Please wait a minute...
Advanced Search
数据分析与知识发现  2019, Vol. 3 Issue (8): 94-104     https://doi.org/10.11925/infotech.2096-3467.2018.1137
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于RBR和CBR的金融事件本体推理研究 *
强韶华1(),罗云鹿2,李玉鹏1,吴鹏3
1南京工业大学经济与管理学院 南京 211800
2西南财经大学经济信息工程学院 成都 611130
3南京理工大学经济管理学院 南京 210094
Ontology Reasoning for Financial Affairs with RBR and CBR
Shaohua Qiang1(),Yunlu Luo2,Yupeng Li1,Peng Wu3
1School of Economics and Management, Nanjing Tech University, Nanjing 211800, China
2School of Economic Information Engineering, Southwestern University of Finance and Economics, Chengdu 611130, China
3School of Economics and Management, Nanjing University of Science &Technology, Nanjing 210094, China;
全文: PDF (1029 KB)   HTML ( 13
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】综合企业财务、非财务和舆情等因素预测金融事件对企业股价的影响, 支持基于特定行业、特定金融事件主题之间的推理。【方法】基于本体的规则推理技术和案例推理技术, 构建金融事件本体, 设计基于本体的SWRL推理规则, 采用Dloors引擎进行规则推理(RBR)。然后利用本体表示案例结构, 建立基于本体的主题事件案例库, 设计案例推理(CBR)表示、检索、重用、修正与保存模型。【结果】基于具体企业实例对规则推理和案例推理的结果进行验证, 证明了本文所提推理模型的可靠性。【局限】本文重点在于金融本体及其推理模型的构建, 股价预测是一种推理结果, 故没有和其他股价预测方法进行定量比较。【结论】融合企业的舆情、财务和非财务指标, 基于金融事件主题的案例推理和基于关联规则的规则推理模型, 可以对大数据环境下企业股价进行预测。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
强韶华
罗云鹿
李玉鹏
吴鹏
关键词 金融事件本体规则推理案例推理股价预测    
Abstract

[Objective] This paper tries to predict the impacts of financial events/news on stock price with financial, non-financial and public opinion factors. [Methods] We designed a financial affairs ontology based on the Rule-Based Reasoning (RBR) and Case-Based Reasoning (CBR). Then, we created a SWRL rule-based reasoning model, which pursued the rule-based reasoning using the Dloors engine. Thirdly, we designed a topic case database to describe the structure of the financial cases. Finally, we used the model to describe, retrieve, reuse, correct and preserve the data. [Results] We conducted an empirical study to examine the reliability of rule-based reasoning and case-based reasoning with enterprise data. [Limitations] We did not compare our model with the existing methods. [Conclusions] The proposed method could predict the stock price in big data environment.

Key wordsFinancial Affairs    Ontology    Rule-Based Reasoning    Case-Based Reasoning    Stock Price Forecast
收稿日期: 2018-10-16      出版日期: 2019-09-29
ZTFLH:  TP393 G35  
基金资助:*本文系国家自然科学基金项目“突发事件网民负面情感的模型检测研究”(71774084);国家自然科学基金项目“基于时间感知模型的学术主题检索与演化挖掘研究”的研究成果之一(71503124)
通讯作者: 强韶华     E-mail: shaohua3900@163.com
引用本文:   
强韶华,罗云鹿,李玉鹏,吴鹏. 基于RBR和CBR的金融事件本体推理研究 *[J]. 数据分析与知识发现, 2019, 3(8): 94-104.
Shaohua Qiang,Yunlu Luo,Yupeng Li,Peng Wu. Ontology Reasoning for Financial Affairs with RBR and CBR. Data Analysis and Knowledge Discovery, 2019, 3(8): 94-104.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2018.1137      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2019/V3/I8/94
  金融事件本体推理模型构建框架
评测指标 备注
所处行业
舆情 股市情绪 网民情感
财务指标 发展能力 净利润增长率
现金流水平 全部现金回收率
盈利能力 净资产收益率、成本费用利润率、营业利润率、资产报酬率
经营能力 固定资产周转率、应收账款周转率、总资产周转率、流动资产周转率
风险能力 经营杠杆、综合杠杆、财务杠杆
非财务指标 专利数量
信息披露
社会责任
子公司数
媒体和机构关注度
金融事件 政府政策
自身危机
行业创新
股价 事件发生前5天涨跌
事件发生前10天涨跌
事件发生后股价涨跌
  金融领域本体类详细结构
规则 说明
规则1 发展能力=0.074×净利润增长率
规则2 现金流水平=0.074×全部现金回收率
规则3 盈利能力=0.083×净资产收益率+0.074×成本费用利润率+0.083×营业利润率+0.078×资产报酬率
规则4 经营能力=0.088×固定资产周转率+0.078×应收账款周转率+0.088×总资产周转率+0.088×流动资产周转率
规则5 风险水平=0.069×经营杠杆+0.0698×综合杠杆+0.064×财务杠杆
规则6 财务指标=发展能力+现金流水平+盈利能力+经营能力+风险水平
规则7 非财务指标=0.17×专利数量+0.392×社会责任+0.545×媒体和分析机构关注度+0.352×信息披露+0.441×子公司数
规则8 舆情=1×正面评论数+0×中性评论数+(-1)×负面评论数
规则9 股价后续发展得分=0.65×财务指标+0.17×非财务指标+0.18×舆情
规则10 股价得分≥90 →股价极有可能上涨, 61<股价得分<89→股价可能上涨, 31<股价得分<60→股价持平, 股价得分<30→股价下跌
  规则列表
  金融领域概念层次结构
  案例推理流程
概念类 相似度
Sim (产品危机, 人事危机) 4/5
Sim (公共政策, 产品创新) 3/5
  相似度计算结果
  金融领域本体的类
  乐视企业本体实例
  金融事件本体
  Dloors推理机
  金融事件发生后股价变化
属性名称 乐视案例 贵州茅台案例 相似度 属性权重 加权相似度
所处行业 传播文化 食品饮料 0 0.05 0
金融舆情 -0.285 -0.263 0.978 0.20 0.196
财务状况 65.62 150.34 0.511 0.36 0.184
非财务状况 153.44 44.13 0.221 0.09 0.020
金融事件 经营危机、前5天股价下跌、前10天股价下跌、后5天股价下跌 产品危机、前5天股价上涨、前10天股价下跌、后5天股价下跌 0.690 0.30 0.207
相似度总和 0.607
  案例间相似度计算结果
[1] Wang S, Zhe Z, Kang Y , et al. An Ontology for Causal Relationships Between News and Financial Instruments[J]. Expert Systems with Applications, 2008,35(3):569-580.
[2] Cheng H, Lu Y C, Sheu C . An Ontology-Based Business Intelligence Application in a Financial Knowledge Management System[J]. Expert Systems with Applications, 2009,36(2):3614-3622.
[3] Shue L Y, Chen C W, Shiue W . The Development of an Ontology-Based Expert System for Corporate Financial Rating[J]. Expert Systems with Applications, 2009,36(2):2130-2142.
[4] Mellouli S, Bouslama F, Akande A . An Ontology for Representing Financial Headline News[J]. Web Semantics Science Services & Agents on the World Wide Web, 2010,8(2-3):203-208.
[5] Lupiani-Ruiz E, García-Manotas I, Valencia-García R , et al. Financial News Semantic Search Engine[J]. Expert Systems with Applications, 2011,38(12):15565-15572.
[6] Du J, Zhou L . Improving Financial Data Quality Using Ontologies[J]. Decision Support Systems, 2012,54(1):76-86.
[7] Chowdhuri R, Yoon V Y, Redmond R T , et al. Ontology Based Integration of XBRL Filings for Financial Decision Making[J]. Decision Support Systems, 2014,68:64-76.
[8] Ren R, Zhang L, Cui L , et al. Personalized Financial News Recommendation Algorithm Based on Ontology[J]. Procedia Computer Science, 2015,55:843-851.
[9] Organ J, Stapleton L . The Control of Human Factors in Catastrophic Financial Systems Risk Using Ontologies[J]. International Federation of Automatic Control, 2017,50(1):6367-6372.
[10] 韩立炜 . 基于本体的金融事件跟踪[D]. 哈尔滨: 哈尔滨工业大学, 2009.
[10] ( Han Liwei . Ontology-Based Financial Events Tracking[D]. Harbin: Harbin Institute of Technology, 2009.)
[11] 刘立博 . 基于异构信息的金融事件发现[D]. 哈尔滨: 哈尔滨工业大学, 2010.
[11] ( Liu Libo . Heterogeneous Information Based Financial Event Detection[D]. Harbin: Harbin Institute of Technology, 2010.)
[12] 李国林 . 基于语义分析的Web金融文本信息情感计算[D]. 南昌: 江西财经大学, 2012.
[12] ( Li Guolin . Sentimental Computaiton of Web Financial Text Based on Sentimental Analysis[D]. Nanchang: Jiangxi University of Finance & Economics, 2012.)
[13] 汪奕丁 . 结合文本与时序数据的金融事件发现研究[D]. 哈尔滨: 哈尔滨工业大学, 2015.
[13] ( Wang Yiding . Research on Financial Events Detection by Incorporating Text and Time-Series Data[D]. Harbin: Harbin Institute of Technology, 2015.)
[14] Kolodner J L . An Introduction to Case-Based Reasoning[J]. Artificial Intelligence Review, 1992,6(1):3-34.
[15] 谢红薇, 李建伟 . 基于本体的案例推理模型研究[J]. 计算机应用研究, 2009,26(4):1422-1424.
[15] ( Xie Hongwei, Li Jianwei . Research of Case-based Reasoning Model Based on Ontology[J]. Application Research of Computers, 2009,26(4):1422-1424.)
[16] 何岩新, 倪丽萍, 曹琳 . 基于本体的股票主题事件案例推理系统研究[J]. 计算机技术与发展, 2016,26(1):33-38.
[16] ( He Yanxin, Ni Liping, Cao Lin . Research on Case Based Reasoning System of Stock Theme Events Based on Ontology[J]. Computer Technology and Development, 2016,26(1):33-38.)
[17] Chen S, Yi J, Jiang H , et al. Ontology and CBR Based Automated Decision-Making Method for the Disassembly of Mechanical Products[J]. Advanced Engineering Informatics, 2016,30(3):564-584.
[18] Gerber A, Morar N, Meyer T , et al. Ontology-Based Support for Taxonomic Functions[J]. Ecological Informatics, 2017,41:11-23.
[19] Abadi A, Ben-Azza H, Sekkat S . Improving Integrated Product Design Using SWRL Rules Expression and Ontology-Based Reasoning[J]. Procedia Computer Science, 2018,127:416-425.
[20] Camarillo A, Ríos J, Althoff K-D . Knowledge-Based Multi-Agent System for Manufacturing Problem Solving Process in Production Plants[J]. Journal of Manufacturing Systems, 2018,47:115-127.
[21] Roldán-García M D M, Uskudarli S, Marvasti N B , et al. Towards an Ontology-Driven Clinical Experience Sharing Ecosystem: Demonstration with Liver Cases[J]. Expert Systems with Applications, 2018,101:176-195.
[22] 陈明亮, 李怀祖 . 基于规则的专家系统中不确定性推理的研究[J]. 计算机工程与应用, 2000,36(5):50-53.
[22] ( Chen Mingliang, Li Huaizu . Study on the Non-Accurate Inference in Expert System Based on Rule[J]. Computer Engineering and Applications, 2000,36(5):50-53.)
[23] Roldán-García M D M, García-Nieto J, Aldana-Montes J F . Enhancing Semantic Consistency in Anti-Fraud Rule-Based Expert Systems[J]. Expert Systems with Applications, 2017,90:332-343.
[24] Tang X, Xiao M, Hu B , et al. Exchanging Knowledge for Test-Based Diagnosis Using OWL Ontologies and SWRL Rules[J]. Procedia Computer Science, 2018,131:847-854.
[25] EI Ghosh M, Naja H, Abdulrab H , et al. Towards a Legal Rule-Based System Grounded on the Integration of Criminal Domain Ontology and Rules[J]. Procedia Computer Science, 2017,112:632-642.
[26] Zhong B, Gan C, Luo H , et al. Ontology-Based Framework for Building Environmental Monitoring and Compliance Checking Under BIM Environment[J]. Building & Environment, 2018,141:127-142.
[27] Pal K . Ontology-Based Web Service Architecture for Retail Supply Chain Management[J]. Procedia Computer Science, 2018,130:985-990.
[28] Goh Y M, Guo B H W . FPSWizard: A Web-Based CBR-RBR System for Supporting the Design of Active Fall Protection Systems[J]. Automation in Construction, 2018,85:40-50.
[29] 崔亮 . 投资者情绪的统计测评及其应用研究[D]. 成都: 西南财经大学, 2013.
[29] ( Cui Liang . A Study on Statistical Evaluation of Investor Sentiment and Its Application[D]. Chengdu: Southwest University of Finance and Economics, 2013.)
[30] 张欣 . 投资者情绪与上市公司投资行为研究[D]. 乌鲁木齐: 新疆财经大学, 2013.
[30] ( Zhang Xin . The Research on Investor Sentiment and Investment Behavior of Listed Companies[D]. Urumqi: Xinjiang University of Finance and Economics, 2013.)
[31] 沈云霞 . 基于股吧舆情的投资者情绪与股票收益研究[D]. 天津: 天津工业大学, 2016.
[31] ( Shen Yunxia . Research on the Investor Sentiment and Stock Returns Based on the Opinion of the Stock Forum[D]. Tianjin: Tianjin Polytechinic University, 2016.)
[32] Qin Y, Lu W, Qi Q , et al. Towards an Ontology-Supported Case-Based Reasoning Approach for Computer-Aided Tolerance Specification[J]. Knowledge-Based Systems, 2018,141:129-147.
[33] 焦海霞 . 基于本体的地铁施工安全风险知识库构建与应用[D]. 南京: 东南大学, 2015.
[33] ( Jiao Haixia . Modeling and Application of Ontology Based Konwledge Base Forrisks of Subway Construction[D]. Nanjing: Southeast University, 2015.)
[1] 陈星月, 倪丽萍, 倪志伟. 基于ELECTRA模型与词性特征的金融事件抽取方法研究*[J]. 数据分析与知识发现, 2021, 5(7): 36-47.
[2] 盛姝, 黄奇, 杨洋, 解绮雯, 秦新国. HL7 FHIR框架下中国医疗领域信息交换研究与解决方案[J]. 数据分析与知识发现, 2021, 5(11): 13-28.
[3] 曾桢,李纲,毛进,陈璟浩. 区域公共安全数据治理与业务领域本体研究*[J]. 数据分析与知识发现, 2020, 4(9): 41-55.
[4] 邓诗琦,洪亮. 面向智能应用的领域本体构建研究*——以反电话诈骗领域为例[J]. 数据分析与知识发现, 2019, 3(7): 73-84.
[5] 高广尚. 用户画像构建方法研究综述*[J]. 数据分析与知识发现, 2019, 3(3): 25-35.
[6] 王颖,钱力,谢靖,常志军,孔贝贝. 科技大数据知识图谱构建模型与方法研究*[J]. 数据分析与知识发现, 2019, 3(1): 15-26.
[7] 何有世, 何述芳. 基于领域本体的产品网络口碑信息多层次细粒度情感挖掘*[J]. 数据分析与知识发现, 2018, 2(8): 60-68.
[8] 唐慧慧, 王昊, 张紫玄, 王雪颖. 基于汉字标注的中文历史事件名抽取研究*[J]. 数据分析与知识发现, 2018, 2(7): 89-100.
[9] 庞贝贝, 苟娟琼, 穆文歆. 面向高校学生深度辅导领域的主题建模和主题上下位关系识别研究*[J]. 数据分析与知识发现, 2018, 2(6): 92-101.
[10] 丁晟春, 刘梦露, 傅柱. 概念设计中基于知识流的多维设计知识统一建模技术研究*[J]. 数据分析与知识发现, 2018, 2(2): 11-19.
[11] 涂海丽, 唐晓波. 基于标签的商品推荐模型研究*[J]. 数据分析与知识发现, 2017, 1(9): 28-39.
[12] 陈二静, 姜恩波. 文本相似度计算方法研究综述[J]. 数据分析与知识发现, 2017, 1(6): 1-11.
[13] 白如江, 冷伏海, 廖君华. 一种基于语义组块特征的改进Cosine文本相似度计算方法*[J]. 数据分析与知识发现, 2017, 1(6): 56-64.
[14] 吴丹, 刘畅, 李翼. 用户步行导航过程中的情感变化研究*[J]. 数据分析与知识发现, 2017, 1(5): 42-51.
[15] 刘健,毕强,刘庆旭,王福. 数字文献资源内容服务推荐研究*——基于本体规则推理和语义相似度计算[J]. 现代图书情报技术, 2016, 32(9): 70-77.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn