From Uniform Models To Generic Representations: Stock Return Prediction With Pre-training

被引:0
|
作者
You, Jiawei [1 ]
Han, Tianyuan [1 ]
Shen, Liping [1 ]
机构
[1] Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai, Peoples R China
关键词
representation learning; stock return prediction; triplet loss;
D O I
10.1109/IJCNN55064.2022.9892697
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The emergence of deep learning has cast new light on the century-old problem of stock return prediction. For single stock return prediction, incorporating peripheral data such as cross sectional information has become the de facto standard for target horizons denoted in hours and above. However, such approach is not directly applicable to predicting short-term stock returns due to their strong stochastic nature. Little has been reported in public domain on how to utilize the rich exogenous data in short-term scenarios effectively. We propose a representation learning solution based on a pretrain-finetune framework. To help models learn high-quality feature extractors, we further propose to use triplet loss as a novel pre-train task. We present a new sample selection criterion and three versions of triplet selection in this context: "easy sample", "multiple samples", and "hard sample". Experiment results using the proposed method demonstrate significant improvement over standard approaches. We also share some insight on how to apply triplet loss effectively in the context of short-term stock return prediction. Specifically, we demonstrate that using regression labels to select triplets is more effective than using embedding similarity. The proposed training framework is model-agnostic and shows great performance improvements in various settings.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Pre-training Mention Representations in Coreference Models
    Varkel, Yuval
    Globerson, Amir
    [J]. PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 8534 - 8540
  • [2] Advances in Pre-Training Distributed Word Representations
    Mikolov, Tomas
    Grave, Edouard
    Bojanowski, Piotr
    Puhrsch, Christian
    Joulin, Armand
    [J]. PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018), 2018, : 52 - 55
  • [3] Multi-stage Pre-training over Simplified Multimodal Pre-training Models
    Liu, Tongtong
    Feng, Fangxiang
    Wang, Xiaojie
    [J]. 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 (ACL-IJCNLP 2021), 2021, : 2556 - 2565
  • [4] Ontology Pre-training for Poison Prediction
    Glauer, Martin
    Neuhaus, Fabian
    Mossakowski, Till
    Hastings, Janna
    [J]. ADVANCES IN ARTIFICIAL INTELLIGENCE, KI 2023, 2023, 14236 : 31 - 45
  • [5] Realistic Channel Models Pre-training
    Huangfu, Yourui
    Wang, Jian
    Xu, Chen
    Li, Rong
    Ge, Yiqun
    Wang, Xianbin
    Zhang, Huazi
    Wang, Jun
    [J]. 2019 IEEE GLOBECOM WORKSHOPS (GC WKSHPS), 2019,
  • [6] Pre-Training Audio Representations With Self-Supervision
    Tagliasacchi, Marco
    Gfeller, Beat
    Quitry, Felix de Chaumont
    Roblek, Dominik
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2020, 27 : 600 - 604
  • [7] Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
    Xing, Yue
    Lin, Xiaofeng
    Song, Qifan
    Xu, Yi
    Zeng, Belinda
    Cheng, Guang
    [J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
  • [8] GBERT: Pre-training User representations for Ephemeral Group Recommendation
    Zhang, Song
    Zheng, Nan
    Wang, Danli
    [J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, : 2631 - 2639
  • [9] Contrastive Representations Pre-Training for Enhanced Discharge Summary BERT
    Won, DaeYeon
    Lee, YoungJun
    Choi, Ho-Jin
    Jung, YuChae
    [J]. 2021 IEEE 9TH INTERNATIONAL CONFERENCE ON HEALTHCARE INFORMATICS (ICHI 2021), 2021, : 507 - 508
  • [10] Stock return prediction: Stacking a variety of models
    Zhao, Albert Bo
    Cheng, Tingting
    [J]. JOURNAL OF EMPIRICAL FINANCE, 2022, 67 : 288 - 317