Abstract
Predicting stock prices through machine learning is a highly anticipated research area. Previous studies have shown improved accuracy in stock price prediction using machine learning, and this study also reported a high degree of accuracy. However, the amount of past data is limited, and the psychological and subjective factors of traders are also involved, and it is still a field with many problems. The effects of weather on human psychology have already been studied and shown to have the potential to affect the psychology of stock traders. In this study, we proposed a new data generation method that takes into account the psychological effects of weather. In detail, image data combining stock price data and weather data were created and trained using a convolutional neural network (CNN). Then, by confirming the validity of the method, we confirmed that weather data can provide clues for predicting stock price fluctuations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yoshikazu, I., Minoru, H.: Application of deep learning to stock price forecasting. Rev. Bus. Econ. 52, Nos. 1,2,3, and 4), The Economic Society of The University of Kitakyushu 13–26 (2017). (in Japanese)
Touru, T., Haruto, T.: Application for a foreign exchange trading system using by AI. In: Proceedings of the National Conference of the Association for Information Systems society of Japan 14. (Johoshisutemugakkaizennkkokutaikaironnbunnsyu14) Information Systems society of Japan (2018). (in Japanese)
Yoshitaka, F.: The impact of weather and seasons on emotional disorders. (kisho.kisetsunokanjoshogaihenoeikyo), Global Environ. 8(2), 221–228 (2003). (in Japanese)
Hideyuki, F.M., Shimura.: Meteorolingical factors and mental disorders - with special reference to psychiatric emergency cases. Jap. J. Biometeorol. 24(2), 67–73 (1987). (in Japanese)
Hideaki, K.: The mysterious relationship between weather and stock prices. (tenkitokabukanofushiginakankei), Toyo Keizai Shinposha (2004). (in Japanese)
Dichev, I.D., Janes, T.D.: Lunar cycle effects in stock returns. J. Private Equity 6(4), 8–29 (2003)
Keiichi, G., Hiroshi, T., Takao, T.: Estimating news articles’ negative-positive by deep learning. In: The 29th Annual Conference of the Japanese Society for Artificial Intelligence, The The Japanese Society for Artificial Intelligence (2015). (in Japanese)
Junya, O.: Prediction of Stock Market Price from Economical News Text Data Using Deep Learning. Bachelor’s Degree Thesis of Kochi University of Technology (2014). (in Japanese)
Yukihiro, T., Atushi, O.: Analysis of the psychological influence on economic indicators by the relationship between the release date of hit movies and stock prices (Economic Analysis of Technological Progress (2)) (hittoeiganokokaibitokabukanokankeiniyorukeizaishihyohenoshinritekieikyonobunseki). In: Annual Conference Proceedings 21.2, Japan Society for Research Policy and Innovation Management (2006). (in Japanese)
Cao, M., Jason, W.: Stock market returns: a note on temperature anomaly. J. Banking Finan. 29(6), 1559–1573 (2005)
Kunihiro, M., Yutaka, M.: Stock prediction analysis using deep learning technique. In: The 31 Annual Conference of the Japanese Society for Artifical Interigence, The Japanese Society for Artificial Intelligence (2017). (in Japanese)
Yoshikazu, I.: Stock movement forecasting with candlestick charts using convolutional neural networks. The review of business and economics, The University of Kitakyushu, vol. 54 no. 1, pp. 1–18 (2019). (in Japanese)
Yoshikazu, I.: An analysis on improving accuracy of deep learning stock price prediction with ensemble learning. The review of business and economics, The University of Kitakyushu, vol. 56, no. 1, pp. 15–34 (2021). (in Japanese)
Keiichi, G., Hiroshi, T., Takao, T.: Modeling the volatility clustering with recurrent neural network. Summary Collection of the National Conference on Business Information Systems 2017 Spring National Research Presentation Conference of the Japan Society of Information and Management (keieijohogakuzenkokukenkyuhappyotaikaiyoshishu2017nenshunkizenkokukenkyuhappyotaikai), The Japan Society for Management Information (2017). (in Japanese)
Katsuhiko, O. : Glabal market seasonality and investor sentiment : a text-mining approach. J. Bus. Admin. 61(4), 110–136 (2014). (in Japanese)
Acknowledgements
This work was supported in part by JSPS KAKENHI Grant Number JP18K11473 and 22K12182.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nakaniwa, K., Matsuki, T., Iguchi, M., Notsu, A., Honda, K. (2023). Predicting Stock Price Fluctuations Considering the Sunny Effect. In: Honda, K., Le, B., Huynh, VN., Inuiguchi, M., Kohda, Y. (eds) Integrated Uncertainty in Knowledge Modelling and Decision Making. IUKM 2023. Lecture Notes in Computer Science(), vol 14376. Springer, Cham. https://doi.org/10.1007/978-3-031-46781-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-46781-3_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46780-6
Online ISBN: 978-3-031-46781-3
eBook Packages: Computer ScienceComputer Science (R0)