Data and concept drift are frequently mentioned in the context of ML monitoring, but what exactly are they and how are they detected? Furthermore, given the common misconceptions surrounding them, are data and concept drift things to be avoided at all costs or natural and acceptable consequences of training models in production? Read on to find out. In this article we will provide a granular breakdown of data and concept drift, along with methods for detecting them and best practices for dealing with them when you do.
Posts by Itai Bar Sinai, Co-founder and CPO:
In the past 3 years I’ve been working with teams implementing automated workflows using ML/DL, NLP, RPA, and many other techniques, for a myriad of business functions ranging from fraud detection, audio transcription all the way to satellite imagery classification. At various points in time, all of these teams realized that alongside the benefits of automation they have also added additional risk. They have lost their “eyes and ears on the field”, the natural oversight you get by having humans in the process. Now, if something goes wrong, there isn’t a human to notify them, and if there’s a place in which an improvement could be made, there might not be a human to think about it and recommend it. Put differently, they realized that humans weren’t only performing the task that is now automated, they were also there, at least partially, to monitor and QA the actual workflow. While each business function is different, and every automation or AI that is used has its own myriad of intricacies and things requiring monitoring and observing, one common thread binding all of these use-cases is that issues and opportunities for improvement usually appear in pockets, as opposed to grand sweeping, across the board.
At Mona, we strive to enable better visibility into AI systems in order to reduce the associated risk with production AI, optimize the operational processes around versions and releases, and plan better AI roadmaps using feedback based on production data.
As our customer base grows and the number of production AI use-cases being monitored by Mona increases, our team has been working tirelessly to advance our product to become a best in class AI observability solution.
Just recently we published an important update on our growth, from recent customers to our team growth. Today, I’d like to go a little deeper on our current product and share how we’ve been expanding it in multiple areas to create value for our customers.
As AI systems become increasingly ubiquitous in many industries, the need to monitor these systems rises. AI systems, much more than traditional software, are hypersensitive to changes in their data inputs. Consequently, a new class of monitoring solutions has risen at the data and functional level (rather than the infrastructure of application levels). These solutions aim to detect the unique issues that are common in AI systems, namely concept drifts, biases, and more.