FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization

2026-06-27

AI Summary

This study addresses the challenge of interpretable prediction in venture capital decision-making under conditions of multi-source heterogeneous data, non-stationary time series, and small-sample, high-risk scenarios. The authors propose a unified graph-temporal-causal architecture that integrates a relational graph encoder, a multi-scale temporal fusion module, and a causal decision head. To enhance generalization to new domains, they introduce a Meta-Causal Adaptation (MCA) strategy that leverages meta-pretraining to learn causally plausible structures. Evaluated on a proprietary venture capital dataset, the proposed method reduces risk-adjusted mean squared error (RA-MSE) to 2.51—outperforming the baseline of 3.05—and achieves an 18.7% improvement in cumulative returns for simulated investment portfolios, significantly surpassing existing approaches.

Abstract

Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings. To overcome these issues, we introduce \textbf{FinInvest-GTCN}, a Graph-Temporal-Causal Network that redefines the task from content recommendation to quantitative risk-return assessment. This architecture combines a relational graph encoder to capture the investment ecosystem's topology, a multi-scale temporal fusion module to handle long-term dependencies and non-stationarity, and a causal decision head that generates risk-adjusted predictions with interpretable causal attributions. A core innovation is the Meta-Causal Adaptation (MCA) strategy, which facilitates robust fine-tuning for new, data-scarce sectors by aligning updates with causally-plausible structures derived from meta-pretraining. Comprehensive experiments on proprietary VC datasets show that FinInvest-GTCN delivers state-of-the-art results, markedly lowering the primary Risk-Adjusted Mean Squared Error (RA-MSE) to 2.51 from a baseline of 3.05 and boosting the cumulative return of a simulated portfolio by 18.7\%. Ablation studies underscore the essential role of each component, while additional analyses confirm the model's stability, interpretability, and enhanced adaptability. This work pioneers a data-driven, explainable framework for investment decision support.

Problem

• venture capital
• risk-aware investment
• explainable AI
• non-stationary time series
• heterogeneous data

Innovation

• Graph-Temporal-Causal Network
• Meta-Causal Adaptation
• Explainable AI
• Risk-Adjusted Prediction
• Non-stationary Time Series