{"title":"RiskMiner:通过风险寻求蒙特卡洛树搜索发现公式字母表","authors":"Tao Ren, Ruihan Zhou, Jinyang Jiang, Jiafeng Liang, Qinghao Wang, Yijie Peng","doi":"arxiv-2402.07080","DOIUrl":null,"url":null,"abstract":"The formulaic alphas are mathematical formulas that transform raw stock data\ninto indicated signals. In the industry, a collection of formulaic alphas is\ncombined to enhance modeling accuracy. Existing alpha mining only employs the\nneural network agent, unable to utilize the structural information of the\nsolution space. Moreover, they didn't consider the correlation between alphas\nin the collection, which limits the synergistic performance. To address these\nproblems, we propose a novel alpha mining framework, which formulates the alpha\nmining problems as a reward-dense Markov Decision Process (MDP) and solves the\nMDP by the risk-seeking Monte Carlo Tree Search (MCTS). The MCTS-based agent\nfully exploits the structural information of discrete solution space and the\nrisk-seeking policy explicitly optimizes the best-case performance rather than\naverage outcomes. Comprehensive experiments are conducted to demonstrate the\nefficiency of our framework. Our method outperforms all state-of-the-art\nbenchmarks on two real-world stock sets under various metrics. Backtest\nexperiments show that our alphas achieve the most profitable results under a\nrealistic trading setting.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"11 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search\",\"authors\":\"Tao Ren, Ruihan Zhou, Jinyang Jiang, Jiafeng Liang, Qinghao Wang, Yijie Peng\",\"doi\":\"arxiv-2402.07080\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The formulaic alphas are mathematical formulas that transform raw stock data\\ninto indicated signals. In the industry, a collection of formulaic alphas is\\ncombined to enhance modeling accuracy. Existing alpha mining only employs the\\nneural network agent, unable to utilize the structural information of the\\nsolution space. Moreover, they didn't consider the correlation between alphas\\nin the collection, which limits the synergistic performance. To address these\\nproblems, we propose a novel alpha mining framework, which formulates the alpha\\nmining problems as a reward-dense Markov Decision Process (MDP) and solves the\\nMDP by the risk-seeking Monte Carlo Tree Search (MCTS). The MCTS-based agent\\nfully exploits the structural information of discrete solution space and the\\nrisk-seeking policy explicitly optimizes the best-case performance rather than\\naverage outcomes. Comprehensive experiments are conducted to demonstrate the\\nefficiency of our framework. Our method outperforms all state-of-the-art\\nbenchmarks on two real-world stock sets under various metrics. Backtest\\nexperiments show that our alphas achieve the most profitable results under a\\nrealistic trading setting.\",\"PeriodicalId\":501294,\"journal\":{\"name\":\"arXiv - QuantFin - Computational Finance\",\"volume\":\"11 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - Computational Finance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2402.07080\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - Computational Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2402.07080","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search
The formulaic alphas are mathematical formulas that transform raw stock data
into indicated signals. In the industry, a collection of formulaic alphas is
combined to enhance modeling accuracy. Existing alpha mining only employs the
neural network agent, unable to utilize the structural information of the
solution space. Moreover, they didn't consider the correlation between alphas
in the collection, which limits the synergistic performance. To address these
problems, we propose a novel alpha mining framework, which formulates the alpha
mining problems as a reward-dense Markov Decision Process (MDP) and solves the
MDP by the risk-seeking Monte Carlo Tree Search (MCTS). The MCTS-based agent
fully exploits the structural information of discrete solution space and the
risk-seeking policy explicitly optimizes the best-case performance rather than
average outcomes. Comprehensive experiments are conducted to demonstrate the
efficiency of our framework. Our method outperforms all state-of-the-art
benchmarks on two real-world stock sets under various metrics. Backtest
experiments show that our alphas achieve the most profitable results under a
realistic trading setting.