Since 2009, we have been hosting BayesiaLab courses and events worldwide. New York, Chicago, Paris, London, Dubai, Bangalore, Singapore, and Sydney, to name a few cities, are part of our regular teaching schedule (check out our photo gallery).
After a long break in the in-person training program due to COVID-19, we are returning with classroom-based training in 2024. Registration for the Introductory and Advanced BayesiaLab Courses in Cincinnati is now open.
After four virtual conferences, we welcome the brightest minds back to the epicenter of Bayesian network innovation, the 2024 BayesiaLab Spring Conference. At this event, our community eagerly anticipates reuniting face-to-face, celebrating the human connections in our field.
We are ready to continue our public education program with relevant topics and innovative methodologies. Many thousands have participated in our seminars over the last ten years. Please check out our photo gallery of BayesiaLab events and see the archive of recorded seminars and webinars:
Our seminars have become very popular because we spend several hours demonstrating a complete research workflow, including all steps from data preprocessing to final optimization. Such in-depth tutorials can show you how to employ the proposed methodologies in your work.
Three-Day Introductory BayesiaLab Course in Miami Beach, Florida
Spaces — 1111 Lincoln Road, Miami Beach, FL 33139 October 7–9, 2024
Since 2009, our BayesiaLab courses and events have spanned the globe. From New York to Sydney, Paris to Singapore, we've touched down in cities worldwide (take a peek at our photo gallery!).
We have a fantastic venue for our course. The classroom is in the heart of Miami Beach, just a few blocks from the glamorous South Beach.
The Introductory BayesiaLab Course is more than just a beginner's guide. It's a deep dive into applying Bayesian networks across diverse fields, from marketing science and econometrics to ecology and sociology. And we don't just stick to theory. Every conceptual lesson transitions seamlessly into hands-on practice with BayesiaLab, allowing you to apply what you've learned directly, whether in knowledge modeling, causal inference, machine learning, or more.
Over 2,000 researchers worldwide can vouch for its impact, many of whom have made Bayesian networks and BayesiaLab integral to their research. Don't just take our word for it - check out the testimonials!
Bayesian Networks: Artificial Intelligence for Decision Support under Uncertainty
Probabilistic Expert Systems
Bayesian Networks and Cognitive Science
Unstructured and Structured Particles Describing the Domain
Expert-Based Modeling and/or Machine Learning
Predictive vs. Explanatory Models, i.e., Association vs. Causation
Examples:
Medical Expert Systems
Consumer Segmentation
Drivers Analysis
Product Optimization
Examples of Probabilistic Reasoning
Cognitive Science: How our probabilistic brain uses priors for the interpretation of images
Interpreting Results of Medical Tests
Kahneman & Tversky’s Yellow Cab/White Cab Example
Probability Theory
Probabilistic Axioms
Perception of Particles
Probabilistic Expert System for Decision Support: Types of Requests
Leveraging Independence Properties
Bayesian Networks
Qualitative Part: Directed Acyclic Graph
Graph Terminology
Graphical Properties
D-Separation
Markov Blanket
Quantitative Part: Marginal and Conditional Probability Distributions
Exact and Approximate Inference in Bayesian networks
Example of Probabilistic Inference: Alarm System
Building Bayesian Networks Manually
Expert-Based Modeling via Brainstorming
Why Expert-Based Modeling?
Value of Expert-Based Modeling
Structural Modeling: Bottom-Up and Top-Down Approaches
Parametric Modeling
Cognitive Biases
Parameter Estimation
Bayesian Parameter Estimation with Dirichlet Priors
Smooth Probability Estimation (Laplacian Correction)
Information Theory
Conditional Entropy
Symmetric Relative Mutual Information
Unsupervised Structural Learning
Entropy Optimization
Structural Coefficient
Minimum Size of Data Set
Search Spaces
Search Strategies
Learning Algorithms
Maximum Weight Spanning Tree
Taboo Search
EQ
TabooEQ
SopLEQ
Taboo Order
Data Perturbation
Example: Exploring the relationships in body dimensions
Data Import (Typing, Discretization)
Definition of Classes
Excluding a Node
Heuristic Search Algorithms
Data Perturbation (Learning, Bootstrap)
Choosing the Structural Coefficient
Console
Symmetric Layout
Model Analysis: Arc Force, Node Force, and Pearson Coefficient
Dictionary of Node Positions
Adding a Background Image
Supervised Learning
Learning Algorithms
Naive
Augmented Naive
Manual Augmented Naive
Tree-Augmented Naive
Sons & Spouses
Markov Blanket
Augmented Markov Blanket
Minimal Augmented Markov Blanket
Variable Selection with the Markov Blanket
Example: Predictions Based on Body Dimensions
Data Import (Data Type, Supervised Discretization)
Heuristic Search Algorithms
Target Evaluation (In-Sample, Out-of-Sample: K-Fold, Test Set)
Smoothed Probability Estimation
Analysis of the Model (Monitors, Mapping, Target Report, Target Posterior Probabilities, Target Interpretation Tree)
Evidence Scenario File
Automatic Evidence-Setting
Adaptive Questionnaire
Batch Labeling
Semi-Supervised Learning - Variable Clustering
Algorithms
Example: S&P 500 Analysis
Variable Clustering
Changing the number of Clusters
Dynamic Dendrogram
Dynamic Mapping
Manual Modification of Clusters
Manual Creation of Clusters
Semi-Supervised Learning
Search Tool (Nodes, Arcs, Monitors, Actions)
Sticky Notes
Data Clustering
Synthesis of a Latent Variable
Expectation-Maximization Algorithm
Ordered Numerical Values
Cluster Purity
Cluster Mapping
Hypercube Cells Per State
Example: Segmentation of Men Based on Body Dimensions
Data Clustering (Equal Frequency Discretization, Meta-Clustering)
Quality Metrics (Purity, Log-Loss, Contingency Table Fit)
Posterior Mean Analysis (Mean, Delta-Means, Radar charts)
Mapping
Cluster Interpretation with Target Dynamic Profile
Cluster Interpretation with Target Optimization Tree
Projection of the Cluster on other Variables
Probabilistic Structural Equation Models
PSEM Workflow
Multiple Clustering for Creating a Factor Variable (via data Clustering) per Cluster of Manifest Variables
Unsupervised Learning for Representing the Relationships between the Factors and the Target Variable
Example: The French Market of Perfumes
Cross-Validation of the Clusters of Variables
Display of Classes
Total Effects
Direct Effects
Direct Effect Contributions
Tornado Analysis
Taboo, EQ, TabooEQ, and Arc Constraints
Multi-Quadrant Analysis
Exporting Variations
Target Optimization (Dynamic Profile)
Target Optimization (Tree)
Since then, BayesiaLab has emerged as the leading software package for knowledge discovery, data mining, and knowledge modeling using Bayesian networks. Dr. Lionel Jouffe is co-founder and CEO of France-based Bayesia S.A.S. Lionel holds a Ph.D. in Computer Science from the University of Rennes and has worked in Artificial Intelligence since the early 1990s. While working as a Professor/Researcher at ESIEA, Lionel started exploring the potential of Bayesian networks.
After co-founding Bayesia in 2001, he and his team have been working full-time on the development of BayesiaLab. Since then, BayesiaLab has emerged as the leading software package for knowledge discovery, data mining, and knowledge modeling using Bayesian networks. It enjoys broad acceptance in academic communities, business, and industry.
Stefan Conrady, Bayesia USA
May 16, 2024, at 11:00 a.m. (EDT).
Structural Equation Modeling (SEM) is a statistical technique for testing and estimating causal relations using a combination of statistical data and qualitative causal assumptions. It allows both confirmatory and exploratory modeling, meaning it is suited to theory testing and theory development.
What we call Probabilistic Structural Equation Models (PSEMs) in BayesiaLab are conceptually similar to traditional SEMs. However, PSEMs are based on a Bayesian network structure as opposed to a series of equations. More specifically, PSEMs can be distinguished from SEMs in terms of key characteristics:
All relationships in a PSEM are probabilistic—hence the name—as opposed to deterministic relationships plus error terms in traditional SEMs.
PSEMs are nonparametric, facilitating the representation of nonlinear relationships and relationships between categorical variables.
The structure of PSEMs is partially or fully machine-learned from data.
Specifying and estimating a traditional SEM requires a high degree of statistical expertise. Additionally, the multitude of manual steps involved can make the entire SEM workflow extremely time-consuming. On the other hand, the PSEM workflow in BayesiaLab is accessible to non-statistician subject matter experts. Perhaps more importantly, it can be faster by several orders of magnitude. Finally, once a PSEM is validated, it can be utilized like any other Bayesian network. This means that the full array of analysis, simulation, and optimization tools is available to leverage the knowledge represented in the PSEM.
In this seminar, we present a prototypical PSEM application: key driver analysis and product optimization based on consumer survey data. We examine how consumers perceive product attributes and how these perceptions relate to their purchase intent for specific products.
Given the inherent uncertainty of survey data, we also wish to identify higher-level variables, i.e., “latent” variables that represent concepts that are not directly measured in the survey. We do so by analyzing the relationships between the so-called “manifest” variables, i.e., variables directly measured in the survey. Including such concepts helps build more stable and reliable models than would be possible using manifest variables only.
Our overall objective is to make surveys clearer for researchers to interpret and make them “actionable” for managerial decision-makers. The ultimate goal is to use the generated PSEM to prioritize marketing and product initiatives to maximize purchase intent.
Stefan Conrady has over 20 years of experience in decision analysis, analytics, market research, and product strategy with Mercedes-Benz, BMW Group, Rolls-Royce Motor Cars, and Nissan, which included assignments in North America, Europe, and Asia.
Today, as the Managing Partner of Bayesia USA and Bayesia Singapore, he is recognized as a thought leader in applying Bayesian networks to research, analytics, and reasoning.
"BayesiaLab is a great tool that is used in my company. So, I joined this training because of my work. I found the training superb and comprehensive, the theoretical part was highly sophisticated and the practical part featured a great diversity of examples. The fact that the training was a virtual reality session turned out to be a great experience. Plus, it allows you to have access to the training videos afterwards." Amel Belounnas, Data Scientist, GRTGaz, Introductory Course (VR Edition), 2020
"I thought it was excellent hands-on training with the right mix of theory. Helped me understand and comprehend the possibilities with modern BBNs. I enjoyed the Virtual World too. It would have been hard for me to take this live training without being offered virtually." Saurav Kumar, Ph.D., P.E., Assistant Professor, Texas A&M AgriLife Research and Department of Biological and Agricultural Engineering, Introductory Course (VR Edition), 2020
"World-class course in an engaging virtual environment! The instructor's depth of knowledge on the subject matter and the BayesiaLab platform is truly incredible. The course provides a deep but still accessible dive into the theory behind the practice with plenty of practical exercises to re-enforce the concepts and learn the wide variety of tools and workflows possible with BayesiaLab. The Laval Virtual Environment is not just another Zoom meeting - it provides an immersive avatar-based experience in 3D space. For example, the instructor can walk through the virtual classroom, see your screen live (if you choose to share it), and provide assistance with the exercises. You can also interact with the other students including private and public discussion spaces; even a trip to the beach. By far the best remote learning experience I’ve had." Mike Brienesse, Policy Advisor, Government of Ontario, Canada, Introductory Course (VR Edition), 2020
Dr. Olivier Cussenot, Professor of Anatomy and Urology at the Sorbonne University Medical School in Paris, Introductory and Advanced Courses (VR Edition), 2020
"The BayesiaLab training is an eye-opening experience and Lionel an engaging teacher. Highly recommended." Dimitri Molerov, Humboldt-Universität zu Berlin, Germany, Introductory and Advanced Courses, Seattle 2019
"Great course. If you want to learn what you can do with Bayesian Networks, attend this course." Ramon Xulvi, Escuela Politécnica Nacional, Ecuador, Introductory Course, Sydney 2019
"Better come rested and with a cleared agenda as you can't afford to miss a minute." Nicolas Clerc, Caterpillar, Introductory Course, Amsterdam 2019
"This is an exceptional three-day intro to Bayesian networks led by top-drawer faculty. Creating a full-dress structural equation model (SEM) in an hour sounds crazy. Because it's impossible. But not with BayesiaLab's probabilistic structural equation model (PSEM) workflow. If you're in data science and haven't experienced BayesiaLab, it's high time. Peerless supervised and unsupervised learning. BayesiaLab beats the stuffing out of traditional linear and logistic regression. No data? No problem -- use expert elicitation to build, validate and optimize your model. Three days just scratches the surface on this powerful analytical tool." Kurt Schulzke, Associate Professor of Accounting & Law, University of North Georgia, Introductory Course, Washington 2019
"The BayesiaLab training course covers it all, from probability theory to practical examples of how to use the wide range of features that the program offers. The hands-on learning sessions help to answer not only how to create and use Bayesian networks, but why doing so is a breakthrough approach in virtually any field. Lionel is a great instructor who is always listening to feedback in order to make both the course and BayesiaLab itself the best it can be." Lisa Shaffer, Marketing Science Specialist at RTi Research, Introductory Course, NYC 2019
"Bring your raincoat to be ready for a firehose of amazing content!!" Bill Anderson, Software Engineering Institute, Carnegie Mellon University, Introductory Course, NYC 2019
"If a new user wants to quickly advance along the learning curve with building Bayesian Networks with BayesiaLab, then this training course is a must." Chad Johnson, Answers Research, Introductory Course, Chicago 2018
"It was a very interesting course, learned more about BayesiaLab and learning algorithms." Linda Smail, Zayed University, Introductory Course, Dubai 2018
"This advanced course introduces to the next level of the remarkable abilities of BayesiaLab in Bayesian network modeling and data analysis. Emphasizing both building and tweaking the models and detailed analysis of the results, the course also provides an in-depth understanding of the concepts introduced in the introductory session. Thorough content, systematic structure, the balance between theory and applications together with excellent organization, and outstanding delivery make this course a must for those who want to fully utilize the power of BayesiaLab." Alexander Alexeev, Indiana University Bloomington, Advanced Course, Seattle 2018
"Excellent course with a promising software that can create a big impact on practice." Hani Mufti, The Royal Children's Hospital Melbourne, Introductory Course, Sydney 2018
"Lionel guides you effortlessly through this fascinating course. He's a great communicator who adapts the message so everyone can understand the essence of what is being discussed regardless of their field of practice." Jef Geys, Primefit, Introductory Course, London 2018
"If you want to use BayesiaLab to its full potential, the Advanced Course is a must! It is a great display of BayesiaLab's functionality and value for money in a three-day packed workshop." Alta de Waal, Department of Statistics, University of Pretoria, South Africa, Advanced Course, Paris 2017
"BayesiaLab is a great software package that has been created to answer various industrial needs ranging from understanding data to validating business assumptions. BayesiaLab offers a three-day-long introductory training session which I found very insightful. I would strongly recommend BayesiaLab as a problem-solving laboratory designed for A/B testing, causal inference, or data understanding." Peyman Rahmati, Senior Data/Applied Scientist, Amazon, Introductory Course, Paris 2017
"BayesiaLab's classes have enabled me to make a tremendous leap forward in my research. I now have the tools needed to create powerful predictive models and to generate new insights from large, complex data sets." Jacqueline MacDonald Gibson, Associate Professor, University of North Carolina, Introductory and Advanced Courses, Boston and Seattle 2017
"Great course for anyone who wants to understand what Bayesian is all about. Very practical and problem-oriented, hands-on training in creating and evaluating Bayesian belief networks. In a few days, you're not an expert but you are trained enough so you can use it in practice. Lionel is a great instructor with perfect knowledge of the theory and software." Adrian Ackers, Totta Data Lab, Introductory Course, Paris 2017
"I felt that the Bayesia product was fascinating. BayesiaLab is like no other in its capacity to reveal otherwise hidden or non-intuitive aspects of data. If I could by some surgery integrate BayesiaLab into my normal cognitive function, I would do so immediately. Lionel is a virtuoso with both his own software and Bayesian analytical strategies. However, as he mentioned during the introduction, it requires - typically - a year to become competent with the program." Peter Capell, SEI-CMU, Introductory and Advanced Courses, Pittsburgh 2017
"I have been using BayesiaLab for about 2 years to develop pure knowledge-based models with success since these models prove to be very efficient in our operational business. However, I never had the opportunity to use the tool in a Machine Learning mode. This training met fully my expectations, which were about understanding the major principles of using the tool for Machine Learning and being able to start using it for specific applications in my business. I have been impressed by the tool’s capabilities and I feel quite comfortable to start using it for Machine Learning. I strongly recommend this training to anyone who would like to make a start in Machine Learning with Bayesian techniques." Philippe Asseman, Airbus, Introductory Course, Paris 2016
"I liked particularly the balance between theory and practice during the training, with Lionel's very accessible explanation of those complex concepts. And given the complexity, there is still a lot for me to learn and explore in this field." Yue Wu, Telethon Kids Institute, Introductory Course, Perth 2016
"I have learned a lot during this training session in Paris. Lionel was outstanding by being able to answer all our concerns and questions, working with us individually and collectively, and also attracting us to ask for more. I am looking forward to my next advanced training session." Linda Smail, Zayed University, Introductory Course, Paris 2016
"BayesiaLab is the ideal tool for research in cognitive science." Yves Ascencio, HIA Robert Picqué, Introductory Course, Paris 2016
"The introductory course was a real inspiration regarding the application of Bayesian Networks." Martin Weiß, IT-Focus, Introductory Course, Paris 2016
"Very informative theoretical and hands-on practical training by an intelligent and kind teacher for anyone who wants to learn how to use this very powerful tool in their field. Coming from a non-analytical background I learned a lot. Thank you!" Rahul Parakhia, Human Health Scientist, RIFM, Introductory Course, Boston 2016
"This is one of the best training I have ever had! Perfect topic that opens so many opportunities in any domain you could think of. The software is amazing and very intuitive. The presenter is extremely knowledgeable, patient, and friendly. I would definitely consider taking this course again if I need to refresh my knowledge, but I also will be extremely happy to take an advanced 3-day course. I look forward to start applying Bayesian network analysis at work and hope BayesiaLab will be an extremely important part of it. Thank you Lionel and Stefan for the wonderful course!" Vladimir Agajanov, Moody's Analytics, USA, Introductory Course, New York City 2016
"This course is quite intensive but very manageable if you have a background in statistics/machine learning/data science etc. Lionel (the instructor) knows the software inside-out and was able to answer all questions knowledgeably and without hesitation. I would absolutely recommend this course as a thorough and in-depth introduction to Bayesian Networks and the BayesiaLab package. The small class sizes also contributed to an enjoyable and engaging learning experience." Brian Potter, Infotools, New Zealand, Introductory Course, Melbourne 2015
"For me, it was a perfect training session and I use the program daily after that." Magnus Lindvall, Lund University, Department of Clinical Sciences, Sweden, Introductory Course, Paris 2015
"BayesiaLab gives the most comprehensive unified suite of data analytics tools I've seen. I've already replicated the findings of a scientific paper with a considerable longitudinal study in only a matter of hours using BayesiaLab. Whether you're a data scientist, researcher, or business professional, you will likely uncover and apply more value from your data using this framework." Nick Tsirlis, Organizational Analytics, Introductory and Advanced Courses, Washington 2015
"There is no other tool on the market that can deal with the non-Linear nature of most real-world problems and provide such a breadth of analysis and visualization." Terry Potter, Venture Solutions & Dev. Inc., Introductory and Advanced Courses, San Jose and Washington 2015
"I enjoyed a very well-prepared course on especially interesting topics and impressive software given by an outstanding instructor. Thanks for the nice and lively training, Lionel." Mario Pichler, Software Competence Center Hagenberg, Austria, Advanced Course, Paris 2015
"I would recommend the Introductory course to anyone interested in beginning their journey or furthering their knowledge in Bayesian Networks. I found Lionel Jouffe to be a true professional with great domain knowledge." Craig Ennis, EFT Energy Inc., Introductory Course, Houston 2015
"The training was a truly mind-altering experience. I thoroughly enjoyed it and would recommend it to anyone interested in modeling with Bayesian Networks. Having Lionel personally deliver the course and answering any and all questions is of great business and educational value. I'm next looking forward to the advanced course." Gabriel Andraos, G Squared Capital, Introductory Course, Paris 2014
"BayesiaLab makes big data digestible/accessible to the amateur inquirer." John Lamia, FedEx, Introductory Course, Chicago 2014
"I attended the Bayesia Advanced training session in NY in Jan 2014 and enjoyed it a lot. It provides in-depth though practical support to design and implement BBN analysis for a range of applications. Lionel Jouffe is particularly supportive and offers his highly valuable professional skills with a friendly smile. Absolutely recommended!" Danilo Gambelli, Università Politecnica delle Marche, Italy, Advanced Course, New York City, 2014
"Fantastic training. Bayesia has compiled one of the most comprehensive training conferences I have ever had the pleasure to attend. If you are working with Bayes you need this class. If you are just thinking about using Bayes you need this class." Michael Grimes, Principal, Veterans Technology Group Inc., Advanced Course, Los Angeles 2014
"Overall, this training was outstanding. Lionel is a gifted teacher, and it helps that you are showcasing a first-rate product. BayesiaLab is the most intuitive and easy-to-use machine-learning software available. It's a first-rate investment." Dr. Felix Elwert, Vilas Associate Professor of Sociology, University of Wisconsin-Madison, Introductory Course, Chicago 2014
"Lionel is a real expert on Bayesian Networks and he does a tremendous job of illustrating the uses of BayesiaLab for our company." Michael Abramovich, Booz Allen Hamilton, Introductory Course, Boston 2013
"The BayesiaLab software is impressive in its sophistication and multi-faceted abilities as a decision support tool. I had been using it primarily as a modeling tool for deductive analysis. Taking this class opened my eyes to BayesiaLab's incredible data-mining abilities. If you are looking for something that will provide a totally new angle on business decision problems, this is it!" Michael Ryall, Ph.D., Professor of Strategy and Economics, Rotman Business School, University of Toronto, Introductory Course, Chicago 2013
"Thank you Lionel and Stefan for the excellent training experience. The mix of Bayesian Network theory and hands-on applications with real data was just about perfect for me. The group of attendees was great too: from genetics, space communication and control, advertising and marketing, and risk assessment. The mix of disciplines made for great classroom questions and interesting lunch conversations. Thanks for being great hosts and for providing the industry with BayesiaLab. I'll recommend this course and BayesiaLab to all of my model-building friends who need to make better predictions." John O. Jones, This or That Media, Introductory Course, San Mateo 2012
"I attended this training in Feb 2012 in Orlando. Dr. Jouffe did a great job explaining the concepts of Bayesian Belief Networks. The hands-on sessions are extremely interesting. The BayesiaLab software has a lot of functions - you can do anything from correlation analysis to supervised learning algorithms! This tool can be for analysis in any area - ranging from market research to health care. I recommend this training to all people interested in Bayesian networks." Krithika Bhuvaneshwar, Bioinformatician/Data Manager, Clinical Informatics, Lombardi Comprehensive Cancer Center, Georgetown University, Introductory Course, Orlando 2012
"A must-take course for anyone looking to leverage advanced BBN techniques in virtually any domain." Alex Cosmas, Booz Allen Hamilton, Introductory Course, Los Angeles 2011
"Bayesian Belief Networks is an advanced technique and Bayesia Lab makes such a complex technique easy to use on fingertips. Without any prior knowledge I had attended the Bayesia Lab Training in Chicago, April 2011, and found it very helpful & worth the money paid. The course structure/contents were well planned and by the end of the course, I felt satisfied & had a sense of mission accomplished. Dr. Jouffe has excellent teaching skills & in his training session, there were several Q&A opportunities all addressed with a smiling face." Supriya Satwah, Senior Scientist, Unilever, Introductory Course, Chicago 2011
"I enjoyed the training course in Chicago in April 2011. It was very interesting and very well organized. I learned a lot of new things and I got inspired for applications of BayesiaLab in my daily job. Finally the environment: very friendly and productive with the other attendees coming both from the business and academic world, a really wonderful “melting pot”. A very exciting experience which I recommend to all people interested in Bayesian networks." Tommaso Pronunzio, Partner at Ales Market Research (Italy), ESOMAR Representative, Introductory Course, Chicago 2011
"The Bayesia training session was one of the most valuable and thoughtful I have ever attended. Dr. Jouffe did an admirable job introducing and explaining Bayesian Belief Networks, an area of predictive modeling that is of rapidly increasing importance in many fields. The course adroitly mixed practical applications, case histories, and key concepts and theory, explaining the uses and remarkable power of these models. The approach was always informative and engaging and included the best set of presentation materials I have encountered in a long time. This is a truly worthwhile course, and it also introduced a remarkable piece of analytical software. I speak as somebody who has given seminars and taught graduate courses for over twenty years; this session definitely deserves the highest praise." Steven Struhl, Harris Interactive, Introductory Course, New York City 2009
"Attend, attend, attend! The training was well done allowing for both hands-on using BayesiaLab but also an exploration of the Bayesian approach. Lionel was a great teacher – to have the brain behind the product guiding you was indeed amazing, no question went unanswered." Yianna Vovides, The George Washington University, Introductory Course, New York City 2009
New course dates to be announced.
Building on the foundation laid in the Introductory BayesiaLab Course, we introduce the Advanced BayesiaLab Course for those ready to delve even deeper.
With this immersive experience, you can take your BayesiaLab certification to the next level. While the introductory course provided a comprehensive overview of Bayesian network applications, our advanced curriculum dives into the nuances.
Expert-Based Modeling via Brainstorming
Why Expert-Based Modeling?
Value of Expert-Based Modeling
Structural Modeling: Bottom-Up and Top-Down Approaches
Parametric Modeling
Interactive
Batch
Segmentation of the Experts
Creation of Bayesian Belief Networks based on the Elicited Probabilities
Analysis of the Expert Assessments
Parameter Sensitivity Analysis
Exercise: Interactive Session for Probability Elicitation
Utility Nodes
Decision Nodes
Expected Utility
Automatic Policy Optimization
Example: Oil Wildcatter
Exercises
Motivation
Inference Functions
Formatting
Function Nodes as Parents
Exercise
Hidden Markov Chain
Unfolded Temporal Bayesian Networks
Dynamic Bayesian Networks
Temporal Simulations (Scenarios, Temporal Conditional Dependencies, Temporal Monitoring)
Exact and Approximate Inference
Unfolding Dynamic Bayesian Networks
Exercise: Maintenance of a Fluid Distribution System
Network Temporalization
Temporal Forecast
Exercise: Box & Jenkins
Unrolled Networks
Compact Networks
Hyperparameters
Conditional Dependencies
Exercise: Bayesian Updating for Equine Anti-Doping
Impact of Discretization
Requirements for a Good Discretization
Pre and Post Discretization
Discretization viewed as the Creation of Latent Variables
Discretization Methods
Manual by Expertise
Univariate
Equal Frequency
(Normalized) Equal Distance
Density Approximation
K-Means
R2-GenOpt
R2-GenOpt*
Bi-Variate
Tree
Perturbed Tree
Multi-Variate
Supervised with Random Forest
Unsupervised with Random Forest
R2-GenOpt
LogLoss-GenOpt
Exercise
Aggregation Methods for Symbolic Variables
Manual by Expertise
Semi-Automatic
Bi-Variate with Tree
Exercise
Types of Missingness
Types of Methods
Static
Filtering
A Priori Replacement
Entropy-Based and Standard Static Imputation
Dynamic
Dynamic Imputation
Entropy-Based Dynamic Imputation
Structural Expectation-Maximization
Approximate Dynamic Imputation with Static Imputation
Missing Values Imputation (Standard, Entropy-Based, Maximum Probable Explanation)
Exercise
Filtered/Censored/Skipped Values
Example: Survey Analysis
Manual Synthesis
Binarization
Clustering
K-Means
Bayesian Clustering
Hierarchical Bayesian Clustering
Exercises
Minimum Description Length (MDL) Score
Parameter Estimation with Trees
Structural Coefficient
Stratification
Smooth Probability Estimation
Exercise: CarStarts
Confidence/Credible Interval Analysis
Evidence Analysis
Joint Probability of Evidence
Log-Loss
Information Gain
Bayes Factor
Maximum Probable Explanation
Maximum A Posteriori
Most Relevant Explanation
Performance Analysis
Supervised
Unsupervised
Compression
Multi-Target
Outlier Detection
Path Analysis
Exercises
Genetic Algorithm
Objective Function
States/Mean
Function value
Maximization/Minimization
Target Value
Resources
Joint Probability/Support
Search Methods
Hard Evidence
Numerical Evidence
Direct Effects
Exercise: Marketing Mix Optimization
Direct Effects
Type I Contribution
Type II Contribution
Base Mean
Normalization
Stacked Curves
Synergies
Dr. Lionel Jouffe is co-founder and CEO of France-based Bayesia S.A.S. Lionel holds a Ph.D. in Computer Science from the University of Rennes and has worked in Artificial Intelligence since the early 1990s. While working as a Professor/Researcher at ESIEA, Lionel started exploring the potential of Bayesian networks.
After co-founding Bayesia in 2001, he and his team have been working full-time on the development of BayesiaLab. Since then, BayesiaLab has emerged as the leading software package for knowledge discovery, data mining, and knowledge modeling using Bayesian networks. It enjoys broad acceptance in academic communities, business, and industry.
This webinar presents a complete workflow for developing a Probabilistic Structural Equation Model (PSEM) based on Bayesian networks and utilizing the software platform. Our objective is to identify key drivers of satisfaction with a PSEM that is machine-learned from consumer survey data. A key challenge in this context is to resolve the conflict between "driver" as a causal concept versus the non-causal nature of non-experimental survey data. Furthermore, we illustrate how quantifying the joint probability of hypothetical scenarios is critical for establishing priorities for improving customer satisfaction.
Recently, Stefan and his colleague Dr. Lionel Jouffe co-authored , which is now available as an e-book.