Dr. Kirk Borne
Principal Data Scientist And Executive Advisor, Booz Allen Hamilton
How to identify modeling opportunities and categorize them (Detect, Discover, Predict, Optimize)
How to select appropriate modeling components and ML algorithms for specific use cases
How to design your own analytics solutions
How to solve a broad range of problems
How to generate value from the data assets in your organization
How to communicate to your stakeholders the importance and meaning of models in data-intensive environments
Work on data literacy exploratory data analysis use cases that broaden and deepen one’s understanding and abilities in insights discovery and value creation from data
Modeling is a fundamental aspect of any science. This fact is particularly apparent in data science. The key aspects of modeling that make it important for science are: (1) models are representations of things that cannot be fully understood or known (e.g., predictive models are essential to predict a future outcome, unless you have access to a time machine that we don’t know about); (2) models can give us new insights into those things, including their behaviors, responses, and characteristics (especially in previously unseen conditions), thereby potentially revealing causal factors for observed outcomes and informing prescriptive actions to optimize outcomes; (3) models provide testable predictions to validate our assumptions and hypotheses about things (otherwise, it’s not science); and (4) models can help answer questions that are not otherwise answerable (e.g., we can pose “what if” scenarios safely in a model environment that we would not be able or allowed to test in a real life situation).
In data science, we use observation (data, evidence) to inform and inspire our models, we use machine learning (algorithms that learn from patterns in the data) to build testable models, and we use the scientific method to verify, validate, and/or refine our models. The ideal goal of these activities is discovery from data, specifically actionable insights discovery.
This two-part workshop on modeling and machine learning in data science follows two main threads: foundational concepts and practical examples. These two threads will sometimes mix and intertwine, which will help to reinforce the importance of both aspects of modeling. As someone once said, “In theory, theory and practice are the same. In practice, they are not.” We will prove that! Numerous examples of machine learning modeling (and other types of modeling), both common and novel, will be presented. The ultimate goals of the workshop are to help develop modeling intuition, data and analytic literacy, scientific reasoning, data-driven curiosity, critical thinking, and an experimental mindset that will contribute to establishing a strong foundation for a career in data science.
Session 1: Theoretical and Foundational Concepts of Modeling and ML (4 hours)
Training Overview and Data Science Preliminaries
Introduction to Modeling Concepts
Supervised vs. Unsupervised Modeling
Insights Discovery and Generalization
Supervised Learning Concepts
Predictive vs. Prescriptive Modeling
What does Cognitive have to do with it?
The Two Most Important Things in Data Science
Optimization and Feedback Loops in Modeling
Cold-Start Modeling: When the Data Becomes the Model (Unsupervised ML)
Machine Learning vs. Deep Learning
Common Business Modeling Examples
The OODA Loop in Decision Science and Data Science
When Predictive Modeling Fails
Enriching Your Models with Smart Data (Semantic Tags, Labels, Annotations)
Exploiting High-Variety Data to Achieve Better Model Outcomes
Steps to Data Analytics Mastery
Session 2: Typical and Novel Applications of ML Algorithms (4 hours)
A Fishy Example of Cost-Sensitive Classification
A 12-step Analytics Program in Healthcare and Medicine
ML and AI Making Big Moves in Marketing Analytics
Exploratory Data Analysis: Successes, Insights, and Lessons
Data Literacy Exercises: Strengthening Your Data Science Abilities
Surprise Discovery in Regression Analysis
Neural Networks in Climate Modeling
ICA vs. PCA: The Cocktail Party Problem
Graph Mining: Connecting the Dots that Aren't Connected
Forecasting 2.0: Beyond Traditional Forecasting
Clustering Analysis: Down to Earth, and Up to Space
Association Mining for Predictive Modeling
The Ways of Bayes: Classification, Markov Models, Missing Value Imputation, Causal Analysis
Precursor Analytics with Statistical Clustering
The Internet of Context: Forecasting-as-a-Service
Matching ML Algorithms to Business Analytics Problems
The Keys to a Successful Data Science Career
Data scientists, data analysts, business intelligence practitioners, data users, and other analytics-related professionals are the target audience for this training. Generally, this training is for anyone:
Anyone who seeks to understand how machine learning works and how ML models can deliver actionable insights, decision support, and value to their organization
Anyone who wants to become more knowledgeable and proficient in identifying machine learning opportunities and in contributing to ML modeling applications
Anyone who seeks to learn the power of machine learning models in thought and action to progress in your own career journey (e.g. from data analyst to data scientist).
There are no specific coding skills required, though familiarity with computational concepts will be helpful, particularly related to modeling.
Basic quantitative skills and math skills are essential. Some knowledge of calculus and linear algebra is helpful, but not required.
Some experience with machine learning will make this workshop easier to follow, but all that is required is basic knowledge of the concepts. The workshop will explain some of the most common ML algorithms in sufficient detail for your own use and will demonstrate their application in the context of the practical examples presented in the workshop.
Access to the 2 live QA and blended training sessions with the Instructor
Access to the on-demand recording
Certification of completion