Towards Autonomous Formulaic Alpha Discovery: An Evolutionary Computation Perspective
2026-08-03 • Neural and Evolutionary Computing
Neural and Evolutionary Computing
AI summaryⓘ
The authors look at how computers can automatically find formula-based trading signals, which help predict market movements. They point out that existing methods face challenges like noisy data and changing markets, and usually study different algorithms separately. The authors propose a new way to see this problem as a symbolic evolutionary optimization task, and introduce frameworks to compare and improve methods based on factors like efficiency and reliability. Their work helps unify different approaches and supports better, more adaptable trading signal discovery systems.
formulaic alphaevolutionary computationsymbolic optimizationgenetic programmingfitness evaluationmarket nonstationaritytrading signalsmultiobjective optimizationreproducibilitybacktesting
Authors
Xinwei Yu, Yiyang Fu, Mingcheng Fan, Enqi Li, Yilin Gao, Shugong Xu
Abstract
Automated formulaic alpha discovery aims to generate predictive and interpretable trading signals from large symbolic factor spaces. Its effectiveness is constrained by noisy fitness estimates, market nonstationarity, costly backtesting, semantic redundancy, and conflicting practical objectives. Existing studies employ diverse techniques, including genetic programming (GP), evolutionary algorithms (EAs), reinforcement learning (RL), generative flow networks (GFlowNets), Monte Carlo tree search (MCTS), large language models (LLMs), and agentic workflows, but generally examine them as separate algorithmic families. This article introduces, for the first time, a unified evolutionary computation (EC) perspective on automated formulaic alpha discovery, formulating it as a noisy, dynamic, and multiobjective symbolic evolutionary optimization problem. A six-component analytical framework is developed to characterize existing methods through representation, variation, fitness evaluation, selection, memory, and adaptation. Furthermore, an eight-dimensional, autonomy-oriented evaluation framework is proposed, covering search efficiency, fitness reliability, residual alpha quality, economic diversity, tradability, evolutionary autonomy, robustness to nonstationarity, and reproducibility. Together, these frameworks provide a systematic foundation for unifying heterogeneous approaches, diagnosing component-level limitations, and guiding the development of reliable, adaptive, interpretable, and reproducible autonomous alpha discovery systems.