PREDICTIVE ANALYTICS & DATA MINING:
STRATEGIC IMPLEMENTATION
A Case-Driven Workshop Progression
To Discover What Really Works
ABOUT THIS COURSE
Data mining is essentially a discovery process — a process riddled with common yet elusive strategic pitfalls. Project failure is rarely due to poor model development. Rather, data mining projects often fall short of their potential due to flawed or overlooked assessment, business understanding, project definition and strategic planning specifically for information discovery.
If you are looking for an intensive vendor-neutral and non-promotional introduction to data mining best practices and an approach to predictive analytics which is critical to modeling success, then this course is designed for you. There are no prerequisites for this course. However, participants will benefit by reviewing the CRISP-DM guide ahead of the training.
“Predictive Analytics & Data Mining: Strategic Implementation” offers a concentrated presentation of capabilities, limitations, risks, rewards, use cases, best practices, strategy and lifecycle management. Those in attendance will actively step through the industry standard process for data mining and realize why an advanced degree in statistics, mathematics or computer science is no longer needed to succeed in predictive analytics. Live working sessions reveal real-world obstacles and breakthroughs from which to interpret, learn and apply.
Practitioners seeking to drill down into the tactical implementation of predictive analytics methods may also attend TMA’s Predictive Analytics & Data Mining: Model Development course. The “Model Development” course is the counterpart to this production within the series, two days immediately preceding this course at the same public venue.
Make sure to view the course series overview page to compare the two primary orientations and target the most fitting agenda for your experience, situation and objectives.
WHO SHOULD ATTEND
- IT/IS EXECUTIVES AND MANAGERS: CIOs, CKOs, CTOs, Stakeholders, Functional Officers, Technical Directors and Project Managers
- LINE-OF-BUSINESS EXECUTIVES AND FUNCTIONAL MANAGERS: Risk Managers, Customer Relationship Managers, Business Forecasters, Inventory Flow Analysts, Financial Forecasters, Direct Marketing Analysts, Medical Diagnostic Analysts, eCommerce Company Executives
- TECHNOLOGY PLANNERS: Who survey emerging technologies in order to prioritize corporate investment
- CONSULTANTS: Whose competitive environment is intensifying and whose success requires competency with data mining and related emerging information technologies
BENEFITS OF ATTENDING
- Make better business decisions based on information hidden within your data
- Develop a strong vocabulary and understanding of data mining terminology
- Communicate with confidence among your developers and consultants
- Plan and manage your data mining projects effectively from the start
- Experience firsthand that actual model-building is not as complicated as it might have seemed through the lecture segments
- Leave with resources, contacts and actionable plans to substantially reduce your project preparation time, costs and risks
THE BUSINESS CHALLENGE
Traditionally, organizations use data tactically – to manage operations. For competitive edge, leading organizations use data strategically – to expand the business, to improve profitability, to reduce costs, anticipate behavior, and market more effectively. The mining of data for predictive indicators creates information assets that an organization can leverage to achieve these strategic objectives.
Predictive analytics is a data-driven extension to an enterprise’s decision support system (DSS) architecture. It complements and interlocks with other DSS capabilities such as query and reporting, on-line analytical processing (OLAP), data visualization, and traditional statistical analysis. These other DSS technologies are generally retrospective.
The predictive aspect of data mining may be defined as “the data-driven discovery and modeling of hidden patterns in large volumes of data.” Predictive analytics differs from the retrospective technologies above because it produces models — models that capture and represent hidden patterns and interactions in the data. Via data mining, a user can discover patterns and build models automatically, without knowing exactly what s/he’s looking for.
The resulting models are both descriptive and prospective. They address why things happened and what is likely to happen next. A user can pose “what-if” questions to a data-mining model that cannot be queried directly from the database or warehouse. Examples include: “What is the expected lifetime value of every customer account,” “Which customers are likely to open a money market account,” or “How will production quality be affected if various resources are adjusted?”
WHAT YOU WILL LEARN
- Basic principles and terminology for predictive analytics
- Who is utilizing predictive analytics, and why
- What are common project pitfalls and how to avoid them
- How to define business objectives for a discovery process
- Project deployment, performance and maintenance issues
- Building confidence through hands-on participation
- How to get started
WHAT MAKES THIS COURSE UNIQUE
This course offers a balanced and non-promotional presentation of data mining topics and its role in enterprise decision support. The instructor has been deeply involved with the design, development and deployment of real-world data mining solutions.
This course does not drill deeply into specific algorithms or technical implementation issues. For a comprehensive presentation of model development methodology and techniques, refer to the Predictive Analytics & Data Mining: Model Development course which directly precedes this event at public venues. This level in the series presents strategic and process challenges that are critical to the success of deploying applied models in real world business environments.
Leading commercial and open-source products will be used from a vendor-neutral perspective to illustrate and compare methods — not to showcase tools. Results are drawn from actual data mining applications and interpreted in the context of business impact. Attendees will depart with a binder full of slides, supporting notes, hands-on experience, a valuable index of data mining resources and certification upon attending the full series and passing an on-line exam.
COURSE OUTLINE
INTRODUCTION
- What is predictive analytics?
- Goal driven analysis of large data sets…
- to identify an approach for allocating organizational resources
- that enhances performance on the organization’s self-defined
performance metrics - to better achieve the organization’s business objectives
- using a repeatable, consistent strategy
- Beyond traditional statistics
- Shift your thinking
- The goal of modeling
- Physical systems
- Human behavior
- Goal driven analysis of large data sets…
- Behaviors of interest
- Setting up the game
- Project team
- Phased development cycle
- Definitions
- Data sandbox
- Formulas vs. Model development
- The conflict between algorithm objectives and business objectives
- Why use predictive analytics?
- Definition of data mining
- What data mining is not
- Why mine data?
- The key question is “so what?”
- Successful data mining is goal-directed analysis
- Traditional statistics are insufficient in today’s world
- What can data mining do?
- Data mining opportunities
- Data mining business goals
- Data mining analytic goals
- Why the majority of data mining projects fail
- How much data is needed to develop a model?
- How many variables?
- Rules of thumb
- Types of sampling
- Experimental design
- Data sets used
- Types of data distribution
- Types of decision
- Predictive analytics key technologies overview*
* Methods and techniques are detailed in the Model Development course - Who needs brains when you’ve got software?
- Low-Risk / High-ROI project design
- The business justification for predictive analytics: Goal driven analytics
- Organizational predictive analytics opportunity identification
- Incremental project design
- Single-tailed model development: Identify positive impacts
- Single-tailed model development: Identify negative impacts
- Two-tailed model development: Conflict resolution
- Ranking across the continuum: Adding resolution
- Subdividing dimensions: Adding detail
- Forecasting model development
- A ‘real world’ standardized development process:
The CRoss-Industry Standard Process for Data Mining (CRISP-DM)
- USE CASE WORKSHOP #1
Implement CRISP-DM for a Single-Tailed Model
- Business Understanding (CRISP 1)
- Determine business objective
- Background and business objectives
- Identify decision process
- Business success criteria
- Identify performance metrics
- Calculate current baseline levels of performance
- Determine modeling objectives
- Requirements
- Assumptions
- Constraints
- Risks and contingencies
- Terminology
- Costs and benefits
- Modeling goals
- Modeling success criteria
- Assess resource availability
- Hardware resources
- Sources of data and knowledge
- Personnel sources
- Produce project plan
- Prepare Business Understanding Deliverables
- Determine business objective
- Data Understanding (CRISP 2)
- Review data availability
- Collect initial data
- Data requirements planning
- Selection criteria
- Insertion of data
- Construction of Output variable
- Describe data
- Volumetric analysis of data
- Attribute types and values
- Keys
- Review assumptions and goals
- Explore data
- Statistical analysis
- Data exploration
- Suppositions for future analysis
- Verify data quality
- Data Understanding Deliverables
- Initial data collection report
- Data description report
- Data exploration report
- Data quality report
( Note: CRISP-DM Parts 3, 4 and 5 are detailed in the “Model Development”
course and extended into practice in this course. It is helpful but not necessary
to have had the tactical drill-down into these Parts prior to their implementation. )
- Data Preparation (CRISP-DM 3)
- Modeling (CRISP-DM 4)
- Evaluation (CRISP-DM 5)
- Deployment (CRISP 6)
- Plan deployment
- Develop monitoring and maintenance plan
- Produce final report
- Project review
- Deliverables
- Deployment plan
- Monitoring and maintenance plan
- Final report
- USE CASE WORKSHOP #2
- Second CRISP-DM pass for a two-tailed model implementation
- Business Understanding (CRISP-DM 1)
- Data Understanding (CRISP-DM 2)
- Data Preparation (CRISP-DM 3)
- Modeling (CRISP-DM 4)
- Evaluation (CRISP-DM 5)
- Deployment (CRISP 6)
- EXTENDED MODELING TOPICS
- WRAP-UP AND NEXT STEPS
- PA&DM: “Model Development” Course
- Certification Exam (for those who complete the series)
- Product training courses
- Keep learning!
- Supplementary materials and resources
- Conferences and communities
- Get started on a project!
Upcoming Sessions
Sign Up Early and Save
On-Site Available
Data Mining Webinar
Next Event
Why Train With TMA?
Attendee Comments
“The presentation from Tony Rathburn was without exaggeration the best I have heard from modelling practitioners in the 20 years I have been a data miner.”
Senior Director Operational Analytics
Australian Taxation Office
“I have been studying material on data mining and predictive analytics for more than a year and have actually dabbled in using it. But this class finally made it real to me. It took me out of the actual mathematics / statistics associated with the practice and helped me understand how to frame the business problem, prepare the data and models to support the business definition and properly apply the methods that I studied in the books. I felt like I left the class armed with the insight that I need to actually transition the practice from theory into reality.”
Strategic Planning &
Business Systems Management
Idaho National Laboratories
“Tony and Keith were fantastic! I learned a lot from them of what to do and not to do — not only for smaller projects but also for the larger initiatives. There were many takeaways for what makes a successful model and what to avoid when approaching this practice.”
Business Operations Analyst
Toshiba America Medical Systems
“There is no better way to learn Data Mining than to do it yourself. Take this course for an invaluable hands-on experience of project definition and implementation. Even if your organization does not adopt predictive analytics as standard, you will have acquired a much needed skill set.”
Wage and Investment Research
Internal Revenue Service
“Great presentation and summarization of predictive analytics. I sat through two days of the Predictive Analytics World conference and got less from that than I received in the first two hours of this course! Thanks!”
“This course gave me just what I needed: a clear conceptual idea of how a data mining project is designed and implemented, and the hands-on to gain confidence in the process.”
Market Information Manager
Bank of Hawaii
“This course opened my eyes to the big picture in a practical way. The content of the Project Implementation course was very clear and responsive to my needs. My questions were answered directly and clearly. Exceeded my expectations!”
ITS – Business Solutions
Surewest Communications
“A few months ago, I attended Prediction Impact’s data mining course. It provided a good orientation to predictive analytics. But I wanted to learn how to really apply data mining at the project level. TMA’s course series provided the comprehensive and pragmatic approach I was truly seeking that will allow me to dive confidently and properly into the practice.”
Aspiring Data Mining Practitioner
Lanham, MD
“I would recommend TMA’s Project Implementation course to executives weighing the costs and benefits of such projects within their organizations. Tony approaches the course from a business management perspective and presents the concepts in real-world cases making the task of visualizing use of the process in one’s own business a snap!”
AVP, Information Technology
iPay, LLC
“When the only complaint is that the course could be longer, I think you’ve got an excellent class! I very much enjoyed the instructor’s use of a real data set to demonstrate principles taught throughout the entire class. The instructor went out of his way both before and during the class to help me to translate the class material to my own work.”
Senior Engineer,
Biological Technologies Analysis Solutions
Wyeth
“The instructor’s presentation was quite thoughtful and very well organized. I came away with a solid map for the ever changing data mining landscape.”
Divisional Scientist
BBN Technologies
“Statisticians and Analysts alike can benefit from this Data Mining course. It is interesting to view the business objective from the other side of the coin. Exploratory Data Analysis in Data Mining is fun because the causality constraint of classical Statistics is relaxed. Take this course and open up to another way of dealing with large data sets.”
Wage and Investment Research
Internal Revenue Service
“The ‘Project Implementation’ course successfully takes the broad and complex subject of data mining and organizes and explains it in a very logical and understandable way. The training provides real-life examples of the various aspects of data mining and a proven approach to successfully achieving desired results. I can highly recommend TMA’s Data Mining courses to anyone interested in understanding the broad landscape of data mining and predictive analytics.”
Principal, Technology Services Group
Computer Sciences Corporation
“If you want a thorough introduction to predictive analytics at the project level with a wealth of real world experience solving problems, then Tony’s your guy.”
Professor of Marketing
Ferris State University
“A great experience. I would recommend this course for anyone interested in Predictive Analytics.”
Analyst, Customer Insights
Giant Food Stores
“This class, by far, is the most interesting, motivating and applicable class I have taken in a very long time. Tony provides a refreshingly different perspective on predictive modeling and approach methodology. Not only would I absolutely recommend this course to any colleague or anyone interested in the practical, yet powerful insights into predictive modeling, but I may look into additional learning and or professional services opportunities. I can’t wait to get back to work and jump right into applying the concepts and learnings.”
“Both instructors in the series did a fantastic job of getting me up to speed in predictive analytics much faster than any book (or probably any other training class or conference) available.”
Knowledge-Based Systems Engineer
Compliance Technologies, Inc.
“Attending The Modeling Agency’s series was a tremendously rewarding experience, helping me to ‘de-mystify data mining’ and interface with exceptionally intelligent people who live in the data mining world.”
Apparel, Merchandising, and Textiles
Washington State University
