Scalable forecasts for IoT in the cloud

This week at the International Conference on Data Mining, IBM Research-Ireland scientist Francesco Fusco demonstrated IBM Research Castor, a system for managing time series data and models at scale and on the cloud. Businesses of today run on forecasts. Whether a hunch of what we think is going to happen or the product of carefully honed analysis, we have a picture of what's going to happen and we act accordingly. IBM Research Castor is for IoT-driven businesses needing hundreds or thousands of different forecasts for time series. Although the model for an individual forecast may be small, keeping up with the provenance and performance of this number of models can be a challenge. In contrast to AI-driven cases using a small number of big models for image processing or natural language, this work aims at the IoT applications needing a large number of smaller models.

from Hi-Tech Innovation News - Information Technology, Inventions News https://ift.tt/2Aoya8J

SHARE SHARE SHARE