Bi-Level Chaotic Fusion Based Graph Convolutional Network for Stock Market Prediction Interval

arXiv cs.LG Papers
stock-market prediction-interval graph-convolutional-network chaotic-fusion deep-learning financial-forecasting uncertainty-quantification

Summary

Proposes a bi-level chaotic fusion based graph convolutional network for stock market prediction intervals, achieving significant improvements in Winkler score, PIAW, and PICP over baselines on NSE data from 2016-2026.

arXiv:2605.16324v1 Announce Type: new Abstract: Financial market forecasting is inherently uncertain, yet most deep learning approaches rely on point predictions that provide only single-value estimates without quantifying uncertainty. Such predictions are insufficient for risk-aware decision-making, as they fail to capture the range of possible outcomes and the associated confidence of forecasts.The problem can be solved using prediction intervals, which allow obtaining an upper and lower bound for the prediction, thus enabling uncertainty representation in the model. Yet, the current methods tend to disregard relationships between assets or cannot simultaneously ensure good calibration and sharpness of the resulting intervals in dynamically changing market regimes. In our work, we propose a spatio-temporal graph-based approach with a bi-level chaotic fusion technique to solve this problem. Our model uses separate nonlinear transformation functions to estimate the interval center and width. Additionally, a volatility-aware gating mechanism is used to make predictions dependent on the regime in which the market operates. Temporal dependencies are considered by embedding graph structures and sequentially modeling them. Training is conducted according to a Lower-Upper Bound Estimation (LUBE) objective. Our experimental results show significant improvements compared to existing baselines (LSTM, GRU, GCN, HGNN) when applied to data from 2016 to 2026 with 43 leading companies in eight sectors of the NSE. It provides the lowest Winkler score (0.0778), tightest prediction intervals (PIAW = 0.1407), and highest coverage (PICP = 96.6%), with all differences statistically significant (p < 0.001) according to the Diebold-Mariano test.
Original Article
View Cached Full Text

Cached at: 05/19/26, 06:41 AM 

# Bi-Level Chaotic Fusion Based Graph Convolutional Network for Stock Market Prediction Interval
Source: [https://arxiv.org/abs/2605.16324](https://arxiv.org/abs/2605.16324)
[View PDF](https://arxiv.org/pdf/2605.16324)

> Abstract:Financial market forecasting is inherently uncertain, yet most deep learning approaches rely on point predictions that provide only single\-value estimates without quantifying uncertainty\. Such predictions are insufficient for risk\-aware decision\-making, as they fail to capture the range of possible outcomes and the associated confidence of[this http URL](http://forecasts.the/)problem can be solved using prediction intervals, which allow obtaining an upper and lower bound for the prediction, thus enabling uncertainty representation in the model\. Yet, the current methods tend to disregard relationships between assets or cannot simultaneously ensure good calibration and sharpness of the resulting intervals in dynamically changing market regimes\. In our work, we propose a spatio\-temporal graph\-based approach with a bi\-level chaotic fusion technique to solve this problem\. Our model uses separate nonlinear transformation functions to estimate the interval center and width\. Additionally, a volatility\-aware gating mechanism is used to make predictions dependent on the regime in which the market operates\. Temporal dependencies are considered by embedding graph structures and sequentially modeling them\. Training is conducted according to a Lower\-Upper Bound Estimation \(LUBE\) objective\. Our experimental results show significant improvements compared to existing baselines \(LSTM, GRU, GCN, HGNN\) when applied to data from 2016 to 2026 with 43 leading companies in eight sectors of the NSE\. It provides the lowest Winkler score \(0\.0778\), tightest prediction intervals \(PIAW = 0\.1407\), and highest coverage \(PICP = 96\.6%\), with all differences statistically significant \(p < 0\.001\) according to the Diebold\-Mariano test\.

## Submission history

From: Vivek Yelleti Dr\. \[[view email](https://arxiv.org/show-email/2276cbb3/2605.16324)\] **\[v1\]**Tue, 5 May 2026 05:06:42 UTC \(5,621 KB\)

Similar Articles

Horizon-Constrained Rashomon Sets for Chaotic Forecasting

arXiv cs.LG

Introduces horizon-constrained Rashomon sets to characterize how model multiplicity evolves in chaotic systems. The framework proves exponential contraction of predictive equivalence and develops decision-aligned algorithms that improve decision quality by 18-34%.