You’ve invested significant time and resources into developing your machine learning models. But how do you get those models to production and manage all stages of the operational lifecycle once they’re there? Algorithmia is machine learning operations (MLOps) software that manages all stages of the ML lifecycle within existing operational processes. In this session, we’ll demonstrate Algorithmia in action and show you how it solves common management challenges to deploy models, connect to data sources, automatically scale model inference, and manage the ML lifecycle in a centralized model catalog.
We’ll demonstrate the process of deploying different types of models to Algorithmia that use different languages and frameworks. You’ll see us deploy regression, gradient boosting, image classification, sentiment analysis, and time-series forecasting models, add a series of model calls to construct a pipeline, test and publish new versions of a model, and call models from different languages. We’ll also discuss how Algorithmia handles the underlying MLOps infrastructure and operations related to security, scalability, and governance. Finally, we’ll demonstrate a metrics pipeline in Algorithmia that can be used to instrument your algorithms, calculate model performance metrics, monitor these metrics for changes, and trigger alerts and retraining jobs to mitigate model risk.