable and how should they be prioritized?
        • Prepare
            • What criteria should drive the analytic culture and mindset shift?
            • How should team responsibilities be refined?
            • What data should I include in my data sandbox?
            • What does a record look like?
            • What does the outcome or target variable look like?
            • What data representations should I use?
            • What data transformations should I use?
            • How do I select variables for my model?
            • What modeling methods should be considered?
            • How do I build my Training/Test/Validation data sets?
            • What is in a Modeling Plan and who should review and approve it?
        • Model
            • Algorithms give us formulas, not answers
            • Formulas create a composite perspective
            • There is no such thing as a ‘good’ algorithm
            • Selecting the right tools for the job
            • The environment is also not consistent
            • Does the story make sense?
            • Not all data is created equal
            • Some data is not ‘math compatible’
            • Data Attributes
                • Qualitative
                • Nominal
                • Ordinal
                • Interval
            • Multiple models are usually needed
            • Adoption by domain experts, end users and leadership
            • Project failure is not the worst outcome
            • Some ‘cool’ features are just ‘nice junk’
            • Variability: Sometimes we want it, sometimes we don’t
            • Perfect correlation is not a good thing
            • No correlation is a waste of time
            • How ready are we for deployment?
        • Validate
            • Are we selecting the most strategic option?
            • Have we maintained an focus on ‘organizational performance’?
            • Is validation expressed in context with the original defined goal?
            • How do finalist models perform against established  benchmarks?
            • Have we formed a consistent implementation strategy?
            • What is the outcome of a dress rehearsal and trial deployment?
            • How to pick a ‘Challenger’
            • Confirming we picked a good Challenger
            • Preparing a final rollout plan
        • Deploy
            • Reviewing all project functions
            • Evaluating the expected performance of our Challenger
            • Adoption by domain experts
            • Adoption by end users
            • Preparing leadership for a new decision process
            • Project failure is not our worst outcome
        • Monitor
            • Adapting to a changing environment
            • Creating a maintenance schedule
            • Determining model life expectancy
            • Establishing maintnenance triggers
            • Assigning monitoring responsibilities
            • Buiding the performance dashboard
            • Identifying new data sources
            • Recording ongoing organizational changes
            • Preparing for the next Framework cycle
    • Development Process by Project Type
        • Predicting a Value Given Specific Conditions
            • Relationships in Data
            • Estimating the future value of an outcome based on known current conditions
            • Additional precision is more difficult to obtain and may put your project at risk
            • Build (observe or work-along)
        • Identifying a Category Given Specific Conditions
            • Shifting our thought process when the target outcome can take on a limited set of values
            • The real world is not normally distributed
            • The unknown attribute we are trying to predict is critical
            • The misuse of regression is dangerous to your financial health – and to your organization
            • Playing the odds
            • The world is round and other non-linear realities
            • We need a different kind of formula… sort of
            • Classification is concerned with proportions, not precision
            • Break-out session (observe or work-along)
        • Predicting the Next Step in a Sequence
            • Time series problems
            • Estimating the future value of an outcome by considering the direction and distance of change relative to our known position
            • Signal versus Noise
            • Plan
            • Break-out session (observe or work-along)
        • Identifying Groups
            • Big Data versus Big Data Analytics – Implementation issues
            • Putting Fat Data on a Diet
            • Plan
            • Break-out session (observe or work-along)
        • Wrap-up
            • The complexity of large-scale analytics
            • Specialization in project teams
            • The power of adapting core analysis skills
            • Where to go from here
                • Predictive analytics, business intelligence and other advanced technologies
                • Resources to get you on your way

The Modeling Agency, LLC, is registered with INFORMS (the INstitute For Operations Research and the Management Sciences) as a Recognized Analytics Continuing Educational Provider for the CAP® (Certified Analytics Professional) program. The CAP® credential provides analytics professionals with a means to distinguish themselves and demonstrate to employers, colleagues, and the public that they are knowledgeable analytics professionals. Courses provided by The Modeling Agency, LLC, are automatically accepted by INFORMS when claimed by credential holders as evidence of continuing education. For more information about the CAP® program, including requirements, eligibility, benefits, preparation, and exam dates, please visit the INFORMS website at www.informs.org/certification.

Upcoming Sessions

August 18 & 19, 2016
October 20 & 21, 2016

Sign Up Early and Save

Events Limited to 20 Seats

On-Site Available

Inquire by Phone or Email

Data Mining Webinar

Learn How to Get
Predictive Modeling Off
the Ground and Into Orbit

Next Event

Wednesday, June 8, 2016
11am EDT / 8am PDT
90-Minute Live Interactive Event

Why Train With TMA?

Determine whether TMA training is right for you, and learn why TMA is truly the best option for live classroom analytics training.

Attendee Comments

“Data Analytics is not merely about the statistical techniques, but also the ability to understand the context of the problems, to ask the right questions, and to establish the performance metrics that are relevant and crucial to answer these questions. It requires a service design mentality, and that’s what this class delivers”

Ting-Shuo Yo
Data Scientist
ASUSTeK Computer inc.

“The instructor is also a consultant. He fully understands real world scenarios, and a project approach to effective execution.”

Jean M. Cotis
Application Development Manager
UPS Freight

“I look forward to applying what we learned during this course to current and new projects. We will be more organized, efficient and effective by applying the concepts and techniques delivered in this class.”

Sean Schmitt
US Customs and Border Patrol

“No fluff at all. The instructor consistently provided specific, practical and understandable advice about complex ideas and processes. He explains things very clearly, backs up his answers with real-world exampls and is patient with questions.”

Partner Conference Production

“As someone without a formal degree, analytics can be a daunting word. This course is approached in a very consumable way and without the blunt theory of academia. It is practical and applicable, which is exactly what analytics needs in order to support organizational objectives.”

Carmen Schwesinger
Government of Alberta