West 2022 Schedule
We are delighted to announce our West 2022 Preliminary Schedule!
Please Note: In-Persons attendees will have access to virtual sessions. If you have a virtual Pass, please note that we will not live-stream any in-person sessions. Only virtual sessions will be recorded.
ODSC West Talks
---Tuesday, 1st November
--Wednesday, 2nd November
Thursday, 3rd November
ODSC West Training&Workshops/Tutorials
----Monday, 31st October
---Tuesday, 1st November
--Wednesday, 2nd November
Thursday, 3rd November
---Tuesday, 1st November
--Wednesday, 2nd November
Thursday, 3rd November
----Monday, 31st October
---Tuesday, 1st November
--Wednesday, 2nd November
Thursday, 3rd November
AI in a Minefield: Learning from Poisoned Data
Virtual | Talk | Machine Learning | Beginner – Intermediate
In this talk, we will present the challenges of learning from dirty data, overview data poisoning attacks on different systems like Spam detection, image classification and rating systems, discuss the problem of learning from web traffic – probably the dirtiest data in the world, and explain different approaches for learning from dirty data and poisoned data. We will focus on threshold-learning mitigation for data poisoning, aiming to reduce the impact of any single data source, and discuss a mundane but crucial aspect of threshold learning – memory complexity. We will present a robust learning scheme optimized to work efficiently on streamed data with bounded memory consumption. We will give examples from the web security arena with robust learning of URLs, parameters, character sets, cookies and more…more details
Reasoning About the Probabilistic Behavior of Classifiers
Virtual | Talk | Machine Learning | Research Frontiers | Intermediate-Advanced
This talk will overview our recent work on reasoning about the behavior of learned classifiers. I will cover techniques to inject domain knowledge into machine learning models, for example by enforcing monotonicity constraints, or logical structure, on neural network outputs…more details
Anomaly Detection with Python and R
In-person | Half-Day Training | Beginner-Intermediate
This course will examine anomaly detection through the example of fraud, but all these techniques can be applied to other areas as well. We will start with the importance of feature creation and transformation. We will then cover more statistical based approaches to anomaly detection. Last, we will end with more machine learning based approaches to allow the learner to approach anomalies from any angle and industry need…more details
Operationalizing Organizational Knowledge with Data-Centric AI
Virtual | Talk | All Levels
Data-centric AI broadly describes the idea that *data*, rather than models, is increasingly the crux of success or failure in AI for many settings and use cases. More specifically, data-centric AI defines ML development workflows that center around principally iterating on the *training data*–e.g. labeling, sampling, slicing, augmenting, etc.–rather than the model architecture. In this talk, I’ll describe how programmatic or weak supervision can not only facilitate these data-centric workflows (in ways that manual labeling cannot), but more importantly, will present an overview about how it can serve as an API for rich organizational knowledge sources, presenting recent technical results and user case studies…more details
Building Production-Ready Recommender Systems with Feast
In-person | Talk
In this talk, we explore:
- Challenges of building recommender systems
- Strategies for reducing latency, while balancing requirements for freshness
- Challenges in mitigating data quality issues
- Technical and organizational challenges feature stores solve
- How to integrate Feast, an open-source feature store, into an existing recommender system to support production systems…more details
Detecting Changes Over Time with Bayesian Change Point Analysis in R
In-person | Talk | Beginner-Intermediate
Did my data change after a certain intervention? This is a common question with data observed over time. Classical statistical and engineering approaches include control charts to see if the series falls outside of the normal boundaries of expected data. A Bayesian approach to this problem calculates the probability that the data series changes at every point along the series. Bayesian change point analysis allows the analyst to evaluate a whole series and look where the highest probability of change occurred. Has the financial asset lost value after the recent financial report? Are the healthcare outcomes at this hospital better after our new process to help patients? Did the manufacturing process improve after upgrading the machinery? All these questions and more can be answered with these techniques which will be shown in R…more details
Transforming The Retail Industry with Transformers
In-person | Talk | Deep Learning | Machine Learning | ML Ops and Date Engineering | All Levels
In this talk, we discuss these challenges and share our findings and recommendations from working on real-world examples at SPINS, a data/tech company focused on the natural grocery industry. More specifically, we describe how we leverage state-of-the-art language models to seamlessly automate parts of SPINS’ data ingestion workflow and drive substantial business outcomes. We provide a walk-through of our end-to-end MLOps system and discuss how using the right tools and methods have helped to mitigate some of these challenges. We also share our findings from our experimentation and provide insights on when one should use these massive transformer models instead of classical ML models. Considering that we have a variety of challenges in our use cases from an ill-defined label space to a huge number of classes (~86,000) and massive data imbalance, we believe our findings and recommendations can be applied to most real-world settings. We hope that the learnings from this talk can help you to solve your own problems more effectively and efficiently!…more details
Human Factors of Explainable AI
In-person | Talk | Responsible AI | Beginner
There are many types of users and stakeholders that require Explainable AI. Without explanations, end-users are less likely to trust and adopt ML-based technologies. Without a means of understanding model decision-making, business stakeholders have a difficult time assessing the value and risks associated with launching a new ML-based product. And without insights into why an ML application is behaving in a certain way, application developers have a harder time troubleshooting issues, and ML scientists have a more difficult time assessing their models for fairness and bias. To further complicate an already challenging problem, the audiences for ML model explanations come from varied backgrounds, have different levels of experience with statistics and mathematical reasoning, and are subject to cognitive biases…more details
The Data Science Behind the Data Science: Why Automated Labelling and Responsible AI are the Foundation of High-Quality Predictive Modeling.
In-person | Talk | MLOps and Data Engineering | | Intermediate
This session will explore the challenges our clients face in data sourcing, data preparation and model evaluation by humans, and discuss how automated labelling and responsible AI optimize predictive modeling. Our expert analysts will examine the technologies and processes used to enable success for clients across data types and industries…more details
Scalable, Real-Time Heart Rate Variability Biofeedback for Precision Health: A Novel Algorithmic Approach
In-person | Talk | Machine Learning | Data Science Research Frontiers | All Levels
Heart rate variability biofeedback (HRV-B) is a clinically effective therapy in which patients can improve their mental and physical well-being through real-time monitoring of the heart-rate and specialized breathing techniques. HRV-B can improve health outcomes in a number of medical or wellness-related conditions, ranging from depression and anxiety, to cardiovascular disease, asthma, cancer fatigue, women’s health, better sleep, peak athletic performance, and stress resilience…more details
Extensible Hosted Jupyter Notebook Platform for Accelerating Data Insights
In-person | Talk | ML Ops and Date Engineering | Data Science Research Frontiers | Data Analytics | Beginner – Intermediate
We at LinkedIn leverage Jupyter notebooks extensively to do ad-hoc data analysis and our data scientists, engineers and developers spend a lot of time iterating over the query development lifecycle. We have created a hosted notebook platform at LinkedIn for our internal users) called Darwin (Data Analytics & Relevance Workbench at LinkedIn) – a one-stop solution for a complete Jupyter notebook/query life cycle (query development, query testing and query productionizing)…more details
Building Modern Search Pipelines with Haystack, Large Language Models and Hybrid Retrieval
In-person | Talk
In this talk we navigate through the latest buzz around semantic search and separate the noise from the meaningful advancements. Is dense retrieval better than BM25’s keyword search? Do large language models outperform smaller transformers? How well do the models generalize to industry corpora? How can we leverage Question Answering? We will benchmark different methods, share best practices from industry use cases and show how you can use the open source framework Haystack to build, test and deploy stellar search pipelines easily yourself…more details
MLOps for Deep Learning
In-person | Talk | Deep Learning | ML Ops and Date Engineering | Intermediate – Advanced
Only a significant minority of companies unlock the true potential of AI as trained models accumulate dust due to challenges in MLOps. Serving reliable AI predictions to customers involves cost, effort, and planning to set up a continuous deployment pipeline. MLOps for Deep Learning demands a carefully crafted deployment pipeline. We discuss our open-source project which is a robust continuous deployment pipeline by integrating our unique drift detection and model retrain algorithms for serving DL models. We show how to efficiently deploy, monitor, and maintain DL models in production using our solution which is a Kubernetes native POC solution…more details
Responsible AI Is Not an Option
In-person | Talk | Machine Learning | Data Analytics | Responsible AI | Intermediate
In his talk “Responsible AI Is Not an Option,” Dr. Scott Zoldi brings to bear his decades of experience in delivering analytic innovation in a highly regulated environment, to underscore the urgency with which the topics of AI fairness and bias must be ushered onto Boards of Directors’ agendas. In his dynamic presentation, Dr. Zoldi spells out the “why” and “how” of fulfilling the social covenant and soon, regulatory requirements of enterprises using AI ethically, transparently, securely and in their customers’ best interests…more details
Optimizing Recommendations for Competing Business Objectives
In-person | Talk | Deep Learning | Machine Learning | Intermediate
In this talk I will give an overview of this problem, what makes it difficult, how we have been addressing it at Wayfair, and the lessons that we have learned so far. I will start by giving an overview of the different types of competing business objectives that can arise in the e-commerce use case and how they compete against each other in practice. Along the way I will introduce some of the fundamental concepts of multi-objective optimization, including Pareto Efficiency and the Pareto Frontier, and how they relate to this problem. Finally, I will discuss the pros and cons of various strategies for making recommendation systems profit aware…more details
Introduction to Differential Privacy Concepts
In-person | Talk
Differential privacy can be viewed as a technical solution for protecting individual privacy to meet legal or policy requirements for disclosure limitation while analyzing and sharing personal data. Using examples and some mathematical formalism, this talk will introduce differential privacy concepts including the definition of differential privacy, how differentially private analyses are constructed, and how these can be used in practice…more details
Causal/Prescriptive Analytics in Business Decisions
In-person | Talk
In this talk, I will provide a holistic review of the research methods and tools for causal analytics in business decisions. I focus especially on causal inference in data science. I will discuss a decision tree that helps data scientists to identify the best causal research method based on the problem, context, and the nature of the data. I will draw on my proprietary research on prescriptive analytics (https://docs.google.com/document/d/1b8yaDzriVB2JyIBNQMsUn-uz4bXnsdFe6hTLLTOs1q4/edit)…more details
Make Your Data Science Environment Just Right With Saturn Cloud
In-person | Demo Talk
In this demo, we’ll cover the best practices for setting up data science environments, how to store them so you can replicate your code, and how to share a setup with your coworkers…more details
An Introduction to Data Literacy with SQL
Virtual | Bootcamp | Data Analytics
Data literacy is an essential foundational topic for anyone considering data science or machine learning. This session will help one understand core data workflow concepts including what is data, data generation and collecting, data profiling, data transformation, data shaping, and other essential workflow topics. As this is an interactive training session, in addition to covering these data topics, we will layer on SQL and an introduction to relational databases…more details
Beyond the Basics: Data Visualization in Python
In-person | Half-Day Training | Machine Learning | Data Visualization | Intermediate-Advanced
While there are many plotting libraries to choose from, the prolific Matplotlib library is always a great place to start. Since various Python data science libraries utilize Matplotlib under the hood, familiarity with Matplotlib itself gives you the flexibility to fine tune the resulting visualizations (e.g., add annotations, animate, etc.). This session will also introduce interactive visualizations using HoloViz, which provides a higher-level plotting API capable of using Matplotlib and Bokeh (a Python library for generating interactive, JavaScript-powered visualizations) under the hood…more details
Machine Learning with Python: A Hands-On Introduction
In-person | Half-Day Training | Machine Learning | All Levels
By completing this hands-on workshop, you will develop an understanding of machine learning concepts and methodologies and learn how to fit, tune, and evaluate the predictive performance of a variety of parametric and non-parametric models for classification and regression. You will become familiar with how to preprocess data, build, tune, and cross-validate predictive models, and make predictions with the models in Python…more details
Large Scale Deep Learning using the High-Performance Computing Library OpenMPI and DeepSpeed
Virtual | Workshop | Deep Learning | MLOps & Data Engineering | Intermediate
OpenMPI is used for high-performance computing at supercomputing centers as part of distributed computing systems. In the first half of this workshop, we will get to know more about OpenMPI and work with it hands-on using a python interface. The second half of the workshop will focus on using DeepSpeed on OpenMPI and work through a few examples. Examples for MPI basics will include inferring pi using distributed computing and running python scripts using OpenMPI…more details
Any Way You Want It: Integrating Complex Business Requirements into ML Forecasting Systems
Virtual | Workshop
Regardless of their concrete application, the primary goal of forecasting systems is to produce the most accurate forecast possible. However, while beating benchmarks is important, a forecast useable in business processes additionally needs to fulfill many more criteria, which significantly increases the complexity of real-world solutions…more details
Self-Supervised and Unsupervised Learning for Conversational AI and NLP
Virtual | Workshop | NLP | Machine Learning | Beginner – Intermediate
In this talk, I will be giving some background in Conversational AI, NLP along with Self-supervised and Unsupervised techniques. Transformers-based large language models (LLMs) such as GPT-3, Jurasic, T5 have been foundational to the advances that we see. I will walk the audience through hands-on examples and how they can leverage transformers and large language models for few-shot, zero-shot learning in a variety of NLP applications such as text classification, summarization and question-answering…more details
Fighting Churn With Data
In-person | Workshop | Machine Learning | Beginner-Intermediate
This workshop will teach hands-on coding techniques covering all the foundations of a complete churn fighting data pipeline including churn measurement, feature engineering from raw data, data set creation, and machine learning. The workshop is taught using Python and SQL from the open source fightchurn package (pypi pypi.org/project/fightchurn/, github github.com/carl24k/fight-churn.) Participants should come with their own laptop prepared with Python and an IDE such as PyCharm or VSCode that will allow them to put breakpoints in code that will be demonstrated and discussed….more details
Foundations of Deep Reinforcement Learning
Virtual | Tutorial | Deep Learning | Intermediate-Advanced
Deep Reinforcement Learning equips AI agents with the ability to learn from their own trial and error. Success stories include learning to play Atari games, Go, Dota2, robots learning to run, jump, manipulate. This tutorial will cover the foundations of Deep Reinforcement Learning, including MDPs, DQN, Policy Gradients, TRPO, PPO, DDPG, SAC, TD3, model-based RL, as well as current research frontiers.…more details
Practical Tutorial on Uncertainty and Out-of-distribution Robustness in Deep Learning
In-person | Tutorial | Deep Learning | All Levels
Deep neural networks can make overconfident errors and assign high confidence predictions to inputs far away from the training data. Well-calibrated predictive uncertainty estimates are important to know when to trust a model’s predictions, especially for safe deployment of models in applications where the train and test distributions can be different. I’ll first present some concrete examples that motivate the need for uncertainty and out-of-distribution (OOD) robustness in deep learning…more details
Building a Semantic Search Engine
In-person | Half-Day Training | Deep Learning | Machine Learning | Beginner – Intermediate
Most production information retrieval systems are built on top of Lucene which use tf-idf and BM25. The current state of the art techniques utilizes embeddings for retrieval. This workshop aims to demystify what is involved in building such a system…more details
Self-Supervised and Unsupervised Learning for Conversational AI and NLP
In-person | Workshop | NLP | Machine Learning | Beginner – Intermediate
In this talk, I will be giving some background in Conversational AI, NLP along with Self-supervised and Unsupervised techniques. Transformers based large language models (LLMs) such as GPT-3, Jurasic, T5 have been foundational to the advances that we see. I will walk the audience through hands-on examples and how they can leverage transformers and large language models for few-shot, zero-shot learning in a variety of NLP applications such as text classification, summarization and question-answering…more details
Bagging to BERT – A Tour of Applied NLP
In-person | Workshop | All Levels
In this workshop, we will explore some of these popular NLP techniques that have broad applicability. From the basics of bagging and word vectors to the creating of contextualized representations of words and sentences, the workshop will equip participants with the tools they need to turn messy text data into useful insights. The focus of the workshop will be building NLP approaches with increasing complexity. Each step in the progression will build on the others and be evaluated against one another…more details
Separating the Signal from the Noise: Signal Processing and Feature Extraction Techniques for Biological Data
In-person | Workshop | All Levels
Your model is only as good as the data that goes into it, so removing the maximum amount of noise while retaining signal is vital. This talk will introduce basic signal processing and motion artefact removal techniques, such as low-pass filtering, Kalman filtering, and Savitzky-Golay filtering. The session will take you through practical examples that you can apply straight away to your biological data. I will also make recommendations for data collection to consider when designing a sensor so that you can get the best possible data (because prevention is better than treatment!). Those interested in machine learning and signal analysis for biomedical processing, electrical and optical signals, and wearables technology will enjoy this talk!…more details
StructureBoost: Gradient Boosting with Categorical Structure
In-person | Workshop | Machine Learning | Intermediate-Advanced
Often, categorical variables possess a natural structure that is not linear or ordinal in nature. The months of the year have a circular structure while the US states have a structure that can be represented by a graph. StructureBoost uses novel techniques that allow this known structure to be exploited to yield better predictions. Recently, StructureBoost has been enhance to utilize the structure in the target variable (i.e. in multi-classification) as well as in the predictor variables. This hands-on workshop will demonstrate how to use StructureBoost in different problems involving categorical variables with known structure…more details
Select date to see events.
