WO2021082811A1 - Procédé de prédiction de séries chronologiques d'opérations de change - Google Patents
Procédé de prédiction de séries chronologiques d'opérations de change Download PDFInfo
- Publication number
- WO2021082811A1 WO2021082811A1 PCT/CN2020/116955 CN2020116955W WO2021082811A1 WO 2021082811 A1 WO2021082811 A1 WO 2021082811A1 CN 2020116955 W CN2020116955 W CN 2020116955W WO 2021082811 A1 WO2021082811 A1 WO 2021082811A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- network
- training
- short
- neural network
- foreign exchange
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Definitions
- Dash Rajashree proposed an evolutionary framework that uses an improved hybrid leapfrog algorithm and artificial neural network to predict foreign exchange time series data. And compared with the hybrid leapfrog algorithm and particle swarm optimization algorithm, the experiment shows that the model proposed in the article is more suitable for foreign exchange time series analysis.
- the long and short-term memory network is performed separately, and the output of the two algorithms is combined to make the final prediction.
- Figure 14 is a graph showing the change trend of training speed with the increase in the number of GPUs
- Figure 19 is a fitting diagram of the prediction effect of the LSTM prediction method
- RSV N (Close (N) -Low (N) ) ⁇ (High (N) -Low (N) ) ⁇ 100% (8)
- the number of lag periods n refers to the length of the analysis and prediction time series, that is, the n+1 day is predicted using the data of the previous n days.
- the difference in the number of lag periods may have an important impact on forecast accuracy.
- choose 5, 10, 20, 30, 40, 50, 60 different lag periods study the influence of the lag period n on the prediction accuracy, and select the best lag period n.
- the detailed laboratory data is shown in Table 3, and the data in Table 3 is visualized to get Figure 6.
- the convolution kernel is 1 ⁇ 1
- the convolution kernel is larger than 3 ⁇ 3
- the spatial features around the data are collected too much .
- the prediction accuracy shows that the location far away from the data has less correlation with the current data.
- the number of convolutional layers is 2 and the convolution sum size is 3 ⁇ 3, the spatial characteristics of the data are better abstracted. Therefore, the number of convolutional layers is set to 2, and the size of the convolution kernel is set. It is 3 ⁇ 3.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Technology Law (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Procédé de prédiction de séries chronologiques d'opérations de change, se rapportant au domaine des données de séries chronologiques d'opérations de change. Selon le procédé de prédiction, des données de séries chronologiques d'opérations de change sont analysées et prédites sur la base d'un algorithme d'apprentissage profond C-LSTM, qui combine un réseau neuronal convolutionnel avec un long réseau à mémoire à court-terme, et un procédé de prédiction à court terme pour une série chronologique d'opérations de change. Trois types de facteurs principaux affectant la précision de prédiction sont systématiquement étudiés. La caractéristique d'entrée optimale, la structure de réseau et le procédé de formation sont sélectionnés. En ce qui concerne le problème du bruit de mégadonnées, un algorithme d'optimisation de caractéristiques est construit sur la base d'un PCA pour effectuer une réduction de dimension et un débruitage sur des caractéristiques d'entrée, et des procédés de perte et régularisation L2 sont ensuite utilisés pour éviter le problème de surapprentissage, ce qui permet d'améliorer davantage la précision de prédiction du procédé de prédiction. En même temps, afin de répondre à l'exigence d'un marché d'opérations de change pour une efficacité élevée dans le temps, un algorithme d'optimisation parallèle est construit sur la base d'une technologie de calcul GPU haute-performance, ce qui permet d'augmenter la vitesse de formation d'un modèle de réseau et d'améliorer la disponibilité du procédé de prédiction dans des scénarios d'application réels.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911035230.0 | 2019-10-29 | ||
CN201911035230.0A CN110782096A (zh) | 2019-10-29 | 2019-10-29 | 一种外汇时间序列预测方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021082811A1 true WO2021082811A1 (fr) | 2021-05-06 |
Family
ID=69387210
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/116955 WO2021082811A1 (fr) | 2019-10-29 | 2020-09-23 | Procédé de prédiction de séries chronologiques d'opérations de change |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110782096A (fr) |
WO (1) | WO2021082811A1 (fr) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113554873A (zh) * | 2021-07-20 | 2021-10-26 | 重庆大学 | 一种基于高阶矩的行程时间波动性预测方法及装置 |
CN113569473A (zh) * | 2021-07-19 | 2021-10-29 | 浙江大学 | 基于多项式特征lstm粒度计算的空分管网氧气长期预测方法 |
CN113642225A (zh) * | 2021-05-24 | 2021-11-12 | 国网新疆电力有限公司经济技术研究院 | 一种基于attention机制的CNN-LSTM短期风电功率预测方法 |
CN113724780A (zh) * | 2021-09-16 | 2021-11-30 | 上海交通大学 | 基于深度学习的蛋白质卷曲螺旋结构特征预测实现方法 |
CN113920408A (zh) * | 2021-09-10 | 2022-01-11 | 天津理工大学 | 一种基于cnn-rnn并行融合的光子晶体透射光谱序列特征提取方法 |
CN114205138A (zh) * | 2021-12-09 | 2022-03-18 | 麒麟软件有限公司 | 针对容器云平台的网络入侵检测方法 |
CN114387030A (zh) * | 2022-01-13 | 2022-04-22 | 瑞祥全球购超市有限公司 | 一种面向网络购物平台的在线用户量的智能分析方法 |
CN114913296A (zh) * | 2022-05-07 | 2022-08-16 | 中国石油大学(华东) | 一种modis地表温度数据产品重建方法 |
CN115018553A (zh) * | 2022-06-30 | 2022-09-06 | 东南大学 | 基于深度学习的区域物流单量预测系统及方法 |
CN115456073A (zh) * | 2022-09-14 | 2022-12-09 | 杭州电子科技大学 | 基于长短期记忆的生成式对抗网络模型建模分析方法 |
WO2023169589A1 (fr) * | 2022-03-07 | 2023-09-14 | 东南大学 | Procédé de modélisation de canal prédictif basé sur un réseau antagoniste et un réseau de mémoire à court et long terme |
CN116805514A (zh) * | 2023-08-25 | 2023-09-26 | 鲁东大学 | 一种基于深度学习的dna序列功能预测方法 |
CN117349774A (zh) * | 2023-10-24 | 2024-01-05 | 重庆邮电大学 | 一种基于大数据的区块链异常交易检测方法 |
CN117635179A (zh) * | 2023-07-25 | 2024-03-01 | 北京壹清能环科技有限公司 | 一种碳交易价格预测方法、装置及存储介质 |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110751562A (zh) * | 2019-10-29 | 2020-02-04 | 山东科技大学 | 一种外汇时间序列预测的训练优化方法 |
CN110782096A (zh) * | 2019-10-29 | 2020-02-11 | 山东科技大学 | 一种外汇时间序列预测方法 |
CN110796306A (zh) * | 2019-10-29 | 2020-02-14 | 山东科技大学 | 一种外汇时间序列预测的构建方法 |
CN111415050B (zh) * | 2020-04-27 | 2023-12-05 | 新奥新智科技有限公司 | 短期负荷预测方法、短期负荷预测模型训练方法及装置 |
CN111639823B (zh) * | 2020-06-10 | 2022-09-23 | 天津大学 | 一种基于特征集构建的建筑冷热负荷预测方法 |
CN112116381B (zh) * | 2020-08-31 | 2021-05-07 | 北京基调网络股份有限公司 | 基于lstm神经网络的月活预测方法、存储介质和计算机设备 |
CN112598526A (zh) * | 2021-03-04 | 2021-04-02 | 蚂蚁智信(杭州)信息技术有限公司 | 资产数据的处理方法及装置 |
CN116777506A (zh) * | 2023-05-16 | 2023-09-19 | 济南明泉数字商务有限公司 | 一种基于生成式ai服务的大宗品交易决策方法及系统 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106886846A (zh) * | 2017-04-26 | 2017-06-23 | 中南大学 | 一种基于长短期记忆循环神经网络的银行网点备付金预测方法 |
CN108305167A (zh) * | 2018-01-12 | 2018-07-20 | 华南理工大学 | 一种基于深度增强学习算法的外汇交易方法及系统 |
CN108694480A (zh) * | 2018-07-13 | 2018-10-23 | 西南石油大学 | 基于改进的长短时记忆网络的金融数据预测方法 |
AU2018101512A4 (en) * | 2018-10-11 | 2018-11-15 | Dong, Xun Miss | A comprehensive stock trend predicting method based on neural networks |
CN109360097A (zh) * | 2018-09-28 | 2019-02-19 | 中山大学 | 基于深度学习的股票预测方法、装置、设备及存储介质 |
CN109711461A (zh) * | 2018-12-25 | 2019-05-03 | 中国人民解放军战略支援部队航天工程大学 | 基于主成分分析的迁移学习图片分类方法及其装置 |
CN110782096A (zh) * | 2019-10-29 | 2020-02-11 | 山东科技大学 | 一种外汇时间序列预测方法 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10783900B2 (en) * | 2014-10-03 | 2020-09-22 | Google Llc | Convolutional, long short-term memory, fully connected deep neural networks |
CN105787582A (zh) * | 2015-12-24 | 2016-07-20 | 清华大学 | 股票风险预测方法和装置 |
KR102008845B1 (ko) * | 2017-11-30 | 2019-10-21 | 굿모니터링 주식회사 | 비정형 데이터의 카테고리 자동분류 방법 |
CN107832897A (zh) * | 2017-11-30 | 2018-03-23 | 浙江工业大学 | 一种基于深度学习的股票市场预测方法 |
CN109190834A (zh) * | 2018-09-12 | 2019-01-11 | 百色学院 | 基于神经网络的股票价格趋势预测方法及系统 |
CN109816140A (zh) * | 2018-12-12 | 2019-05-28 | 哈尔滨工业大学(深圳) | 基于跨市场影响的股价预测方法、装置、设备及存储介质 |
-
2019
- 2019-10-29 CN CN201911035230.0A patent/CN110782096A/zh active Pending
-
2020
- 2020-09-23 WO PCT/CN2020/116955 patent/WO2021082811A1/fr active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106886846A (zh) * | 2017-04-26 | 2017-06-23 | 中南大学 | 一种基于长短期记忆循环神经网络的银行网点备付金预测方法 |
CN108305167A (zh) * | 2018-01-12 | 2018-07-20 | 华南理工大学 | 一种基于深度增强学习算法的外汇交易方法及系统 |
CN108694480A (zh) * | 2018-07-13 | 2018-10-23 | 西南石油大学 | 基于改进的长短时记忆网络的金融数据预测方法 |
CN109360097A (zh) * | 2018-09-28 | 2019-02-19 | 中山大学 | 基于深度学习的股票预测方法、装置、设备及存储介质 |
AU2018101512A4 (en) * | 2018-10-11 | 2018-11-15 | Dong, Xun Miss | A comprehensive stock trend predicting method based on neural networks |
CN109711461A (zh) * | 2018-12-25 | 2019-05-03 | 中国人民解放军战略支援部队航天工程大学 | 基于主成分分析的迁移学习图片分类方法及其装置 |
CN110782096A (zh) * | 2019-10-29 | 2020-02-11 | 山东科技大学 | 一种外汇时间序列预测方法 |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113642225A (zh) * | 2021-05-24 | 2021-11-12 | 国网新疆电力有限公司经济技术研究院 | 一种基于attention机制的CNN-LSTM短期风电功率预测方法 |
CN113569473A (zh) * | 2021-07-19 | 2021-10-29 | 浙江大学 | 基于多项式特征lstm粒度计算的空分管网氧气长期预测方法 |
CN113554873A (zh) * | 2021-07-20 | 2021-10-26 | 重庆大学 | 一种基于高阶矩的行程时间波动性预测方法及装置 |
CN113920408A (zh) * | 2021-09-10 | 2022-01-11 | 天津理工大学 | 一种基于cnn-rnn并行融合的光子晶体透射光谱序列特征提取方法 |
CN113724780A (zh) * | 2021-09-16 | 2021-11-30 | 上海交通大学 | 基于深度学习的蛋白质卷曲螺旋结构特征预测实现方法 |
CN113724780B (zh) * | 2021-09-16 | 2023-10-13 | 上海交通大学 | 基于深度学习的蛋白质卷曲螺旋结构特征预测实现方法 |
CN114205138A (zh) * | 2021-12-09 | 2022-03-18 | 麒麟软件有限公司 | 针对容器云平台的网络入侵检测方法 |
CN114387030A (zh) * | 2022-01-13 | 2022-04-22 | 瑞祥全球购超市有限公司 | 一种面向网络购物平台的在线用户量的智能分析方法 |
CN114387030B (zh) * | 2022-01-13 | 2024-03-15 | 瑞祥全球购超市有限公司 | 一种面向网络购物平台的在线用户量的智能分析方法 |
WO2023169589A1 (fr) * | 2022-03-07 | 2023-09-14 | 东南大学 | Procédé de modélisation de canal prédictif basé sur un réseau antagoniste et un réseau de mémoire à court et long terme |
CN114913296A (zh) * | 2022-05-07 | 2022-08-16 | 中国石油大学(华东) | 一种modis地表温度数据产品重建方法 |
CN114913296B (zh) * | 2022-05-07 | 2023-08-11 | 中国石油大学(华东) | 一种modis地表温度数据产品重建方法 |
CN115018553A (zh) * | 2022-06-30 | 2022-09-06 | 东南大学 | 基于深度学习的区域物流单量预测系统及方法 |
CN115018553B (zh) * | 2022-06-30 | 2024-05-07 | 东南大学 | 基于深度学习的区域物流单量预测系统及方法 |
CN115456073B (zh) * | 2022-09-14 | 2023-07-07 | 杭州电子科技大学 | 基于长短期记忆的生成式对抗网络模型建模分析方法 |
CN115456073A (zh) * | 2022-09-14 | 2022-12-09 | 杭州电子科技大学 | 基于长短期记忆的生成式对抗网络模型建模分析方法 |
CN117635179A (zh) * | 2023-07-25 | 2024-03-01 | 北京壹清能环科技有限公司 | 一种碳交易价格预测方法、装置及存储介质 |
CN116805514B (zh) * | 2023-08-25 | 2023-11-21 | 鲁东大学 | 一种基于深度学习的dna序列功能预测方法 |
CN116805514A (zh) * | 2023-08-25 | 2023-09-26 | 鲁东大学 | 一种基于深度学习的dna序列功能预测方法 |
CN117349774A (zh) * | 2023-10-24 | 2024-01-05 | 重庆邮电大学 | 一种基于大数据的区块链异常交易检测方法 |
Also Published As
Publication number | Publication date |
---|---|
CN110782096A (zh) | 2020-02-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021082809A1 (fr) | Procédé d'optimisation d'entraînement pour prédiction chronologique d'opération de change | |
WO2021082811A1 (fr) | Procédé de prédiction de séries chronologiques d'opérations de change | |
WO2021082810A1 (fr) | Procédé de construction pour prédiction de séries chronologiques d'opérations de change | |
Li et al. | Risk prediction in financial management of listed companies based on optimized BP neural network under digital economy | |
Vochozka et al. | Predicting future Brent oil price on global markets. | |
Wu et al. | Portfolio management system in equity market neutral using reinforcement learning | |
Sermpinis et al. | Neural networks in financial trading | |
Li et al. | Heterogeneous ensemble learning with feature engineering for default prediction in peer-to-peer lending in China | |
Ruyu et al. | A comparison of credit rating classification models based on spark-evidence from lending-club | |
Li et al. | Prediction on blockchain virtual currency transaction under long short-term memory model and deep belief network | |
Syu et al. | Portfolio management system with reinforcement learning | |
Liang et al. | The analysis of global RMB exchange rate forecasting and risk early warning using ARIMA and CNN model | |
Bebeshko et al. | Analysis and modeling of price changes on the exchange market based on structural market data | |
Sakhare et al. | Retracted: Prediction of stock market movement via technical analysis of stock data stored on blockchain using novel History Bits based machine learning algorithm | |
Behura et al. | Stock Price Prediction using Multi-Layered Sequential LSTM | |
Pandey et al. | A review and empirical analysis of neural networks based exchange rate prediction | |
Ma et al. | Research on stock trading strategy based on deep neural network | |
Samarawickrama et al. | Multi-step-ahead prediction of exchange rates using artificial neural networks: a study on selected sri lankan foreign exchange rates | |
Liashenko et al. | Neural Networks in Application to Cryptocurrency Exchange Modeling. | |
Buczynski et al. | GARCHNet: Value-at-Risk Forecasting with GARCH Models Based on Neural Networks | |
Friday et al. | IRGM: An Integrated RNN-GRU Model for Stock Market Price Prediction | |
Goyal | Financial Time Series Stock Price Prediction using Deep Learning | |
Kochliaridis et al. | UNSURE-A machine learning approach to cryptocurrency trading | |
Liu et al. | A new LASSO-BiLSTM-based ensemble learning approach for exchange rate forecasting | |
Zankova | High frequency financial time series prediction: machine learning approach |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20882690 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20882690 Country of ref document: EP Kind code of ref document: A1 |