Quick Index for the Learning Sessions

[#1]

Learning sessions are a popular resource in the community. To make them easy to find, we've created this quick index. And, our SMEs are always interested in hearing ideas for new learning sessions! If you have a burning AI/ML/DR topic that you don't see covered already, please click Comment and send it along!

Types of content for learning sessions

• AI Success
• Industry Solutions
• Model Building
• Data Engineering

---

AI Success sessions

• Evaluating an AI Use Case—How to move forward successfully with machine learning use cases. 
• AI Problem Framing—Properly framed AI use cases are most effective at guiding businesses through current and future decision-making opportunities. This learning session presents considerations for framing effective AI use cases.
• Change Management in the AI Space—Community DataRobot experts discuss the importance of change management in machine learning, best practices, and more. Join this learning session and learn tips for managing change in your business.
• Identifying & Qualifying AI Use Cases—How to assess individual use cases and proactively identify and avoid blockers to getting an AI use case from data to business value.
• AI Practitioner Worksheet #1: The Path to AI Success—Helping AI practitioners develop use cases; provides The Path to AI Success worksheet to help stakeholders collaborate on use cases.

Industry Solutions sessions

• Gas & Oil—Response & Opportunity for Market Volatility—Some of the ways customers in natural resources industries can employ machine learning to get through the current global economic slowdown.
• AI in the Retail Industry—Retail trends and how AI as an enabling technology can transform the performance of a retail business.

Model Building sessions

• Automated Feature Engineering with Feature Discovery—Feature engineering is important and often time-consuming and even challenging. This learning session discusses some of the common FE techniques and how DataRobot's Feature Discovery tools help uncomplicate FE.
• Visual AI—You've built your first set of image models using DataRobot's new Visual AI capability. So, now what comes next? How can you improve model accuracy? How can you understand what the models are learning? And, all of the built-in Image Insights look cool—how can you use them to drive modeling decisions? This learning session explains how to best leverage Visual AI in your machine learning projects.
• Model Explainability with SHAP in DataRobot—Understanding how a model makes its predictions helps you trust the model. This session introduces DataRobot's use of SHAP values (Shapley values) which help explain models and how they arrive at their predictions.
• Trust Bias in AI—Discussion of the theoretical understanding of bias and fairness, and demonstration of how DataRobot can help you tackle AI bias.
• Improving Time Series Models—Tips and tricks for developing highly effective and competitive machine learning models for time series forecasting.
• Best Practices for Imbalanced Data and Partitioning—Best practices around data partitioning and working with imbalanced datasets.
• Building Neural Networks with Keras—Ways neural networks and deep learning benefit from DataRobot Keras models.
• Reducing Costs with Predictive Maintenance—Numerous Qs&As around machine learning for predictive maintenance.
• DataRobot Location AI for AutoML—Introduction to DataRobot's Location AI capabilities and explanation of the industries and use cases that stand to benefit immediately from the emerging use of geospatial analysis in their machine learning workflows.
• Using Small Datasets to Build Models—Challenges and strategies for building effective models when data is limited. 
• Explanation Clustering—Advanced techniques for using Prediction Explanations in DataRobot and introduction to a recommended technique, explanation clustering.
• Best Practices for Setting Up a DataRobot Project—Common modeling pitfalls and best practices to avoid them.
• Integrate DataRobot Models with Alteryx—Walkthrough of integrating DataRobot models with an Alteryx workflow.
• Selecting Target Variables in Modeling— Exploration of an important piece of ML that is often missing: creating the target variable.
• Model Building--Autopilot Done, Now What? —Considerations when choosing a model to deploy after building models with DataRobot.
• The Latest and Greatest in DS/ML—DataRobot 6.1—Introduction and demo of the data science / machine learning features and enhancements included in DataRobot 6.1.
• Earth Day—Green ML—Earth Day discussion around how to make AI and ML "green" and efficient. 

• Oct 8—Data Cheats: How Target Leakage Affects Models—Explanation of target leakage and its impact on ML models, and how the DataRobot platform detects it automatically.

Data Engineering sessions

• Code Generation—Predictions with Scoring Code—Exploration of DataRobot's exportable scoring code and several ways you can integrate these models into your data pipelines to achieve real operational value.
• Scalable Batch Predictions—How to use the Batch Prediction API for scoring datasets, especially large datasets.
• Interactive Dashboards—Big Data & ML—Ways to generate insights from big data and machine learning, and considerations for a building scoring pipeline for interactive dashboards.
• Monitoring All Your Models with DataRobot Agents—Do you have machine learning models that are running outside of DataRobot? Is your organization using a set of diverse tools and platforms to deploy models, despite what IT wants? This session introduces DataRobot's MLOps agent framework which allows anyone to monitor models deployed externally, to DataRobot MLOps platform.
• Model Creation and Scoring from Data—Guidance for using databases (specifically Snowflake) with DataRobot.