Nature

Two forecasting model selection methods based on time series image feature augmentation

Accurate forecasting of food commodity prices is one of the most challenging yet crucial tasks for agricultural economists. Timely and reliable price predictions not only support market participants ...
Nature

A multiscale model for multivariate time series forecasting

Transformer based models for time-series forecasting have shown promising performance and during the past few years different Transformer variants have been proposed in time-series forecasting domain.
Forbes

IBM Improves Generative AI Forecasting Using Time, Not Just Attention

According to IBM, attention is not all you need when forecasting certain outcomes with generative AI. You also need time. Earlier this year, IBM made its open-source TinyTimeMixer (TTM) model ...
VentureBeat

IBM Granite 3.2 uses conditional reasoning, time series forecasting and document vision to ...

In the wake of the disruptive debut of DeepSeek-R1, reasoning models have been all the rage so far in 2025. IBM is now joining the party, with the debut today of its Granite 3.2 large language model ...