Salesforce
Assembly Line
Unified Training of Universal Time Series Forecasting Transformers
Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time Series Model capable of addressing diverse downstream forecasting tasks. However, constructing such a model poses unique challenges specific to time series data: i) cross-frequency learning, ii) accommodating an arbitrary number of variates for multivariate time series, and iii) addressing the varying distributional properties inherent in large-scale data. To address these challenges, we present novel enhancements to the conventional time series Transformer architecture, resulting in our proposed Masked Encoder-based Universal Time Series Forecasting Transformer (Moirai). Trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains, Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models.
Rootstock Debuts AIRS™: Cutting-Edge AI for Manufacturers
Rootstock Software, a recognized leader in the Manufacturing ERP space, is thrilled to announce the launch of AIRS. Short for “Artificial Intelligence (AI) from Rootstock (RS).” Built on Salesforce Einstein 1 Platform, AIRS leverages Rootstock’s unique ERP dataset—including order, supply, financial, and production data. This dataset is collected from across the Signal Chain—from CRM, SCM, PLM, IoT platforms and other systems. As a result, AIRS enables a complete Signal Chain Decisioning Platform, as it bridges the physical and digital worlds and enables smart, autonomous decisions that will redefine manufacturing innovation.