Forecasting Apple Stock Closed Prices by LR and LSTM with Discrete Wavelet Transformation

Yuxin Yang ()
Additional contact information
Yuxin Yang: Woodsworth College, University of Toronto

A chapter in Proceedings of the 2022 2nd International Conference on Economic Development and Business Culture (ICEDBC 2022), 2022, pp 935-943 from Springer

Abstract: ABSTRACT Stock prediction has long had a high profile among investors under the incentives of profit maximization. However, as a result of the instability and chaos of the financial stock market, predicting stock prices is challenging. To address this problem, the discrete wavelet transformation (DWT) is applied to denoise stock prices when data preprocessing. Long short-term memory (LSTM) and linear regression model (LR) are chosen to train the model. The performances of LR, LSTM, the combination of DWT and LR and the combination of DWT and LSTM are demonstrated and compared when predicting the Apple stock closed prices by using its rescaled closed price five days ago. The prediction results proved the effectiveness of DWT and illustrated LR still acts well although it is much simpler compared with LSTM in terms of RMSE, MAE, MAPE. These model- based analytic strategies and pre-programmed stock price prediction are likely to give precious guidance to investors in the pursuit of maximum benefits.

Keywords: LR; DWT; LSTM; Apple; Forecast (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:advbcp:978-94-6463-036-7_138

Ordering information: This item can be ordered from
http://www.springer.com/9789464630367

DOI: 10.2991/978-94-6463-036-7_138

Access Statistics for this chapter

More chapters in Advances in Economics, Business and Management Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().