Deep Learning for Event-Driven Stock Prediction

Authors: Xiao Ding, Yue Zhang, Ting Liu, Junwen Duan

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that our model can achieve nearly 6% improvements on S&P 500 index prediction and individual stock prediction, respectively, compared to state-of-the-art baseline methods.
Researcher Affiliation Academia Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China {xding, tliu, jwduan}@ir.hit.edu.cn Singapore University of Technology and Design yue zhang@sutd.edu.sg
Pseudocode Yes Algorithm 1: Event Embedding Training Process
Open Source Code No The paper does not explicitly provide a link or statement about the availability of its source code. Footnote 1 refers to the dataset released by Ding et al. [2014], not the code for this paper's methodology.
Open Datasets Yes We use financial news from Reuters and Bloomberg over the period from October 2006 to November 2013, released by Ding et al. [2014]1. (Footnote 1: http://ir.hit.edu.cn/~xding/index_english.htm)
Dataset Splits Yes Detail statistics of training, development (tuning) and test sets are shown in Table 1.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions tools like 'Re Verb' and 'ZPar' and algorithms like 'skip-gram' but does not specify version numbers for these or any other software dependencies.
Experiment Setup Yes The standard L2 regularization weight λ is set as 0.0001. The iteration number N is set to 500. The input of neural tensor network is word embeddings and the output is event embeddings. We learn the initial word representation of d-dimensions (d = 100) from large-scale financial news corpus, using the skip-gram algorithm [Mikolov et al., 2013]. We use a feedforward neural network with one hidden layer and one output layer.