This paper presents the iterative technical evolution of the quantitative trading agent for the FinMMEval 2026 Task 3 challenge, detailing an initial baseline architecture that failed due to domain-blind lexical text processing and structural feature alignment anomalies, and detail the core feature innovation: a mathematically formulated recursive sentiment memory feature designed to preserve historical narrative contexts across successive trading days.
Predicting next-day stock movements from corporate announcements is a complex task, especially in markets where financial text is published in low-resource languages such as Arabic. In this study, we develop a hybrid, multimodal forecasting framework designed to capture both the semantic depth of Arabic announcements a...
Abdullah Almusned, Mohammad Mehedi Hassan, Muhammad Al-Qurishi et al.· International Journal of Adv...· 0 citations
Oilfield production forecasting serves as the decision-making basis for monthly production allocation and injection–production system optimization. Existing mainstream prediction methods face significant limitations: the Arps decline curve extrapolates historical production trends, yet its accuracy degrades rapidly fol...
We introduce the CDSP (context-conditional deliberation signal pipeline), converting an investment committee's meeting transcripts into structured predictive features. CDSP segments the meeting transcripts into topical chunks, assigns asset-class context labels using a large language model (LLM), maps financial keyword...
Vivek Batra, Kris Chen, Sanjiv R. Das et al.· 0 citations
An ERNIE-Transformer sentiment classification model that integrates ERNIE and Transformer architectures is proposed that achieves high classification accuracy for financial forum text sentiment analysis and provides an efficient and accurate solution for investor sentiment monitoring.
Xiu-Mei Li, Fei Chen, Wen-Chao Ling et al.· Journal of Electrical System...· 0 citations
In the overall comparison, FinBERT and DeBERTa-v3-base outperform the traditional baseline, whereas ModernBERT-base does not, indicating that the preferred encoder depends on the evaluation setting.
Xian-Hua Peng· Applied and Computational En...· 0 citations
Accurate prediction of equity returns remains a major challenge in computational finance due to the non-stationary, nonlinear, and low signal-to-noise ratio nature of financial time series. This paper proposes a hybrid two-stage architecture that combines a long short-term memory (LSTM) network with an XGBoost gradient...
