Enhancing Stock Movement Prediction with Adversarial Training

Authors: Fuli Feng, Huimin Chen, Xiangnan He, Ji Ding, Maosong Sun, Tat-Seng Chua

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution [Xu and Cohen, 2018] with 3.11% relative improvements on average w.r.t. accuracy, validating the usefulness of adversarial training for stock prediction task.
Researcher Affiliation Academia Fuli Feng1 , Huimin Chen2 , Xiangnan He3 , Ji Ding4 , Maosong Sun2 and Tat-Seng Chua1 1National University of Singapore 2Tsinghua Unversity 3University of Science and Technology of China 4University of Illinois at Urbana-Champaign
Pseudocode No The paper describes the model architecture and training process in detail and provides figures illustrating the model components (Figure 2, 3), but it does not contain any formal pseudocode blocks or algorithms labeled as such.
Open Source Code Yes Code could be accessed through https://github.com/hennande/Adv-ALSTM.
Open Datasets Yes We evaluate the proposed method on two benchmarks on stock movement prediction, ACL18 [Xu and Cohen, 2018] and KDD17 [Zhang et al., 2017].
Dataset Splits Yes We temporally split the identified examples into training (Jan-01-2014 to Aug-01-2015), validation (Aug-01-2015 to Oct-01-2015), and testing (Oct-01-2015 to Jan-01-2016). ... We then temporally split the examples into training (Jan-01-2007 to Jan-01-2015), validation (Jan-01-2015 to Jan-01-2016) and testing (Jan-012016 to Jan-01-2017).
Hardware Specification No The paper states that Adv-ALSTM is implemented with Tensorflow, but it does not provide any specific details about the hardware (e.g., GPU models, CPU types, or cloud instances) used for running the experiments.
Software Dependencies No The paper states 'We implement the Adv-ALSTM with Tensorflow and optimize it using the mini-batch Adam', but it does not specify version numbers for these software dependencies.
Experiment Setup Yes We implement the Adv-ALSTM with Tensorflow and optimize it using the mini-batch Adam[Diederik and Jimmy, 2015] with a batch size of 1,024 and an initial learning rate of 0.01. ... We further tune β and ϵ within [0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1] and [0.001, 0.005, 0.01, 0.05, 0.1], respectively.