Documentation Index
Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt
Use this file to discover all available pages before exploring further.
Enhancements
December 13, 2021Model Performance Tab: Output Segmentation Analysis
**Confusion Matrix - **Given a model is set up with a default positive class (set this up on the config tab), we generate a matrix showcasing TF, FP, TN, FN counts of the dataset(s) to easily visualize model performance issues.
Model Performance Tab: Cohort Filtering
Various filter combinations can now be applied to individual datasets (or both datasets). Previously, filters were applied across both datasets by default.
In the News
December 13, 2021Best Practices for ML Monitoring and Observability of Demand Forecasting Models
This holiday season, having an ML observability strategy in place may be the difference between having enough inventory on-hand to meet holiday demand or losing out on millions of sales due to out-of-stock merchandise. Here’s our primer on ML monitoring and observability of demand forecasting models just in time for a season of snarled supply chains, snippy customers and sudden sleigh drift Read More
Ancestry CEO, Deb Liu, On Building Teams, Closing the Gender Gap, and Learning From Failure
Ancestry CEO Deb Liu recently joined us to talk about building teams, closing the gender gap in products, and learning from failure. Read the whole interview here.
Best Practices For ML Observability In Lending and Insurance with America First Credit Union
The lending and insurance industries are being transformed by AI, as financial services and insurance companies deploy ML models to inform everything from pre-eligibility checks to credit decisioning and premium pricing. In this webinar, Reah Miyara, Arize AI’s Head of Product, and Richard Woolston of Americas First Credit Union give an overview of ML observability, demo the Arize AI platform, and have a fireside chat on best practices for observing lending models in production. Watch it.
Security Notice: CVE-44228
December 15, 2021Summary
An open-source library, Log4J, used widely in many products worldwide has been reported (2021-12-09) to have a critical vulnerability, and is now published as CVE-2021-44228. This vulnerability allows Remote Code Execution and is easy enough to trigger that the CVSS score is 10. This vulnerability has been fixed in log4j-2.15.0 and greater. More information from the National Vulnerability Database can be found (here).As an Arize AI customer am I impacted?
Arize teams followed security protocol on 2021-12-10 09:03 and here is the conclusion of our Vulnerability Analysis report. Although the vulnerability is not directly exposed, to ensure future exploits are not possible in any case, we did do an update to use log4j-2.16.0 for impacted internal components.SAAS Platform
No action is required on your end, we are running our latest environment.On-Prem
Please reach out to Arize to follow the procedure to update your environment.Mitigation controls that prevent exploitation
- A EGRESS filtering firewall, would prevent the exploit payload to be loaded.
- A Web-Application Firewall can catch exploit payload before it reaches the server.
- Close monitoring of server process using an Intrusion Detection System would also detect the abnormal behavior of the application