@inproceedings{51a410cf4ea140288105b58c36efc140,
title = "GANStick: US stock forecasting with GAN-generated candlesticks",
abstract = "Stock forecast with candlestick patterns is heavily based on template-oriented and rule-based heuristics, which requires laborious sample labelling and profound financial expertise. These methods are retrospective in nature and fail to capture premature or partial signals in candlesticks. Such rigidity limits the application of candlesticks primarily to classification tasks. Thus, we propose a novel, end-to-end deep learning model, GANStick, to address all these issues. GANStick is a conditional DCGAN-convolutional BiLSTM-based model which generates future predictive candlesticks to augment multistep time series forecasting with regression. GANStick has been empirically shown to significantly beat multiple baseline implementations, with an average error rate of 68% lower across all five timesteps on the dataset composed of 11 large-cap US stocks. GANStick is the first work in automating the workflow from candlestick pattern recognition and generation to quantifying future price volatility, with the novel generative candlestick approach using the generative adversarial network.",
keywords = "Deep learning, Fintech, GAN, Machine learning, Stock forecasting",
author = "Wong, {Man Hing} and Lee, {Lik Hang} and Pan Hui",
note = "Publisher Copyright: {\textcopyright} ICIS 2020. All rights reserved.; 2020 International Conference on Information Systems - Making Digital Inclusive: Blending the Local and the Global, ICIS 2020 ; Conference date: 13-12-2020 Through 16-12-2020",
year = "2020",
month = dec,
language = "English",
series = "International Conference on Information Systems, ICIS 2020 - Making Digital Inclusive: Blending the Local and the Global",
publisher = "Association for Information Systems",
booktitle = "International Conference on Information Systems, ICIS 2020 - Making Digital Inclusive",
address = "United States",
}