A hybrid self attentive linearized phrase structuredtransformer based RNN for financial sentenceanalysis with sentence level explainability

As financial institutions want openness and accountability in their automated systems, the task of understanding modelchoices has become more crucial in the field of financial text analysis. In this study, we propose xFiTRNN, a hybridmodel that integrates self-attention mechanisms, linearized phrase structure, and a contextualized transformer-basedRecurrent Neural Network (RNN) to enhance both model performance and explainability in financial sentence prediction.The model captures subtle contextual information from financial texts while maintaining explainability. xFiTRNN providestransparent, sentence-level insights into predictions by incorporating advanced explainability techniques such as LIME(Local Interpretable Model-agnostic Explanations) and Anchors. Extensive evaluations on benchmark financial datasetsdemonstrate that xFiTRNN not only achieves a remarkable prediction performance but also enhances explainability inthe financial sector. This work highlights the potential of hybrid transformer-based RNN architectures for fostering moreaccountable and understandable Artificial Intelligence (AI) applications in finance.