A MF-ConvLSTM-XAI model integrating multi-feature and fuzzy control for financial time series forecasting

Ruimin Liu, Shuihan Yi, Arman Ablikim, Xiaonan Song · 2025

Read A MF-ConvLSTM-XAI model integrating multi-feature and fuzzy control for financial time series forecasting by Ruimin Liu, Shuihan Yi, Arman Ablikim, Xiaonan Song (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12669620.txt.

Description

Ruimin Liu and co-authors propose in 2025 a forecasting model for financial time series that blends several feature types. Prices, trading volumes, and technical indicators are combined to capture market patterns. Existing methods struggle with nonlinear links and volatile conditions, and they often lack clear explanations.

Their model turns windowed data into image form, then applies a convolutional memory network. A fuzzy control mechanism reshapes the network's input gate. Explainable AI tools are added so users can see what drives each forecast. The authors aim for better accuracy and stability in rough markets, plus clearer reasoning behind predictions.

Catalog record

CREATORRuimin Liu, Shuihan Yi, Arman Ablikim, Xiaonan Song
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE68 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12669620

Browse the full library · About the Tower of Babel