Pragmatic-applications-webinar

Webinar

Pragmatic Applications Series

  Live

  30 minutes

Join us every Wednesday for a 30-minute Arize overview session. We’ll answer your questions live and guide you through a specific use case every week. These workshops will give you insight into fundamental Arize use cases to better navigate key feature sets and maximize model improvements.

Improving Churn Models | November 2, 9am PST

You are a machine learning engineer at a credit card company who is responsible for building a model to predict customer churn. After building your model, you will need to monitor its performance, drift, as well as any data quality issues in production. Arize will show you how to monitor and troubleshoot performance, drift and data quality issues in production.

In this workshop, you’ll learn best practices for how to:

  • Set-up performance, drift and data quality monitoring to better understand how your model is performing.
  • Discover feature drifts corresponding to time periods of performance degradation and how to resolve them.
  • Check to see if explainability and algorithm bias are having an impact on your model decisions.
Detecting Fraud | November 9, 9am PST

Every year, fraud costs the global economy over $5 trillion. AI practitioners are on the front lines of this battle building and deploying sophisticated ML models to detect fraud, saving organizations billions of dollars in the process. Of course, it’s a challenging task as fraud takes many forms and attacks vectors across industries. ML teams need an approach that is both reactive in monitoring key metrics and proactive in measuring drift, counter-abuse ML teams.

In this webinar, you’ll learn best practices for how to:

  • Account for model, feature and actuals drift to ensure your models stay relevant
  • Troubleshoot performance degradations across various cohorts
  • Avoid common pitfalls from misleading evaluation metrics to imbalanced datasets
NLP Classification | November 16, 9am PST

From images and video to natural language and audio, unstructured data coupled with machine learning can unlock deeper AI potential and ROI for many organizations and use cases. Embeddings are the core of how deep learning models represent structures and are fundamental to how the next generation of ML models work.

Join this workshop to:

  • Troubleshoot a sentiment classification model in production
  • Learn about emerging techniques like UMAP to transform unstructured data into embeddings that can be more efficiently processed by ML models
  • Implement new technologies to monitor and improve models in production
Optimize Demand Forecasting | November 30, 9am PST

You are a machine learning engineer at a retail company that maintains and monitors a demand forecasting regression model that predicts the one week unit quantity demanded for items in your stores. The business objective of your ML model is so that your store fronts can supply them exactly the number of items demanded on time, as predicted by your model. You have been alerted to calls about stores overshelfing and unhappy customers in the last month due to mispredictions by your demand forecasting model, so you turn to Arize to gain insight as to why.

In this workshop, you’ll learn best practices for how to:

  • Set-up performance, drift and data quality monitoring to better understand our model performance.
  • Discover feature drifts corresponding to time periods of performance degradation and how to resolve them.
  • Check to see if explainability and algorithm bias are having an impact on your model decisions.

Register

Speakers

Amber Roberts
Machine Learning Engineer

Amber Roberts is an astrophysicist and machine learning engineer who was previously the Head of AI at Insight Data Science. Since then she has been at Splunk in their ML Product Org to build out ML feature solutions as a ML Product Manager. She now joins us at Arize as a ML Sales Engineer looking to help teams across industries build ML Observability into their productionalized AI environments.

Get ML observability in minutes.

Get Started