AI Briefing#forecasting
The latest AI and developer news about #forecasting, with the original source and a short summary.
The latest AI and developer news about #forecasting, with the original source and a short summary.
IBM has unveiled Granite Timeseries Ensemble R1, which combines four time series models.
The open-source model uses a MOMENT-1-large backbone and DARR mode to blend direct predictions with k-nearest-neighbor retrieval from historical data.
The open-source release includes 5M to 209M parameter checkpoints supporting zero-shot forecasting with up to 32,768 historical time steps.
The system provides 30 to 60 minutes of advance warning and detected nearly 80% of major space-weather events during evaluation.
IBM has released Granite PatchTST-FM-r2, a time series foundation model licensed under Apache 2.0.
The LEAP panel forecasts a surge in data center investment and a slowdown in semiconductor growth, while predicting continued revenue growth for OpenAI and Anthropic.
Airbnb provided criteria for deciding whether to refit, respecify, or hold models during retraining.
OpenAI shared its experience redesigning finance operations around AI and five key lessons.
Datadog announced Toto-2.0, a new time-series forecasting model capable of parallel processing and highly scalable.
A research paper has been published arguing that a Dynamical Systems Reconstruction (DSR) perspective should be adopted to overcome the limitations of time series modeling.
Finance teams use Codex to quickly draft monthly business reviews (MBR), variance analyses, and forecasts.
PwC and OpenAI have begun a collaboration to apply AI agents to the CFO organization.
Afresh's AI demand forecasting has cut grocery store waste by up to 25%.
His 2021 prediction of AI 2026 was surprisingly accurate, but he missed on information warfare and physical infrastructure.
ChatGPT makes finance teams' reporting, budgeting, and audit work faster and more consistent.
The booking-to-trip structure broken by COVID was restored through a decomposed model and structural break response.
**EMBERS** is an old model, but its way of evaluating future forecasts and fusing warnings is still valid today.
It introduces how to combine Replit Agent with Snowflake to build advanced data apps with forecasting and alert features.
TabPFN is a pretrained Transformer that produces fast baselines on small tabular data.
This explains the structure of PatchTST, a model that improves time-series forecasting performance, and how to use it with the Hugging Face library.
IBM Research's lightweight time series model PatchTSMixer has been integrated into the HuggingFace Transformers library.
The transformer-based model Autoformer has proven superior to the simple linear model DLinear in time series forecasting performance.
Coupang used LightGBM and Bayesian Optimization to predict the number of inbound trucks, reducing dock slot waste.