Services: Data Mining Project Assessment, Data Preparation For Data Mining, Data Mining Model Development, Data Mining Model Deployment, Data Mining Course: Overview for Project Managers, Data Mining Course: Overview for Practitioners, Customized Data Mining Engagements
Insight 1: Find Correlated Variables Prior to Modeling Topic: Data Understanding and Data Preparation Sub-Topic: Feature Selection Insight 2: Beware of Outliers in Computing Correlations Topic: Data Preparation Sub-Topic: Outliers Insight 3: Create Three Sampled Data Sets, not Two Topic: Modeling Sub-Topic: Sampling Insight 4: Use Priors to Balance Class Counts Topic: Modeling Sub-Topic: Decision Trees Insight 5: Beware of Automatic Handling of Categorical Variables Topic: Data Understanding and Data Preparation Sub-Topic: Feature Selection and Creation Insight 6: Gain Insights by Building Models from Several Algorithms Topic: Modeling Sub-Topic: Algorithm Selection Insight 7: Beware of Being Fooled with Model Performance Topic: Data Evaluation Sub-Topic: Model Performance
Client List and Case Studies
Upcoming Data Mining Seminars A Practical Introduction to Data Mining Upcoming courses (nationwide) Data Mining Level II: A drill-down of the data mining process, techniques, and applications Data Mining Level III: A hands-on day of data mining using real data and real data mining software Anytime Courses Overview for Project Managers: Train project managers on the data mining process. Overview for Practitioners: Train practitioners (data analysts, project managers, managers) on the data mining process.
Data Mining Resources, Books, Websites, White Papers, Presentations, Tutorials
Mr. Abbott is a seasoned instructor, having taught a wide range of data mining tutorials and seminars for a decade to audiences of up to 400, including DAMA, KDD, AAAI, and IEEE conferences. He is the instructor of well-regarded data mining courses, explaining concepts in language readily understood by a wide range of audiences, including analytics novices, data analysts, statisticians, and business professionals. Mr. Abbott also has taught applied data mining courses for major software vendors, including Clementine (SPSS), Affinium Model (Unica Corporation), Model 1 (Group1 Software), and hands-on courses using S-Plus and Insightful Miner (Insightful Corporation), and CART (Salford Systems).
Courses and Events
- PAW for Business (Livestream Classroom), May 20 - 25, 2021
- TDWI Data Science Bootcamp Seminar (Austin, TX / Virtual Classroom), September 20 - 22, 2021
Follow Dean on Twitter
Upcoming Courses and Events (Nationwide)
Predictive Analytics World Converence (Livestream):
A collection of models is greater than one. Ensemble models are a fundamental, key technique for improving machine learning model accuracy. An ensemble model combines predictions from several to thousands of individual models into a single, new model prediction. Model ensembles are usually more accurate than any single model and are typically more fault tolerant. Are model ensembles an algorithm or an approach? How can one understand the influence of key variables in the ensembles? Which options affect the ensembles most? This workship dives into the key ensemble approaches, including Bagging, Boosting, Random Forests, and Stochastic Gradient Boosting. Attendees will learn "best practices" and attention will be paid to learning and experiencing the influce various options have on ensemble models so that attendees will gain a deeper understanding of how the algorithms work qualitatively and how one can interpret resulting models. Attendees will also learn how to automate the building of ensembles by changing key parameters.
- Thursday, May 20, 2021 (8:00am - 3:00pm PDT)
TDWI Data Science Bootcamp Seminar (Austin, TX / Virtual Classroom):
Data science has been called "the sexiest job of the 21st century" and with good reason -- the size and breadth of our data is growing exponentially, making the ability to understand that data more and more challenging. This course provides a complete overview of the data science process and drills into detail on key tasks that occur before analytic model-building begins. A project-oriented framework is used to introduce the discipline of data science, placing activities in the context of business value and covering key concepts every data scientist needs to know. Each project must define objectives, collect and integrate data, prepare it for analysis, perform the analysis, and deploy the results. Whether the end goal of the project is reporting, visualization, descriptive modeling, or predictive modeling, the same principles apply. For each stage, key principles are extablished and illustrated through real-world examples. Next, the course breaks down the data science activities that occur before analytic modeling can begin. You may have heard that data scientists spend 80 percent of their time sourcing, cleaning, and preparing data. Although this may be an exaggeration (or not!), data preparation is certainly a large and important part of data science and predictive analytics. Data often does not start out in the ideal format; it may contain bad values, it may not be easily accessible, or it may need to be transformed before we can start exploring the data and building models.
- Monday, September 20, 2021 (9:00am - 5:00pm CT)
At its core, data science leverages machine learning and statistics-based algorithms to find patterns in data. The second day of the TDWI Data Science Bootcamp covers the most commonly used algortithms in data science, providing overviews of what they are and how they find patterns -- without an in-depth treatment of the mathematics. You will learn how to match these common algorithms to analytics objectives and best practices to ensure they lead to business results. We will explore similarities and differences between the algorithms, what types of patterns each can find most easily, and which patterns are more difficult for each to uncover. You will learn how data preparation and feature creation (from Day One) influence the accuracy of your results. Explanations of model accuracy will cover standard metrics, such as mean-squared error and percent correct classification, as well as other metrics that are more useful in practice. Analytic models can only lead to business impact if they are trusted by stakeholders who are willing to act on their results. You will learn how to explain models and model accuracy to business stakeholders. Model interpretation strategies and metrics for complex algorithms will also be described, equipping you with the communication techniques needed to generate business value.
- Tuesday, September 21, 2021 (9:00am - 5:00pm CT)
During the final day of the TDWI Data Science Bootcamp, you will learn how advanced modeling techniques can be layered on top of the foundational machine learning algorithms (covered on Day Two), and how model interpretation is extended accordingly. Demonstrations will show how to build and interpret these advanced models using actual examples. An extensive overview of model ensembles will cover principles and practices and a variety of specific techniques. You will also be exposed to algorithms that are frequent winners of international modeling competitions such as random forests and gradient boosting machines. You will learn about sampling and re-sampling strategies, interpretation of complex models, randomization experiments to build and interpret models, and advanced feature creation approaches.
- Wednesday, September 22, 2021 (9:00am - 5:00pm CT)
Customer On-Site Courses
Overview for Project Managers: Train project managers on the data mining process.
Overview for Practitioners: Train practitioners (data analysts, project managers, managers) on the data mining process.
Past National Courses and Presentations
Mega-PAW Conference 2019, Las Vegas, NV:
Customer Lifetime Value (CLV) is considered one of the most useful measures for business to consumer (B2C) companies, and is usually considered more valuable than other measures like conversion rate, average order value, and purchase frequency. If an accurate measure of CLV can be obtained, companies can determine which customers to prioritize with marketing messages and discount offers. Basic CLV is actually quite easy to compute. But more sophisticated analysts and statisticians use parametric models that take into account purchase frequency, purchase recency, churn risk, and even customer age. These models can provide value estimates 5, 8, and even more than 10 years into the future. However, most retailers, while interested in lifetime value, are especially interested in estimating near-term customer value so they can create effective marketing strategies now. In this talk, SmarterHQ's founding Chief Data Scientist Dean Abbott describes non-parametric machine learning approaches to calculating customer value for retail that can accommodate additional measurements and features not typically used in CLV models. Model summaries and accuracy metrics for several retail clients will illustrate the effectiveness of this style of model.
- Las Vegas, NV - June 18, 2019
Once you know the basics of predictive analytics and machine learning—including data exploration, data preparation, model building, and model evaluation—what can be done to improve model accuracy? One key technique is the use of model ensembles, combines several or even thousands of models into a single, new model score. It turns out that model ensembles are usually more accurate than any single model, and they are typically more fault tolerant than single models. Are model ensembles an algorithm or an approach? How can one understand the influence of key variables in the ensembles? Which options affect the ensembles most? This workshop dives into the key ensemble approaches, including Bagging, Random Forests, and Stochastic Gradient Boosting. Attendees will learn “best practices” and attention will be paid to learning and experiencing the influence various options have on ensemble models so that attendees will gain a deeper understanding of how the algorithms work qualitatively and how one can interpret resulting models. Attendees will also learn how to automate the building of ensembles by changing key parameters.
- Las Vegas, NV - June 17, 2019
Preeminent consultant, author and instructor Dean Abbott, along with Rexer Analytics president Karl Rexer, field questions from an audience of predictive analytics practitioners about their work, best practices, and other tips and pointers.
- Las Vegas, NV - June 18, 2019
TDWI Coronado Solutions Summit: Coronado, CA:
We live in an age of big data, where companies collect information on nearly every aspect of customer experiences. With more data, companies can understand shopper behavior and intent with far more precision than ever before, and with these insights, provide shoppers with timely, relevant information that improves the shopper experience. However, personalization done irresponsibly can come across as invasive and off putting, increasing customer fears about data privacy and data misuse. Privacy concerns have led to regulations such as The General Data Protection Regulation (EU) 2016/679 ("GDPR"), enacted May 25, 2018, and new US regulations such as the California Consumer Privacy Act (CCPA), to be enacted January 1, 2020. This talk will describe how these two worlds can co-exist, summarizing consumer preferences for privacy and how brands can comply with legal and personal preferences and still recognize and understand their audiences. Descriptions of powerful personalization strategies that comply with privacy regulations will be provided through real-world use cases.
- Coronado, CA - June 4, 2019
2019 BAFT Global Annual Meeting – The Americas, San Diego, CA:
The increased use of digital technology is creating massive amounts of data resulting in data deluge. But this digital transformation comes with challenges, particularly around data management. The opportunities that arise from improved data collection, security and management will enable financial institutions to offer a better customer experience thereby boosting customer loyalty, revenues and brand reputation. This session will explore ways to ensure a successful data management strategy.
- San Diego, CA - April 30, 2019
KNIME Spring Summit 2019, Berlin, Germany:
- Berlin, Germany - March 18, 2019
This workshop describes why Random Forests and Gradient Boosted Trees are so much more accurate than individual decision trees or even other ensemble approaches (such as Bagging). We'll also look at examples of how to build them in KNIME, and provide practical warnings of how they can fail.
- Berlin, Germany - March 20, 2019
Predictive modelers often start learning how to build models with linear methods and statistical models. These approaches usually assume smaller data, known distributions, no missing values, and more, and as a result, make building and assessing the models straightforward, blessed with many very good metrics to use to judge model accuracy and the influence of individual predictor variables. As we build models using non-parametric, highly nonlinear techniques, many of these measures no longer make sense or are impossible to apply.
- Berlin, Germany - March 19, 2019
DAMA Portland Metro Chapter, Portland, OR:
- Portland, OR - October 18, 2018
KNIME Fall Summit 2018, Austin, TX:
- Austin, TX - November 8, 2018
Predictive modelers often start learning how to build models with linear methods and statistical models. These approaches usually assume smaller data, known distributions, no missing values, and more, and as a result, make building and assessing the models straightforward, blessed with many very good metrics to use to judge model accuracy and the influence of individual predictor variables. As we build models using non-parametric, highly nonlinear techniques, many of these measures no longer make sense or are impossible to apply. This workshop summarizes a half dozen ways to use randomization in the model building process. For each, principles describing the approach will be provided, followed by demonstrations of the techniques using KNIME. This course is intended for Data Scientists, Statisticians, Mathematicians, Computer Scientists, and IT Professionals who build and interpret predictive models. Prior predictive modeling experience is very helpful.
- Austin, TX - November 7, 2018
PAW Conference, Berlin, Germany:
- Berlin, Germany - November 14, 2018
Predictive analytics has moved from a niche technology used in a few industries, to one of the most important technologies any data-driven business needs. Because of the demand, there has been rapid growth in university programs in machine learning and data science. These teach the science well, but do not describe the tradeoffs and the “art” of predictive analytics.
- Berlin, Germany - November 12, 2018
Predictive Analytics World Conference, Las Vegas, NV:
As crucial as it is, data preparation is perhaps the most under-taught part of the predictive analytics (machine learning) process, even though we spend 60%, 70%, even up to 90% of our time doing data preparation steps. This workshop will cover the most important aspects of data preparation. Each of these topics will be described and connected to specific modeling algorithms that benefit from the data preparation step.
- Las Vegas, NV - June 4, 2018
As data science captures more attention from decision makers, translating the models from the language of the analyst into a language of the decision maker has become an important topic at conferences and in journals. It used to be that the focus on data storytelling was on visualization techniques. While this is important, as analyses become more complex, the task of interpreting the models likewise becomes more complex. Before we can decide on visualization techniques, we first need to uncover what to visualize. In this presentation, Mr. Abbott will describe ways to unravel complex descriptive and predictive models so they can be explained and visualized using machine learning models and resampling techniques.
- Las Vegas, NV - June 6, 2018
Preeminent consultant, author and instructor Dean Abbott, along with Karl Rexer of Rexer Analytics, field questions from an audience of predictive analytics practitioners about their work, best practices, and other tips and pointers.
- Las Vegas, NV - June 6, 2018
Once you know the basics of predictive analytics and have prepared data for modeling, how do you build models with the best possible accuracy? This workshop explains the principles of the most popular ensemble techniques found in software and used in analytics competitions: model ensembles. The instructor will explain Bagging, Boosting, Random Forests, and Stochastic Gradient Boosting. Attendees will build each type of ensemble using SPM, and adjust learning parameter settings to improve model accuracy.
- Las Vegas, NV - June 7, 2018
Predictive Analytics World Conference, New York, NY:
Once you know the basics of predictive analytics and have prepared data for modeling, how do you build models with the best possible accuracy? This workshop explains the principles of the most popular ensemble techniques found in software and used in analytics competitions: model ensembles. The instructor will explain Bagging, Boosting, Random Forests, and Stochastic Gradient Boosting. Attendees will build each type of ensemble using SPM, and adjust learning parameter settings to improve model accuracy.
- New York, NY - November 2, 2017
- New York, NY - October 31, 2017
Preeminent consultant, author and instructor Dean Abbott, along with Rexer Analytics president Karl Rexer, field questions from an audience of predictive analytics practitioners about their work, best practices, and other tips and pointers.
- New York, NY - October 31, 2017
As crucial as it is, data preparation is perhaps the most under-taught part of the predictive analytics (machine learning) process, even though we spend 60%, 70%, even up to 90% of our time doing data preparation steps. This workshop will cover the most important aspects of data preparation. Each of these topics will be described and connected to specific modeling algorithms that benefit from the data preparation step.
- New York, NY - November 1, 2017
Human Capital Analytics and Workforce Planning Event, San Diego, CA:
Predictive Analytics and the related fields of Data Science and Machine Learning have become an integral part of organizations who want to become “data-driven”. But there is more to predictive analytics that data and algorithms. This workshop is aimed at business professionals and managers who are used to looking at data and trying to make sense of data but want to move beyond reporting and summary statistics (like averages) to gain deeper insight into their data.
- San Diego, CA - June 11, 2018
KNIME Fall Summit 2017, Austin, TX:
- Austin, TX - November 3, 2017
Predictive Analytics World Conference, Berlin, Germany:
As data science captures more attention from decision makers, translating the models from the language of the analyst into a language of the decision maker has become an important topic at conferences and in journals. It used to be that the focus on data storytelling was on visualization techniques. While this is important, as analyses become more complex, the task of interpreting the models likewise becomes more complex. Before we can decide on visualization techniques, we first need to uncover what to visualize. In this keynote, Mr. Abbott will describe ways to unravel complex descriptive and predictive models so they can be explained and visualized using machine learning models and resampling techniques.
- Berlin, Germany - November 13, 2017
Predictive analytics has moved from a niche technology used in a few industries, to one of the most important technologies any data-driven business needs. Because of the demand, there has been rapid growth in university programs in machine learning and data science. These teach the science well, but do not describe the tradeoffs and the “art” of predictive analytics. This workshop will cover the practical considerations for using predictive analytics in your organization through the six stages in the predictive modeling process.
- Berlin, Germany - November 15, 2017
PASS Business Analytics Day, La Jolla, CA:
As the world of data expands, data science is becoming more challenging to understand, pushing this job function to become an essential role in business now more than ever before. As organizations collect and process more and more data, turning these data lakes into actionable decisions creates obstacles for even the most forward-looking companies. This full-day, intermediate workshop covers data science in depth, compares it with related analytics disciplines, and unpacks key algorithms and approaches to help attendees stay competitive in this field.
- La Jolla, CA - October 3, 2017
TDWI Data Science Bootcamp, Anaheim, CA:
Data science has been called “the sexiest job of the 21st century” and with good reason—the size and breadth of our data is growing exponentially, making our ability to understand that data more and more challenging. This session defines data science, describes how it is similar and different from related analytics disciplines, and the key concepts every data scientist needs to know. In this overview, data science will be described in a project-oriented framework. Each project must define objectives, collect and integrate data, prepare it for analysis, perform the analysis, and deploy the results. Whether the end-goal of the project is reporting, visualization, descriptive modeling, or predictive modeling, the same principles apply. For each stage, key principles will be described and real-world examples will illustrate the meaning of these principles.
- Anaheim, CA - August 7, 2017 (two sessions)
TDWI Conference, Chicago, IL:
Predictive analytics (PA) has emerged as a go-to approach to creating data-driven business decisions. The science of PA is not new nor are the algorithms commonly used in PA. What is new is how organizations are leveraging predictive techniques and insights to drive business value. This tutorial will describe tasks performed by data engineers and predictive models who want to build data for predictive modeling. We will cover three of the six stages of predictive analytics as defined in CRISP-DM, the Cross-Industry Process Model for Data Mining: Business Understanding, Data Understanding, and Data Preparation, Throughout the tutorial, concepts will be illustrated with data and real use cases.
- Chicago, IL - May 9, 2017
Predictive analytics (PA) has emerged as a go-to approach to creating data-driven business decisions. The science of PA is not new nor are the algorithms commonly used in PA. What is new is how organizations are leveraging predictive techniques and insights to drive business value. This tutorial will describe tasks performed by data engineers and predictive models who want to build data for predictive modeling. We will cover three of the six stages of predictive analytics as defined in CRISP-DM, the Cross-Industry Process Model for Data Mining: Business Understanding, Data Understanding, and Data Preparation, Throughout the tutorial, concepts will be illustrated with data and real use cases.
- Chicago, IL - May 9, 2017
PASS Business Analytics Marathon, Live Online:
Every predictive modeler or analytics professional knows the importance of data preparation; experts place the time expended in this stage from 50% to even 90% of the time one spends building predictive models. It is time-consuming and daunting because there are so many ways data can be wrong. Yet there are many principles that are reused in nearly every data set. This session focuses on three essential steps in data preparation, taking into consideration the data itself and how algorithms sometimes dictate the kinds of data preparation we do. The principles apply not only to predictive models, but also to data visualization and dashboards. Examples from actual modeling projects will illustrate the principles.
- Live, Online - March 29, 2017 (21:00 GMT)
Digital Analytics Hub, Monterey, CA:
Keynote Address: The New Era in Customer Analytics: Big Data, Cloud Computing & Advanced Analytics
In this new era of Big Data, retailers collect data in ever-increasing volume, variety, and even velocity. In the midst of Big Data, a revolution is taking place in how retailers gain insights about customers, whether they interact with the brand online, in stores, or both.
- Monterey, CA - September 26 - 28, 2016
DAMA Portland Chapter, Portland, OR:
Most of what data scientists do is nothing new, and much of what’s new is really a throwback to what we used to do 20 years ago. So why data science so popular now? In this talk, Dean will describe what differentiates data science from related fields like Business Intelligence, Predictive Analytics, and Statistics, and will illustrate the use of data science from case studies in customer analytics and fraud detection.
- Portland, OR - July 20, 2017
eMetrics Summit 2017, Chicago, IL:
Personalization, one to one, predictive targeting, whatever you call it, serving the optimal digital experience for each customer is often touted as the pinnacle of digital marketing efficacy. But if predictive targeting is so great, why isn’t everyone doing it? Dean first provides an overview of predictive targeting methodologies as well as a general framework for thinking about the trade-offs of predictive methods in your marketing systems/process. He then explores data exploration, data preparation, modeling building, and model evaluation, what can be done to improve model accuracy. Dean also explains model ensembles, including Bagging, Random Forests, and Stochastic Gradient Boosting. Come for the enlightenment, stay for the bar-bet-winning vocabulary.
- Chicago, IL - June 21, 2017
How Predictive Modelers Should Leverage Big Data, Berkeley, CA:
- Haas School of Business, University of California, Berkeley - May 16, 2017
WEBINAR: Predictive World Virtual Conference, Live Online:
The most effective approach to win predictive analytics data competitions and producing highly accurate predictive models is the use of model ensembles, a technique that combines predictions from multiple models into a single score. The use of ensembles has revolutionized predictive modeling not just in competitions, such as the Netflix Prize, Kaggle, and KDD CUP competitions, but also in everyday modeling for private and public sector organizations. This talk introduces model ensembles and will walk through the history of model ensembles in machine learning and predictive analytics, including Bagging, Boosting, Random Forests, Stochastic Gradient Boosting, and heterogeneous ensembles. While ensembles appear to be more complex than individual models, thus violating Occams Razor, this talk will also unravel the apparent contradiction. Real-world examples of the application of model ensembles will be provided throughout the talk.
- Live, Online - May 26, 2017 (15:00 PDT)
WEBINAR (with Dr. Mamdouh Refaat, Senior Vice President Chief Data Scientist, Angoss Software), Live Online:
It is inevitable that organizations will continue to accrue vast amounts of data, not only from traditional sources that are product level focused but also from digital outlets such as mobile devices, social media networks or the Internet of Things. Accumulation of data collected from these sources is also known as Big Data. Regardless of where the data comes from organizations have instinctively determined that Big Data is a precious asset, one that can positively shape the direction of the business.
- Live, Online - May 31, 2017 (10:00 PDT)
TDWI Data Science Bootcamp, San Diego, CA:
An Overview of Data Science
Data science has been called “the sexiest job of the 21st century” and with good reason—the size and breadth of our data is growing exponentially, making our ability to understand that data more and more challenging. This session defines data science, describes how it is similar and different from related analytics disciplines, and the key concepts every data scientist needs to know. In this overview, data science will be described in a project-oriented framework. Each project must define objectives, collect and integrate data, prepare it for analysis, perform the analysis, and deploy the results. Whether the end-goal of the project is reporting, visualization, descriptive modeling, or predictive modeling, the same principles apply. For each stage, key principles will be described and real-world examples will illustrate the meaning of these principles.
- San Diego, CA - October 3, 2016
Cloud Analytics Symposium, Los Angeles, CA:
- Event Preview, Online Live - June 10, 2016, 11:00am PT
- Los Angeles, CA - June 16, 2016
KNIME Fall Summit, San Francisco, CA:
Don't miss the first North America KNIME Summit this September near downtown San Francisco at the Mission Bay Conference Center. For the first time, we are hosting our signature event in the US, bringing together KNIME users, the KNIME community and partners, and those interested in learning more about KNIME.
- San Francisco, CA - September 14 - 16, 2016
Webinar: Practical Customer Analytics using Predictive Approaches:
- Online - Thursday, October 8, 2015, noon PDT
Webinar: Best Practices for Analyzing Business Data Using Predictive Analytics:
- Online - Wednesday, October 14, 2015, 1:00pm - 2:00pm EST
TDWI Executive Summit:
- San Diego, CA - September 22, 2015
- Austin, TX - December 5, 2016
TDWI Accelerate Conference, Boston, MA:
- Boston, MA - July 19, 2016
PASS Business Analytics Conference, San Jose, CA:
Predictive modeling contains six stages of analysis according to the Cross Industry Standard Process Model for Data Mining (CRISP-DM). I will break this down into three primary tasks for predictive modelers including preparing data, building models, and explaining results. Data preparation often requires skills in SQL, python, or other languages to be able to pull data out of data stores and convert the normalized data into flattened data that the algorithms can use to build models. Modeling requires a qualitative (if not quantitative) understanding of the algorithms, including mathematics or statistics, in order to bulid the effectively. Finally, modelers should know how to explain the results of their findings to other analysts and to decision-makers and stakeholders. The session will walk through the building of a predictive model for a retail appliction: predicting the days to next purchase propensity model.
- San Jose, CA - May 3, 2016
This is a 2-hour lab session. This session describes the six stages of predictive analytics projects according to the CRISP-DM predictive modeling framework: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. Each stage is described from the analyst’s perspective, providing insights into what the science tells us about each stage, and where theory falls short to help us make about how to proceed in building models. After completion of the lab, participants should be able to load data, perform simple data preparation, and create predictive models from modeling data sets. The data preparation steps will include filling missing values and creating dummy variables. Predictive modeling steps will include sampling, building models with decision trees, logistic regression, and neural networks. Even though we are using only the KNIME software, the principles will apply to any workflow-style predictive analytics software package.
- San Jose, CA - May 4, 2016
PASS Business Analytics Conference:
From learning best practices and developing new connections with peers and experts to walking away with a deeper and broader understanding of today's analytics technologies, you'll find even more real-world insights and examples, how-to guidance, and strategic vision from some of the most knowledgeable and top-rated speakers in the BA industry. If you work every day to give your organization the information it needs to make better data-driven decisions, this conference is for you.
- Santa Clara, CA April 22 - 24, 2015
CRM Conference, Keynote Speaker:
- Lausanne, Switzerland - November 6 - 7, 2014
All Analytics A2 Radio:
The Art of Predictive Modeling - August 20, 2014
University of California, Irvine Extension:
Algorithms, Modeling Methods, Verification & Validation
- Summer Quarter 2016: June 27 - September 9, 2016
- Spring Quarter 2016 - April 4 - May 22, 2016
- Summer Quarter 2014; July 21 - September 7, 2014
- Winter Quarter 2014; January 27 - March 16, 2014
Deploying and Refining Predictive Models
- Irvine, CA (Online) - May 16 - June 19, 2016
9th KNIME User Group Meeting and Workshops:
- Berlin, Germany - February 24 - 26, 2016
7th KNIME User Group Meeting and Workshops:
This annual event serves an international forum for discussion of KNIME and how it is used in various fields such as business and customer intelligence, analytics and the life sciences. It brings together practitioners and researchers from around the world to explore KNIME and examine how KNIME is used in different industries.
- Zurich, Switzerland February 12 - 13, 2014
1st San Diego KNIME Meet-Up:
This is the inaugural San Diego KNIME Meetup. We will recap the highlights from the KNIME User Group Meeting in Zurich earlier that month and we will also have a couple of user presentations from the area. There will be plenty of time for questions, discussions and informal chats over small bites and drinks.
- San Diego, CA February 26, 2014
Webinar, Hosted by EITA Global:
Key Steps in Starting Your First Predictive Analytics Project
This webinar summarizes the best practices for building predictive models including both the art and the science of PA during each stage of the process, including Data Understanding, Data Preparation, Predictive Modeling and Deployment.
- January 14, 2014; 10:00am PST (1:00pm EST)
IBM SPSS Modeler Seminar Series, Hosted by Quebit:
Techniques for Unbalanced Data
Unbalanced data is a common problem in data mining – the imbalance of sample size of categories in a target variable. The standard way of addressing the problem is to discard cases using the balance node. But is this the only way? This seminar will discuss the pros and cons of a variety of methods of addressing the problem using Modeler. The balance node will be briefly reviewed, but the focus of the seminar will be the many alternatives to using the balance node in the standard way. Creative ways of using the balance node will be discussed as way as well as techniques like adjusting priors and utilizing costs. In addition there will be a one-hour question and answer follow-up session to address any student questions or concerns.
- January 22, 2014; 1;00pm - 4:00pm EST
- January 23, 2014; 1;00pm - 2:00pm EST; Q & A Follow Up
Talent Analytics Webinar:
Modeling Analytics Dream Team
- September 11, 2013 (12:00 - 1:00pm EST)
Dean will discuss his extensive experience as an analytics professional, building successful analytics teams, working with clients to build their analytics teams, being part of an extended analytics team inside an organization as well as with Elder Research during its early years.
The Briefing Room:
Bridging the Gap: Analyzing Data in and Below the Cloud
- Tuesday, July 23, 2013 - 4:00pm ET
Today's desire for analytics extends well beyond the traditional domain of Business Intelligence. That's partly because business users are realizing the value of mixing and matching all kinds of data, from all kinds of sources. One emerging market driver is Cloud-based data, and the desire companies have to analyze this data cohesively with their on-premise data sets. Register for this episode of The Briefing Room to learn from Analyst Dean Abbott, who will explain how the ability to access data in the cloud can play a critical role for generating business value from analytics.
ISACA San Diego Chapter Meeting:
Predictive Data Analytics and Fraud Detection
- San Diego, CA - June 20, 2013
Data-Intensive Summer School:
Introduction to Text Mining (KNIME Installation, Data and workflow instructions)
- San Diego, CA - June 10, 2013
Fact-Based Performance Management 2013:
Next Generation Performance Management: Moving from Business Intelligence to Predictive Analytics
- San Diego, CA - June 6, 2013
Create a rock solid foundation to advance performance management and grow your analytics practice
Southern California Chapter of the Marketing Research:
- Anaheim, CA - May 2, 2013
INFORMS Conference on Business Analytics & Operations:
- San Antonio, TX - April 7 - 9, 2013
PACE (Predictive Analytics Center of Excellence) Data Mining Boot Camp 2:
Overview of Text Mining
- San Diego, CA - February 8, 2013
- San Diego, CA - October 18, 2013
Pace Tech Talk: Why Model Ensembles Win Data Mining Competitions
The most effective approach to win predictive analytics data competitions and producing highly accurate predictive models is the use of model ensembles, a technique that combines predictions from multiple models into a single score. The use of ensembles has revolutionized predictive modeling not just in competitions, such as the Netflix Prize, Kaggle, and PAKDD competitions, but also in everyday modeling.
This talk introduces model ensembles and will walk through the history of model ensembles in machine learning and predictive analytics, including Bagging, Boosting, Random Forests, Stochastic Gradient Boosting, and heterogenous ensembles. While ensembles appear to be more complex than individual models, thus violating Occams Razor, this talk will explain how to unravel the apparent contradiction. Real-world examples of the application of model ensembles will be provided throughout the talk.
- San Diego, CA - November 14, 2012
Joint Statistical Meetings (JSM): Moderator
Senior executives of major predictive analytics and data mining software firms come together for a panel discussion. Data miners and analysts can hear firsthand the perspectives of the founders, CEO's, and other senior executives at Frontline Systems, Revolution Analytics (R), Rapid-I, Salford Systems, SAS, Statsoft. "Big data" is a rapidly evolving field - so what are these key decision-makers hearing from customers? What are their own plans? Where do they think predictive analytics is headed? What will surprise us? The format will be a dynamic panel-style question/answer session, moderated by industry specialist Dean Abbott (noted for his vendor-neutral workshops on data mining). Audience questions are accepted in advance will be worked into the program.
- San Diego, CA - August 1, 2012
University of California, San Diego Extension: Text Mining
With experts claiming that unstructured data comprises more than 80% of the stored business information, text mining has emerged as a critical leading-edge technology. This course will describe practical techniques for text extraction and text mining in a data mining context, including document clustering and classification, information retrieval and the enhancement of structured data. An emphasis on practical use of text mining in a business context will be evident throughout.
- May 11, 18, & 25, 2012; 9:00am - 4:00pm
- February 3, 10, & 17, 2012 9:00am - 4:00pm
- Spring Quarter 2014; April 28 - June 2, 2014
- Fall Quarter 2014; September 29 - November 10, 2014
Text Analytics World:
Case Study: Rules Rule: Inductive Business-Role Discovery in Text Mining
- San Francisco, CA - March 7, 2012
Customer Support Case Study: A Fortune 500 global technology company
Rules Rule: Inductive Business-Rule Discovery in Text Mining
- New York City, NY - October 19, 2011
Data Mining Conference at a Fortune 500 Company: Speaker / Expert Panelist
- San Diego, CA - May 30, 2012
SAS Customer Connection for Data Mining: Speaker / Expert Panelist
- Cary, NC - June 4 - 6, 2012
JMP Live Webcast: Analytically Speaking
Many people ask Dean Abbott, President of Abbott Analytics, Inc., how to succeed in data mining and predictive analytics. Now you can, too. We've invited Abbott, a noted data mining expert with more than two decades of experience, to lead us in a conversation about applying advanced data mining, data preparation and data visualization methods to real-world, data-intensive problems.
- On-line - June 6, 2012; 7:00am Pacific, 10:00am Eastern
Decision Management Solutions Webinar:
- Ten Best Practices in Operational Analytics - February 9, 2011
Predictive Analytics World Government:
Defense Finance & Accounting Service (DFAS) Case Study
- Washington, DC - September 12 - 13, 2011
DM Radio:
- Back to Basics Best Practices for Data Mining - September 19, 2013
- Rules, Rules, Rules: The Magic of Real-Time Decisioning - November 29, 2012
- Acres of Diamonds -- Mining Enterprise Data with an Open Mind - April 5, 2012
- The Power of Prescience: Achieving Lift with Predictive Analytics - February 24, 2011
- Stop Thief! Fraud Detection in a Web-Enabled World - September 9, 2010
- Embedded Analytics and Business Rules: The Holy Grail? - June 3, 2010
- Text Analytics in the Contextual Enterprise - September 17, 2009
- Putting the Context Around Text Mining - April 17, 2008
ACM Data Mining Camp: Expert Panelist
Focus is on Data Mining, Analytics, Cloud Computing, Machine Learning, and the various applications of these technologies.
- November 13, 2010
Predictive Analytics World Conference:
Keynote Speaker
- Chicago, IL - June 20, 2017
- Berlin, Germany - November 3 - 4, 2015
- London, UK - October 28 - 29, 2015
- Boston, MA - September 29, 2015
- London, England - October 29 - 30, 2014
- Berlin, Germany - November 4 - 5, 2014
- Berlin, Germany - November 4 - 5, 2013
Session: Ask Dean Anything (About Best Practices)
- Chicago, IL - June 21, 2017
- New York, NY - October 26, 2016
- Chicago, IL - June 22, 2016
- Boston, MA - September 29, 2015
- San Francisco, CA - May 16, 2017
Predictive Analytics for Practitioners
- Berlin, Germany - November 7, 2016
Data Preparation from the Trenches: Four Approaches to Deriving Attributes
- Boston, MA - October 7, 2014
Supercharging Prediction: Hands-On with Ensemble Models
- Chicago, IL - June 19, 2017
- San Francisco, CA - May 15, 2017
- New York, NY - October 24, 2016
- Chicago, IL - June 23, 2016
- Boston, MA - September 30, 2015
- Chicago, IL - June 11, 2015
- San Francisco, CA - April 2, 2015
- Boston, MA - October 8, 2014
- San Francisco, CA - March 19, 2014
- San Francisco, CA - April 17, 2013
My Five Predictive Analytics Pet Peeves
- Toronto, ON - May 14, 2014
- Chicago, IL - June 12, 2013
- San Francisco, CA - April 16, 2013
- Toronto, ON - March 20, 2013
Deep Dive - Guided Analytics: Letting the Sexiest Job in the 21st Century Stay Sexy
- Berlin, Germany - November 9, 2016
What is Big Data Analytics: A Canadian Perspective
- Toronto, ON - March 21, 2013
Workshop: Advanced Methods Hands-On: Predictive Modeling Techniques
- Chicago, IL - June 22, 2017
- San Francisco, CA - May 18, 2017
- New York, NY - October 27, 2016
- Chicago, IL - June 20, 2016
- Boston, MA - October 1, 2015
- Chicago, IL - June 8, 2015
- San Francisco, CA - March 30, 2015
- Boston, MA - October 9, 2014
- Toronto, ON - May 12, 2014
- San Francisco, CA - March 20, 2014
- Chicago, IL - June 14, 2013
- San Francisco, CA - April 18, 2013
- Toronto, ON - March 18, 2013
- Boston, MA - October 4, 2012
- Chicago, IL - June 28, 2012
- Toronto, ON - April 27, 2012
- San Francisco, CA - March 8, 2012
Full-Day Workshop: Hands-On Predictive Analytics
- New York, NY - October 18, 2011
- San Francisco, CA - March 17, 2011
- Washington, DC - October 18, 2010
- San Francisco, CA - February 16 - 17, 2010
- Washington, DC - October 20 - 21, 2009
Case Study: Hiring and Selecting Key Personnel Using Predictive Analytics
- Chicago, IL - June 26, 2012
- Toronto, ON - April 26, 2012
Case Study: YMCA - Turning Member Satisfaction Surveys into an Actionable Narrative
- New York, NY - October 19, 2011
- San Francisco, CA - March 14, 2011
- Washington, DC - October 19, 2010
How to Improve Customer Acquisition Models with Ensembles and
Cross-Industry Challenges and Solutions in Predictive Analytics
- San Francisco, CA - February 18 & 19, 2009
Case Study: SmarterHQ - The Revolution in Retail Customer Intelligence
- New York, NY - October 25, 2016
- Chicago, IL - June 21, 2016
eMetrics Marketing Optimization Summit:
- Predicting the Future New York, NY - October 21, 2011
- Behavioral Driven Marketing Attribution San Jose, CA - May 3 - 7, 2010
The Modeling Agency Webinar:
- Failure to Launch: How to get Predictive Analytics off the Ground and into Orbit - March 16, 2010
StatSoft Webinar:
- Wisdom of Crowds: Using Ensembles of Predictive Models - February 24, 2010
Salford Data Mining Conference:
- A More Transparent Interpretation of Health Club Surveys
San Diego, CA - May 24, 2012
- A Business-Centric Solution to Text Mining of Help Desk Data using CART
San Diego, CA - August 23 - 25, 2009
TDWI World Conference: Data Mining Techniques, Tools, and Tactics
- Las Vegas, NV - February 22 - 27, 2009
Invoice Fraud Detection: Successful application of data mining by Abbott Analytics
TDWI Data Science Bootcamp Seminar (Austin, TX / Virtual Classroom): September 20 - 22, 2021
PAW for Business (Virtual Classroom): May 20 - 25, 2021
Abbott, D.W., Combining Models to Improve Classification Accuracy and Robustness (PDF), The 2nd International Conference On Information Fusion - FUSION'99, San Jose, CA, July 6, 1999.