Similar articles

Abstract: The field of artificial intelligence (AI) in quantitative investment has seen significant advancements, yet it lacks a standardized benchmark aligned with industry practices. This gap hinders research progress and limits the practical application of academic innovations. We present QuantBench, an industrial-grade benchmark platform designed to address this critical need. QuantBench offers three key strengths: (1) standardization that aligns with quantitative investment industry practices; (2) flexibility to integrate various AI algorithms; (3) full-pipeline coverage of the entire quantitative investment process. Our empirical studies using QuantBench reveal some critical research directions, including the need for continual learning to address distribution shifts, improved methods for modeling relational financial data, and more robust approaches to mitigate overfitting in low signal-to-noise environments. By providing a common ground for evaluation and fostering collaboration between researchers and practitioners, QuantBench aims to accelerate progress in AI for quantitative investment, similar to the impact of benchmark platforms in computer vision and natural language processing. The code is open-sourced on GitHub at https://github.com/SaizhuoWang/quantbench.

QuantBench：全流水线视角的AI量化投资方法评估基准

[1]Bai SJ, Kolter JZ, Koltun V, 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. https://arxiv.org/abs/1803.01271

[2]Cao BK, Lin XY, Qi YY, et al., 2025. Financial wind tunnel: a retrieval-augmented market simulator.

[3]Cattaneo MD, Crump RK, Farrell MH, et al., 2020. Characteristic-sorted portfolios: estimation and inference. Rev Econ Stat, 102(3):531-551.

[4]Chen TQ, Guestrin C, 2016. XGBoost: a scalable tree boosting system. Proc 22^nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.785-794.

[5]Chen YM, Wei ZY, Huang XJ, 2018. Incorporating corporation relationship via graph convolutional neural networks for stock price prediction. Proc 27^th ACM Int Conf on Information and Knowledge Management, p.1655-1658.

[6]Cheng DW, Yang FZ, Wang XY, et al., 2020. Knowledge graph-based event embedding framework for financial quantitative investments. Proc 43^rd Int ACM SIGIR Conf on Research and Development in Information Retrieval, p.2221-2230.

[7]Cui C, Wang W, Zhang MH, et al., 2021. AlphaEvolve: a learning framework to discover novel alphas in quantitative investment. Proc Int Conf on Management of Data, p.2208-2216.

[8]Deng J, Dong W, Socher R, et al., 2009. ImageNet: a large-scale hierarchical image database. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.248-255.

[9]Deng SM, Zhang NY, Zhang W, et al., 2019. Knowledge-driven stock trend prediction and explanation via temporal convolutional network. World Wide Web Conf, p.678-685.

[10]de Prado ML, 2018. Advances in Financial Machine Learning. John Wiley & Sons, Hoboken, USA.

[11]Ding Q, Wu S, Sun H, et al., 2021. Hierarchical multi-scale Gaussian Transformer for stock movement prediction. Proc 29^th Int Joint Conf on Artificial Intelligence, p.4640-4646.

[12]Du YT, Wang JD, Feng WJ, et al., 2021. AdaRNN: adaptive learning and forecasting of time series. Proc 30^th ACM Int Conf on Information & Knowledge Management, p.402-411.

[13]Feng FL, He XN, Wang X, et al., 2019. Temporal relational ranking for stock prediction. ACM Trans Inform Syst, 37(2):27.

[14]Gao Y, Chen HK, Wang X, et al., 2024. DiffsFormer: a diffusion Transformer on stock factor augmentation.

[15]Grinsztajn L, Oyallon E, Varoquaux G, 2022. Why do tree-based models still outperform deep learning on typical tabular data? Proc 36^th Int Conf on Neural Information Processing Systems, Article 37. https://dl.acm.org/doi/10.5555/3600270.3600307

[16]He CM, Shen YQ, Fang CY, et al., 2025. Diffusion models in low-level vision: a survey. IEEE Trans Pattern Anal Mach Intell, 47(6):4630-4651.

[17]Hochreiter S, Schmidhuber J, 1997. Long short-term memory. Neur Comput, 9(8):1735-1780.

[18]Hu ZX, Zhao YQ, Khushi M, 2021. A survey of forex and stock price prediction using deep learning. Appl Syst Innov, 4(1):9.

[19]Huynh TT, Nguyen MH, Nguyen TT, et al., 2022. Efficient integration of multi-order dynamics and internal dynamics in stock movement prediction. Proc 16^th ACM Int Conf on Web Search and Data Mining, p.850-858.

[20]Jiang WW, 2021. Applications of deep learning in stock market prediction: recent progress. Expert Syst Appl, 184:115537.

[21]Jiang ZY, Xu DX, Liang JJ, 2017. A deep reinforcement learning framework for the financial portfolio management problem.

[22]Kakushadze Z, 2016. 101 formulaic alphas. http://arxiv.org/abs/1601.00991

[23]Ke GL, Meng Q, Finley T, et al., 2017. LightGBM: a highly efficient gradient boosting decision tree. Proc 31^st Int Conf on Neural Information Processing Systems, p.3149-3157.

[24]Kelly B, Xiu D, 2023. Financial machine learning. Found Trends Finance, 13(3-4):205-363.

[25]Kipf TN, Welling M, 2017. Semi-supervised classification with graph convolutional networks. 5^th Int Conf on Learning Representations.

[26]Koa KJL, Ma YS, Ng R, et al., 2024. Learning to generate explainable stock predictions using self-reflective large language models. Proc ACM Web Conf, p.4304-4315.

[27]Li C, Liu FB, 2017. Multi-Factor Stock Selection via Short-Term Volume–Price. Guotai Junan Securities, Hong Kong, China.

[28]Li WD, Yang X, Liu WQ, et al., 2022. DDG-DA: data distribution generation for predictable concept drift adaptation. Proc 36^th AAAI Conf on Artificial Intelligence, p.4092-4100.

[29]Liu T, Roberts S, Zohren S, 2023. Deep inception networks: a general end-to-end framework for multi-asset quantitative strategies.

[30]Liu XY, Xia ZY, Rui JY, et al., 2022. FinRL-Meta: market environments and benchmarks for data-driven financial reinforcement learning. Proc 36^th Int Conf on Neural Information Processing Systems, Article 134. https://dl.acm.org/doi/abs/10.5555/3600270.3600404

[31]Liu Y, Liu Q, Zhao HK, et al., 2020. Adaptive quantitative trading: an imitative deep reinforcement learning approach. Proc 34^th AAAI Conf on Artificial Intelligence, p.2128-2135.

[32]Markowitz H, 1952. Portfolio selection. J Finance, 7(1):77-91.

[33]Markowitz H, 1959. Portfolio Selection: Efficient Diversification of Investments. Yale University Press, New Haven, USA.

[34]Nie YQ, Nguyen NH, Sinthong P, et al., 2022. A time series is worth 64 words: long-term forecasting with transformers. 11^th Int Conf on Learning Representations.

[35]Niu H, Li SY, Li J, 2022. MetaTrader: an reinforcement learning approach integrating diverse policies for portfolio optimization. Proc 31^st ACM Int Conf on Information & Knowledge Management, p.1573-1583.

[36]Prokhorenkova L, Gusev G, Vorobev A, et al., 2018. CatBoost: unbiased boosting with categorical features. Proc 32^nd Int Conf on Neural Information Processing Systems, p.6639-6649.

[37]Qin Y, Song DJ, Chen HF, et al., 2017. A dual-stage attention-based recurrent neural network for time series prediction. Proc 26^th Int Joint Conf on Artificial Intelligence, p.2627-2633.

[38]Sawhney R, Agarwal S, Wadhwa A, et al., 2020. Spatiotemporal hypergraph convolution network for stock movement forecasting. Proc IEEE Int Conf on Data Mining, p.482-491.

[39]Sawhney R, Agarwal S, Wadhwa A, et al., 2021a. Exploring the scale-free nature of stock markets: hyperbolic graph learning for algorithmic trading. Proc Web Conf, p.11-22.

[40]Sawhney R, Agarwal S, Wadhwa A, et al., 2021b. Stock selection via spatiotemporal hypergraph attention network: a learning to rank approach. Proc 35^th AAAI Conf on Artificial Intelligence, p.497-504.

[41]Schlichtkrull M, Kipf TN, Bloem P, et al., 2018. Modeling relational data with graph convolutional networks. 15^th Int Conf on the Semantic Web, p.593-607.

[42]Sonkiya P, Bajpai V, Bansal A, 2022. Stock price prediction using artificial intelligence: a survey. IEEE 7^th Int Conf for Convergence in Technology, p.1-9.

[43]Sun S, Wang XR, Xue WQ, et al., 2023a. Mastering stock markets with efficient mixture of diversified trading experts. Proc 29^th ACM SIGKDD Conf on Knowledge Discovery and Data Mining, p.2109-2119.

[44]Sun S, Qin ML, Wang XR, et al., 2023b. PRUDEX-Compass: towards systematic evaluation of reinforcement learning in financial markets. https://arxiv.org/abs/2302.00586

[45]Sun S, Qin ML, Zhang WT, et al., 2023c. TradeMaster: a holistic quantitative trading platform empowered by reinforcement learning. Proc 37^th Int Conf on Neural Information Processing Systems, Article 2576.

[46]Tolstikhin I, Houlsby N, Kolesnikov A, et al., 2021. MLP-Mixer: an all-MLP architecture for vision. Proc 35^th Int Conf on Neural Information Processing Systems, Article 1857.

[47]Veličković P, Cucurull G, Casanova A, et al., 2018. Graph attention networks. http://arxiv.org/abs/1710.10903

[48]Wang A, Singh A, Michael J, et al., 2019. GLUE: a multi-task benchmark and analysis platform for natural language understanding. Proc 7^th Int Conf on Learning Representations.

[49]Wang HY, Li S, Wang TJ, et al., 2021. Hierarchical adaptive temporal-relational modeling for stock trend prediction. Proc 30^th Int Joint Conf on Artificial Intelligence, p.3691-3698.

[50]Wang JN, Zhang S, Xiao YH, et al., 2021. A review on graph neural network methods in financial applications.

[51]Wang JY, Zhang Y, Tang K, et al., 2019. AlphaStock: a buying-winners-and-selling-losers investment strategy using interpretable deep reinforcement attention networks. Proc 25^th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining, p.1900-1908.

[52]Wang SZ, Yuan H, Zhou L, et al., 2023. Alpha-GPT: human-AI interactive alpha mining for quantitative investment.

[53]Wang SZ, Yuan H, Ni LM, et al., 2024. QuantAgent: seeking holy grail in trading by self-improving large language model.

[54]Wang ZC, Huang BW, Tu SK, et al., 2021. DeepTrader: a deep reinforcement learning approach for risk-return balanced portfolio management with market conditions embedding. Proc 35^th AAAI Conf on Artificial Intelligence, p.643-650.

[55]Wei ZK, Dai B, Lin DH, 2023. E2EAI: end-to-end deep learning framework for active investing. Proc 4^th ACM Int Conf on AI in Finance, p.55-63.

[56]Wu HX, Xu JH, Wang JM, et al., 2022. Autoformer: decomposition Transformers with auto-correlation for long-term series forecasting. Proc 35^th Int Conf on Neural Information Processing Systems, Article 1717.

[57]Xu WT, Liu WQ, Wang LW, et al., 2021. HIST: a graph-based framework for stock trend forecasting via mining concept-oriented shared information.

[58]Yang X, Liu W, Zhou D, et al., 2020. Qlib: an AI-oriented quantitative investment platform. http://arxiv.org/abs/2009.11189

[59]Yu S, Xue HY, Ao X, et al., 2023. Generating synergistic formulaic alpha collections via reinforcement learning. Proc 29^th ACM SIGKDD Conf on Knowledge Discovery and Data Mining, p.5476-5486.

[60]Zhang LH, Aggarwal C, Qi GJ, 2017. Stock price prediction via discovering multi-frequency trading patterns. Proc 23^rd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.2141-2149.

[61]Zhang TP, Li YQ, Jin YF, et al., 2020. AutoAlpha: an efficient hierarchical evolutionary algorithm for mining alpha factors in quantitative investment.

[62]Zhang WT, Zhao LX, Xia HC, et al., 2024. A multimodal foundation agent for financial trading: tool-augmented, diversified, and generalist. Proc 30^th ACM SIGKDD Conf on Knowledge Discovery and Data Mining, p.4314-4325.

[63]Zhang YF, Zhao PL, Wu Q, et al., 2022. Cost-sensitive portfolio selection via deep reinforcement learning. IEEE Trans Knowl Data Eng, 34(1):236-248.

[64]Zhao LF, Kong SM, Shen YY, 2023. DoubleAdapt: a meta-learning approach to incremental learning for stock trend forecasting. Proc 29^th ACM SIGKDD Conf on Knowledge Discovery and Data Mining, p.3492-3503.

[65]Zhou HY, Zhang SH, Peng JQ, et al., 2021. Informer: beyond efficient Transformer for long sequence time-series forecasting. Proc 35^th AAAI Conf on Artificial Intelligence, p.11106-11115.

[66]Zhou T, Ma ZQ, Wen QS, et al., 2022. FEDformer: frequency enhanced decomposed Transformer for long-term series forecasting.

[67]Zhu YD, Chen WY, Zhang Y, et al., 2021. Probabilistic framework for modeling event shocks to financial time series. Proc 2^nd ACM Int Conf on AI in Finance, Article 42.