神经符号框架：在线自适应模糊认知图结合 LSTM 做金融预测
Online-Adaptive Fuzzy Cognitive Maps for Neuro-symbolic Financial Forecasting
做量化或金融建模的可以看看这篇：用带引用的 FCM 图谱让预测过程可审计，收益符号准确率比纯 LSTM 高 7.6 个百分点，换市场状态后 10-15 天就能自适应。想解释模型为什么这么预测的团队会感兴趣。
一项研究提出神经符号框架，将在线自适应 Fuzzy Cognitive Maps（FCM）与 LSTM 网络配对用于金融预测。
Framework I 从双源价格序列与宏观经济指标构建 FCM，通过误差驱动的 Hebbian 规则在线更新边权重，并用 Asymmetric Additive Residual Fusion 方法融合 FCM 与 LSTM 的预测。
在 NASDAQ Composite 数据上，Framework I 在状态方向准确率上与 LSTM 基线持平，在收益符号准确率上高出 LSTM 基线 7.6 个百分点，并在两项指标上均超过独立 FCM 模型；
自适应图在 10-15 个交易日内收敛到新市场状态。Framework II 则构建基于文献、LLM 增强的 FCM，每条边附带可验证引用，形成可审计的因子交互图谱，其中心节点模型的状态方向准确率达 68.
9% 至 85.7%。
现有时序模型往往只捕捉时间模式而隐藏因果驱动，因果图模型又难以在训练后继续适应，该工作试图同时兼顾两者。
Online-Adaptive Fuzzy Cognitive Maps for Neuro-symbolic Financial Forecasting
We present a neuro-symbolic framework that pairs online-adaptive Fuzzy Cognitive Maps (FCMs) with long short-term memory (LSTM) networks for financial forecasting. Financial markets exhibit regime shifts and nonlinear dynamics. Existing models often trade off one of these key properties: these models capture temporal patterns but hide causal drivers, or they recover causal graphs that cannot adapt post-training. We close this gap with two frameworks. Framework I constructs an FCM from live dual-source price series and macroeconomic indicators, and adapts its edges online through an error-driven Hebbian rule. We introduce the Asymmetric Additive Residual Fusion method to seamlessly combine the FCM and LSTM predictions under Framework I. Framework II constructs a literature-grounded, LLM-augmented FCM where every edge carries a verifiable citation that gives an auditable map of factor interactions. On NASDAQ Composite data, Framework I matched the performance of the LSTM baseline on state-directional accuracy and outperformed LSTM by 7.6 percentage points on the return-sign accuracy. Framework I outperformed standalone FCM models across both evaluation metrics. The adaptive maps converged to new regimes within 10-15 trading days, and Framework II center-node FCMs scored 68.9% to 85.7% on the state-directional accuracy.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Fuzzy Cognitive Maps, LSTM, 金融预测, 神经符号.
Source attribution: curated from arXiv cs.AI (@Brandon Rodriguez, Abel Deulofeu, Olaoluwa Adigun).