article thumbnail

Demand forecasting at Getir built with Amazon Forecast

AWS Machine Learning Blog

Among those algorithms, deep/neural networks are more suitable for e-commerce forecasting problems as they accept item metadata features, forward-looking features for campaign and marketing activities, and – most importantly – related time series features. She has 12 years of software development and architecture experience.

article thumbnail

Principal Financial Group uses AWS Post Call Analytics solution to extract omnichannel customer insights

AWS Machine Learning Blog

This Lambda function identifies CTR records and provides an additional processing step that outputs an enhanced transcript containing additional metadata such as queue and agent ID information, IVR identification and tagging, and how many agents (and IVRs) the customer was transferred to, all aggregated from the CTR records.

article thumbnail

Definite Guide to Building a Machine Learning Platform

The MLOps Blog

To make that possible, your data scientists would need to store enough details about the environment the model was created in and the related metadata so that the model could be recreated with the same or similar outcomes. You need to build your ML platform with experimentation and general workflow reproducibility in mind.