Work by Aldan Jay and coauthors. Published papers and an oral communication are distinguished throughout.
6 items shown1 item shown1 item shown1 item shown3 items shown
Aldan Jay; Rafael Berlanga.
We compare a Wavelet–Transformer model with persistence for Bitcoin price forecasting. In the reported one-day test, the more complex model does not outperform the last observed price. The result concerns this model and this test.
Algorithms · 19(2) · 101 · Published
Aldan Jay; Rafael Berlanga; Yoelvis Moreno; Vicent Santamarta.
We study verbatim extraction of causal spans from financial texts in English and Spanish. VERSA combines specialised agents, question rephrasing and iterative aggregation. Development results improve on a single-pass baseline; some component tests remain preliminary estimates.
The 7th Financial Narrative Processing Workshop @ LREC 2026 · ELRA · 139–145 · Published
Aldan Jay; Rafael Berlanga.
An oral presentation at BLOCKCHAIN’26 on using blockchain to make AI explanations checkable in decentralised finance workflows involving agents. No published paper is available.
BLOCKCHAIN’26 · Naples · 21–23 October 2026 · Oral communication
V. Casales-Garcia; A. Jay; Ll. Museros; I. Sanz; L. Gonzalez-Abril.
We study regional scent profiles and the relationship between expected scents and dish colours. Scent profiles differ across groups, while regional colour-coherence effects are negligible and cease to be significant after adjusting for recipe composition.
Artificial Intelligence Research and Development · IOS Press · 73–82 · Published
V. Casales-Garcia; Aldan Jay; L. Museros; I. Sanz; L. Gonzalez-Abril.
We classify gastronomic regions using interpretable colour features and dish-type indicators. The study compares several models with a stratified baseline and examines which features contribute to the predictions.
International Journal of Computational Intelligence Systems · 19 · 224 · Published
V. Casales-Garcia; A. Jay; I. Sanz; L. Museros.
We compare colours associated with ingredient scents with dominant colours in photographs of dishes. Recipes and an olfactory lexicon provide a descriptive view of scent–colour correspondence.
Artificial Intelligence Research and Development · IOS Press · 153–162 · Published