News

Pre-trained foundation models are making time-series forecasting more accessible and available, unlocking its benefits for smaller organizations with limited resources.
We explore the added value of deep learning techniques for forecasting and nowcasting in official statistics as an alternative to classic time series models. Several neural network algorithms are ...
The 2023 paper “Time Series-Based Quantitative Risk Models: Enhancing Accuracy in Forecasting and Risk Assessment” by Olanrewaju Olukoya Odumuwagun, published in the International Journal of ...
The same model can be used to build multiple applications in time series. Synthefy’s foundation model brings multi-modal reasoning to time series forecasting.
Attention is not all you need when forecasting with generative AI. You also need time. IBM recently made its open-source TinyTimeMixer model available on Hugging Face.