As ML practitioners deploy more models into production, the stakes for model performance are higher than ever — and the mistakes costlier… — Part One: From No Monitoring to Monitoring To paraphrase a common bit of wisdom, if a machine learning model runs in production and no one is complaining, does it mean the model is perfect? The unfortunate truth is that production models are usually left alone unless they lead to negative business impacts.

Compared to DevOps or data engineering, MLOps is still relatively young as a discipline despite tremendous growth. While it’s tempting to… — Compared to DevOps or data engineering, MLOps is still relatively young as a discipline despite tremendous growth. While it’s tempting to draw parallels to DevOps in particular since some of its best practices easily carry over into MLOps, most in the industry agree there are a unique set of challenges…

Tips for improving LTV model performance in production — Written in collaboration with Reah Miyara, Head of Product at Arize AI The age-old saying still holds: the customer is always right, but some are more right than others (that’s the saying, right?). While there are many metrics to estimate the value of a customer within any organization, customer lifetime…

Welcome to “The Slice,” a new blog series that explains the essence of ML concepts — Written in collaboration with Amber Roberts, ML Sales Engineer at Arize AI The adoption of machine learning (ML) has resulted in an array of artificial intelligence (AI) applications in the growing areas of language processing, computer vision, unsupervised learning and even autonomous systems. As models increase in complexity, the ability…

Tips to keep clicks rolling in over the holidays and beyond — Written in collaboration with Reah Miyara, Head of Product at Arize AI Total digital ad spending is expected to reach $455.3 billion this year. Of that, 55.2% will go to display advertising and 40.2% will go to search. With digital formats commanding the lion’s share of ad dollars, marketers need…

Best practices for ML monitoring and observability of demand forecasting models just in time for a season of snarled supply chains, snippy… — Written in collaboration with Reah Miyara, Head of Product at Arize AI Demand forecasting is the time-tested discipline of using historical data, traditionally on purchases, to forecast customer demand over a given time period. Critical to operations and pricing strategy, nearly every category of business uses demand forecasting in some…

Best practices in ML observability for monitoring, mitigating and preventing fraud — Written in collaboration with Reah Miyara, Head of Product at Arize AI Every year, fraud costs the global economy over $5 trillion. In addition to taking a deeply personal toll on individual victims, fraud impacts businesses in the form of lost revenue and productivity as well as damaged reputation and…

A guide to optimizing ML service latency and ML inference latency — Over the last decade, a wave of renewed interest in machine learning has encouraged countless researchers to attempt to solve problems with state of the art machine learning techniques. …

A primer on the different levels of explainability and how each can be used across the ML lifecycle — In the last decade, significant technological progress has been driven rapidly by numerous advances in applications of machine learning. Novel ML techniques have revolutionized industries by cracking historically elusive problems in computer vision, natural language processing, robotics, and many others. …