Towards interpretable stock trend prediction through causal inference

被引：0

作者：

Department of Computer Science, The University of Hong Kong, Pokfulam Road, Hong Kong ^{[1
]}

不详 ^{[2
]}

机构：

来源：

Expert Sys Appl | 2024年

关键词：

With the emergence of artificial intelligence; deep learning techniques have been widely deployed in forecasting stock markets. However; existing deep-learning-based models for news-based forecasts of stock trends are mostly black-box and difficult to explain. The procedure by which how final predictions are made within models keeps unknown; making it hard to interpret why one prediction should be better than the other. To provide explanations on predictions; this paper proposes to inject causal inference into model procedures and causally interpret predictions. We first generate a causal graph from financial news; and then integrate the information in the causal graph into a neural network model for stock trend prediction. Moreover; in order to better extract keywords from financial news we introduce a novel keyword extraction method named Distinguishable Word Filtering by Kolmogorov–Smirnov Test (DWF-KST). The experiment results on five financial datasets demonstrate that not only our proposed model explicitly provides an interpretation of prediction results; but also outperforms the state-of-art methods. the achieved results boost predictions of S&P 500 2-category from 89.7% to 97.4%; 3-category from 77.4% to 82.5%; and 5-category from 61.5% to 71.6%. For the other two indexes; the performances of Dow index improve from 86.2% to 90.2% and Nasdaq index improve from 76.4% to 78.9%. © 2023 Elsevier Ltd;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

引用

共 50 条

[41] Causal Inference through a Witness Protection Program
Silva, Ricardo
Evans, Robin
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 2014, 27
[42] MATHEMATICAL COUPLING AND CAUSAL INFERENCE THROUGH EXAMPLE
Berrie, L.
Tennant, P. W. G.
Norman, P. D.
Baxter, P. D.
Gilthorpe, M. S.
JOURNAL OF EPIDEMIOLOGY AND COMMUNITY HEALTH, 2018, 72 : A66 - A66
[43] Causal Inference through a Witness Protection Program
Silva, Ricardo
Evans, Robin
JOURNAL OF MACHINE LEARNING RESEARCH, 2016, 17
[44] Prediction meets causal inference: the role of treatment in clinical prediction models
van Geloven, Nan
Swanson, Sonja A.
Ramspek, Chava L.
Luijken, Kim
van Diepen, Merel
Morris, Tim P.
Groenwold, Rolf H. H.
van Houwelingen, Hans C.
Putter, Hein
le Cessie, Saskia
EUROPEAN JOURNAL OF EPIDEMIOLOGY, 2020, 35 (07) : 619 - 630
[45] Prediction meets causal inference: the role of treatment in clinical prediction models
Nan van Geloven
Sonja A. Swanson
Chava L. Ramspek
Kim Luijken
Merel van Diepen
Tim P. Morris
Rolf H. H. Groenwold
Hans C. van Houwelingen
Hein Putter
Saskia le Cessie
European Journal of Epidemiology, 2020, 35 : 619 - 630
[46] iTrendRNN: An Interpretable Trend-Aware RNN for Meteorological Spatiotemporal Prediction
Huang, Xu
Luo, Chuyao
Zhang, Bowen
Lin, Huiwei
Li, Xutao
Ye, Yunming
THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 20, 2024, : 22132 - 22140
[47] Stock trend prediction method coupled with multilevel indicators
Liu, Yu
Pan, Yuting
Liu, Xiaoxing
Journal of Southeast University (English Edition), 2024, 40 (04) : 425 - 431
[48] Prediction and causal inference of hyperuricemia using gut microbiota
Miyajima, Yuna
Karashima, Shigehiro
Mizoguchi, Ren
Kawakami, Masaki
Ogura, Kohei
Ogai, Kazuhiro
Koshida, Aoi
Ikagawa, Yasuo
Ami, Yuta
Zhu, Qiunan
Tsujiguchi, Hiromasa
Hara, Akinori
Kurihara, Shin
Arakawa, Hiroshi
Nakamura, Hiroyuki
Tamai, Ikumi
Nambo, Hidetaka
Okamoto, Shigefumi
SCIENTIFIC REPORTS, 2024, 14 (01):
[49] Causal Effect Prediction with Flow-based Inference
Ren, Shaogang
Li, Dingcheng
Li, Ping
2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2022, : 1167 - 1172
[50] Optimised Prediction Model For Stock Market Trend Analysis
Soni, Devpriya
Agarwal, Sparsh
Agarwal, Tushar
Arora, Pooshan
Gupta, Kopal
2018 ELEVENTH INTERNATIONAL CONFERENCE ON CONTEMPORARY COMPUTING (IC3), 2018, : 368 - 370

← 1 2 3 4 5 →