Paper: arXiv 2406.18394
Authors: Hao Shi, Weili Song, Xinting Zhang, Jiahe Shi, Cuicui Luo, Xiang Ao, Hamid Arian, Luis Seco
Abstract
The complexity of financial data, characterized by its variability and low signal-to-noise ratio, necessitates advanced methods in quantitative investment that prioritize both performance and interpretability.Transitioning from early manual extraction to genetic programming, the most advanced approach in the alpha factor mining domain currently employs reinforcement learning to mine a set of combination factors with fixed weights. However, the performance of resultant alpha factors exhibits inconsistency, and the inflexibility of fixed factor weights proves insufficient in adapting to the dynamic nature of financial markets. To address this issue, this paper proposes a two-stage formulaic alpha generating framework AlphaForge, for alpha factor mining and factor combination. This framework employs a generative-predictive neural network to generate factors, leveraging the robust spatial exploration capabilities inherent in deep learning while concurrently preserving diversity. The combination model within the framework incorporates the temporal performance of factors for selection and dynamically adjusts the weights assigned to each component alpha factor. Experiments conducted on real-world datasets demonstrate that our proposed model outperforms contemporary benchmarks in formulaic alpha factor mining. Furthermore, our model exhibits a notable enhancement in portfolio returns within the realm of quantitative investment and real money investment.
Complexity vs Empirical Score
- Math Complexity: 6.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper introduces advanced neural network architectures (generative-predictive models) and dynamic weighting schemes with some mathematical notation, but the core challenge is implementation-heavy. The rigorous validation via real-world datasets, portfolio simulations, and financial metrics like IC/ICIR positions it for practical application.
Research Flowchart
flowchart TD A["Research Goal<br>Alpha Factor Mining & Combination"] --> B["Input: Financial Market Data"] B --> C["Stage 1: Factor Mining<br>Generative-Predictive Neural Network"] C --> D["Stage 2: Dynamic Factor Combination<br>Time-Aware Weight Adjustment"] D --> E["Output: Adaptive Formulaic Alphas"] E --> F["Outcomes<br>Higher Returns & Better Adaptability"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes AlphaForge, a two‑stage framework that mines formulaic alpha factors with a generative‑predictive neural network and dynamically combines them with time‑varying weights.
Source sentence
this paper proposes a two-stage formulaic alpha generating framework AlphaForge, for alpha factor mining and factor combination.
Assumes 3
- Models are retrained annually with the preceding year as validation data. model
Source sentence
The model was retrained annually with updated data, using the year preceding the test year as the validation dataset, resulting in a total of five training sessions.
- The label used for training is Ref(VWAP, -21)/Ref(VWAP, -1) - 1, assumed to reflect real‑world scenarios. data
Source sentence
We use ’Ref(VWAP, -21)/Ref(VWAP, -1) - 1’ as the label because it more closely reflects real‑world scenarios, although it may lead to changes in the metrics.
- Trading is limited to changing at most 5 stocks per day to avoid excessive trading costs. execution
Source sentence
Additionally, a daily limit of changing a maximum of 5 stocks was imposed to avoid excessive trading costs.
Data
2018-01 – 2022-12 · CSI300 stocks · equities · daily
- CSI300 market-prices public
Source sentence
We choose the CSI300 and CSI500 dataset because the constituent stocks of these two indices cover the majority of the market capitalization in China’s A‑share market.
- CSI500 market-prices public
Source sentence
A real account was used with an investment of 3 million RMB in CSI500.
- Training/validation splits synthetic unknown
Source sentence
The first training set, validation set and test set are respectively (2010-01-01 to 2016-12-31), (2017-01-01 to 2017-12-31) and (2018-01-01 to
Qlib datasets
Costs
Partial
A daily limit of changing at most 5 stocks is imposed to avoid excessive trading costs; no explicit cost model is reported.
Source sentence
Additionally, a daily limit of changing a maximum of 5 stocks was imposed to avoid excessive trading costs.
Finds 3
- AlphaForge outperforms prior formulaic alpha approaches across metrics such as IC and RankIC. performance
Source sentence
As shown in Table 1, our method demonstrates superior performance across various metrics, including stock selection ability indicators such as IC and RankIC.
- The dynamic combination model yields higher returns than the static version, confirming the benefit of time‑varying weights. performance
Source sentence
Our findings indicate that our predictive‑generative alpha factor mining method achieves superior results compared to the previous state‑of‑the‑art algorithm. Furthermore, the superior performance of the ”Dynamic” model over the ”Static” model confirms the efficacy of our dynamic factor combining approach.
- In real‑money trading, the model generated a 21.68% higher excess return versus CSI500 over about nine months. performance
Source sentence
A real account was used with an investment of 3 million RMB in CSI500. Untill now, after approximately 9 months of investment, it has generated a 21.68% higher excess return compared to CSI500.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 17 related papers). Coverage is partial, so this is neither replication nor refutation.
12 papers in the archive : AlphaLogics: A Market Logic-Driven Multi-Agent System for … ; FactorBench: A Portfolio-Aware Benchmark for Automated … ; Alpha-R1: Alpha Screening with LLM Reasoning via … ; AlphaRLM: Aligning Language Models for Literature-Grounded … ; EFS: Evolutionary Factor Searching for Sparse Portfolio …
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (62)
- Blackboard Systems (1986)
- Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education (1983)
- Classification Problem Solving (1984)
- New Ways to Make Microcircuits Smaller (1980) — link
- New Ways to Make Microcircuits Smaller—Duplicate Entry (1980)
- Strategic explanations for a diagnostic consultation system (1984) — link
- Strategic Explanations in Consultation—Duplicate (1983)
- Poligon: A System for Parallel Problem Solving (1986)
and 54 more
- Transfer of Rule-Based Expertise through a Tutorial Dialogue (1979)
- The Engineering of Qualitative Models (2021)
- Attention Is All You Need (2017) — link
- Pluto: The ‘Other’ Red Planet (2015)
- 101 formulaic alphas (2016)
- A generative neural network for maximizing fitness and diversity of synthetic DNA and protein sequences (2020)
- The cross-section of expected stock returns (1992)
- Factorvae: A probabilistic dynamic factor model based on variational autoencoder for predicting cross-sectional stock returns (2022)
- Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning — → 2306.12964
- Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment — → 2308.00016
- AutoAlpha: An efficient hierarchical evolutionary algorithm for mining alpha factors in quantitative investment (2020) — link
- AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment (2021) — link
- Online detection of stealthy false data injection attacks in power system state estimation (2016)
- Xgboost: A scalable tree boosting system (2016)
- AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment (2021)
- A review on time series forecasting techniques for building energy consumption (2017)
- Long short-term memory (1997)
- A closer look at invalid action masking in policy gradient algorithms (2020) — link
- 101 formulaic alphas (2016)
- Factor Momentum and the Momentum Factor (2022) — link
- Lightgbm: A highly efficient gradient boosting decision tree (2017)
- Research on Product Sales Forecasting Based on Online Reviews and Data Mining (2023) — link
- Sales forecasting for Chemical Products by Using SARIMA Model (2022) — link
- Spatio-temporal self-supervised learning for traffic flow prediction (2023)
- Customer churn prediction using composite deep learning technique (2023)
- Revisiting Stock Alpha Mining Based On Genetic Algorithm (2019)
- Revisiting Stock Alpha Mining Based On Genetic Algorithm (2019)
- You impress me: Dialogue generation via mutual persona perception (2020) — link
- Symbolic regression via neural-guided genetic programming population seeding (2021) — link
- Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients (2021) — link
- Quantitative equity portfolio management: modern techniques and applications (2007)
- Learning equations for extrapolation and control (2018)
- Mastering atari, go, chess and shogi by planning with a learned model (2020)
- Proximal policy optimization algorithms (2017) — link
- How are you feeling?: A personalized methodology for predicting mental states from temporally observable physical and behavioral information (2017)
- Finding Alphas: A quantitative approach to building trading strategies (2019)
- Symbolicgpt: A generative transformer model for symbolic regression (2021) — link
- Attention is all you need (2017)
- DeepTrader: a deep reinforcement learning approach for risk-return balanced portfolio management with market conditions Embedding (2021)
- Hist: A graph-based framework for stock trend forecasting via mining concept-oriented shared information (2021) — link
- Rest: Relational event-driven stock trend forecasting (2021)
- Qlib: An ai-oriented quantitative investment platform (2020) — link
- Stock price prediction via discovering multi-frequency trading patterns (2017)
- AutoAlpha: An efficient hierarchical evolutionary algorithm for mining alpha factors in quantitative investment (2020) — link
- A unified framework for deep symbolic regression (2022)
- Neural symbolic regression that scales (2021)
- Data-driven discovery of coordinates and governing equations (2019)
- Age-fitness pareto optimization (2010)
- Geometric semantic genetic programming (2012)
- Epsilon-lexicase selection for regression (2016)
- Multiple regression genetic programming (2014)
- Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients (2021) — link
- Where are we now? A large benchmark study of recent symbolic regression methods (2018)
- A Unified Framework for Deep Symbolic Regression (2022) — link
2 of 62 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.