| 336 | 0 | 107 |
| 下载次数 | 被引频次 | 阅读次数 |
本文介绍算法交易中的一个重要指标——成交量加权平均价格(volume-weighted average price, VWAP). VWAP是一种广泛应用于日内交易的基准价格，不仅为交易者提供了一个衡量执行价格是否优于市场平均水平的标准，还在优化交易策略、减少市场冲击和管理风险等方面发挥着至关重要的作用.首先介绍了VWAP的一些数学建模方法，然后提出利用强化学习等算法来优化VWAP策略，并展示了在模拟市场环境中的实验结果.
Abstract：This paper introduces an important indicator in algorithmic trading——the volume-weighted average price(VWAP). VWAP is a benchmark price widely used in intraday trading, providing traders with a standard to measure whether the execution price is better than the market average level. It also plays a crucial role in optimizing trading strategies, reducing market impact, and managing risks. The paper first introduces some mathematical modeling methods for VWAP, then proposes using reinforcement learning algorithms to optimize VWAP strategies, and demonstrates experimental results in simulated market environments.
[1]Cartea á,Jaimungal S,Penalva J.Algorithmic and high-frequency trading[M].Cambridge:Cambridge University Press,2015.
[2]Berkowitz S A,Logue D E,Noser Jr E A.The total cost of transactions on the NYSE[J].The Journal of Finance,1988,43:97-112.
[3]Cartea á,Jaimungal S.A closed-form execution strategy to target volume weighted average price[J].SIAM Journal on Financial Mathematics,2016,7(1):760-785.
[4]McCulloch J,Kazakov V.Mean variance optimal VWAP trading[EB/OL].[2024-12-20].https://ssrn.com/abstract=1803858.
[5]Mitchell D,Bialkowski J P,Tompaidis S.Optimal VWAP tracking[EB/OL].[2024-12-20].https://ssrn.com/abstract=2333916.
[6]Frei C,Westray N.Optimal execution of a VWAP order:a stochastic control approach[J].Mathematical Finance,2015,25(3):612-639.
[7]Guéant O,Royer G.VWAP execution and guaranteed VWAP[J].SIAM Journal on Financial Mathematics,2014,5(1):445-471.
[8]Bia?kowski J,Darolles S,Le Fol G.Improving VWAP strategies:a dynamic volume approach[J].Journal of Banking & Finance,2008,32:1709-1722.
[9]Darolles S,Le Fol G.Trading volume and arbitrage[J].GSTF:Journal on Business Review,2014,3(3):29-40.
[10]Humphery-Jenner M L.Optimal VWAP trading under noisy conditions[J].Journal of Banking & Finance,2011,35(9):2319-2329.
[11]Alvim L G M,Dos Santos C N,Milidiu R L.Daily volume forecasting using high frequency predictors[C]//Proceedings of the 10th IASTED International Conference,2010,674(47):248.
[12]Boser B E,Guyon I M,Vapnik V N.A training algorithm for optimal margin classifiers[C]// Proceedings of the fifth Annual Workshop on Computational Learning Theory,1992:144-152.
[13]Bennett K P,Mangasarian O L.Robust linear programming discrimination of two linearly inseparable sets[J].Optimization Methods and Software,1992,1(1):23-34.
[14]Liu X,Lai K K.Intraday volume percentages forecasting using a dynamic SVM-based approach[J].Journal of Systems Science and Complexity,2017,30:421-433.
[15]Tsoukalas L H,Uhrig R E.Fuzzy and neural approaches in engineering[M].New York:John Wiley & Sons,Inc.,1996.
[16]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[17]Papanicolaou A,Fu H,Krishnamurthy P,et al.An optimal control strategy for execution of large stock orders using LSTMs[EB/OL].arXiv preprint,2023.arXiv:2301.09705.
[18]Lu M,Xu X.TRNN:an efficient time-series recurrent neural network for stock price prediction[J].Information Sciences,2024,657:119951.
[19]Lee H,Park H.IVE:enhanced probabilistic forecasting of intraday volume ratio with transformers[EB/OL].arXiv preprint,2024.arXiv:2411.10956.
[20]Tang B,Matteson D S.Probabilistic transformer for time series analysis[J].Advances in Neural Information Processing Systems,2021,34:23592-23608.
[21]Ye J,Li X,Wang Y.A multi-agent deep reinforcement learning framework for VWAP strategy optimization[C]//2022 International Joint Conference on Neural Networks (IJCNN),2022:1-8.
[22]Li X,Wu P,Zou C,et al.Hierarchical deep reinforcement learning for VWAP strategy optimization[J].IEEE Transactions on Big Data,2024,10(3):288-300.
[23]Kim S,Kim J,Sul H K,et al.An adaptive dual-level reinforcement learning approach for optimal trade execution[J].Expert Systems with Applications,2024:252.
[24]Jia Y,Zhou X Y.Policy evaluation and temporal-difference learning in continuous time and space:a martingale approach[J].Journal of Machine Learning Research,2022,23(154):1-55.
[25]Jia Y,Zhou X Y.Policy gradient and actor-critic learning in continuous time and space:theory and algorithms[J].Journal of Machine Learning Research,2022,23(275):1-50.
基本信息:
DOI：10.19943/j.2095-3070.jmmia.2025.01.01
中图分类号:TP181;F830.9
引用信息:
[1]周星雨,许明宇,王伟等.算法交易之成交量加权平均价格[J].数学建模及其应用,2025,14(01):1-14.DOI:10.19943/j.2095-3070.jmmia.2025.01.01.
基金信息: