In general there are two broad phases in any machine learning deployment – (a) training, where the machine learning model is learned and (b) inference, where the machine learning transforms raw data into predictions, prescriptions (like Uplift Modeling), recommendations, and look-alikes.
New Feature : Smart Training
Setting the right cadence used for training a model allows a business to ensure the model is using the best data. As of last week, Cortex automates when to retrain a model in order to maintain strong ongoing performance. When continuous predictions are specified in the UI, Smart Training will be automatically enabled for that pipeline.
New Feature : Granular Batch Inference Schedules
We added more flexibility to the batch inference schedules enabling our customers to schedule when to generate predictions. Users are now able to schedule daily, weekly, or monthly schedules for machine learning pipelines.
Check out the new functionality in your Cortex account and let us know what you think! If you have any questions or want to learn more please reach out to us at email@example.com!