Non-stationary financial time series forecasting based on meta-learning

被引：2

作者：

Hong, Anqi ^{[1
]}

Gao, Minghan ^{[2
]}

Gao, Qiang ^{[1
]}

Peng, Xiao-Hong ^{[3
]}

机构：

[1] Beihang Univ, Sch Elect & Informat Engn, Beijing, Peoples R China

[2] Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing, Peoples R China

[3] Birmingham City Univ, Fac Comp Engn & Built Environm, Birmingham, England

来源：

ELECTRONICS LETTERS | 2023年 / 59卷 / 01期

关键词：

convolutional neural nets; economic forecasting; learning (artificial intelligence); neural nets; time series;

D O I：

10.1049/ell2.12681

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this letter, the authors address the challenge in forecasting non-stationary financial time series by proposing a meta-learning based forecasting model equipped with a convolution neural network (CNN) predictor and a long short-term memory (LSTM) meta-learner. The model is applied to a set of short subseries which are the result of dividing a long non-stationary financial time series. As a result, a promising performance can be achieved by the proposed model in terms of making more accurate prediction than the traditional CNN predictor and auto regressive (AR)-based forecasting models in non-stationary conditions.

引用

页数：3

共 50 条

[41] On the interaction between forecasting and stock control: The case of non-stationary demand [J].

Strijbosch, Leo W. G. ;

Syntetos, Aris A. ;

Boylan, John E. ;

Janssen, Elleke .

INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS, 2011, 133 (01) :470-480

[42] Measuring correlations between non-stationary series with DCCA coefficient [J].

Kristoufek, Ladislav .

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2014, 402 :291-298

[43] Causal Discovery for Non-stationary Non-linear Time-series Data Using Just-In-Time Modeling [J].

Fujiwara, Daigo ;

Koyama, Kazuki ;

Kiritoshi, Keisuke ;

Okawachi, Tomomi ;

Izumitani, Tomonori ;

Shimizu, Shohei .

CONFERENCE ON CAUSAL LEARNING AND REASONING, VOL 213, 2023, 213 :880-894

[44] The Parzen Kernel Approach to Learning in Non-stationary Environment [J].

Pietruczuk, Lena ;

Rutkowski, Leszek ;

Jaworski, Maciej ;

Duda, Piotr .

PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, :3319-3323

[45] Self CNN-based time series stream forecasting [J].

Zeng, Zhiping ;

Xiao, Haidong ;

Zhang, Xinpeng .

ELECTRONICS LETTERS, 2016, 52 (22) :1857-+

[46] Instance-based meta-learning for conditionally dependent univariate multi-step forecasting☆ [J].

Cerqueira, Vitor ;

Torgo, Luis ;

Bontempi, Gianluca .

INTERNATIONAL JOURNAL OF FORECASTING, 2024, 40 (04) :1507-1520

[47] Evaluation of Error Metrics for Meta-learning Label Definition in the Forecasting Task [J].

Santos, Moises R. ;

Mundim, Leandro R. ;

Carvalho, Andre C. P. L. F. .

HYBRID ARTIFICIAL INTELLIGENT SYSTEMS, HAIS 2020, 2020, 12344 :397-409

[48] An integrated simulation-based fuzzy regression-time series algorithm for electricity consumption estimation with non-stationary data [J].

Azadeh, Ali ;

Saberi, Morteza ;

Gitiforouz, Anahita .

JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS, 2011, 34 (08) :1047-1066

[49] A Method of Preliminary Forecasting of Time Series of Financial Data [J].

A. D. Shatashvili ;

I. Sh. Didmanidze ;

G. A. Kakhiani ;

T. A. Fomina .

Cybernetics and Systems Analysis, 2020, 56 :296-302

[50] Financial Time Series Forecasting Enriched with Textual Information [J].

Steve Ataucuri Cruz, Lord Flaubert ;

Silva, Diego Furtado .

20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2021), 2021, :385-390

← 1 2 3 4 5 →