Robust Portfolio Optimization using LSTM-based Stock and Cryptocurrency Price Prediction: An Application of Algorithmic Trading Strategies

Algorithmic trading (AT) has become widely used recently because of its high speed and accuracy in implementing diverse and complex strategies. Using algorithms also allows traders to execute their trading strategies in a high volume and numerous transactions without involving human emotions. While...

Full description

Saved in:
Bibliographic Details
Main Authors: Mehrdad Heydarpour, Hossein Ghanbari, Emran Mohammadi, Saeed Shavvalpour
Format: Article
Language:English
Published: Ferdowsi University of Mashhad 2025-07-01
Series:Iranian Journal of Accounting, Auditing & Finance
Subjects:
Online Access:https://ijaaf.um.ac.ir/article_46039_2cc452aeb68b12518fe4220f0aec055e.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849329541961482240
author Mehrdad Heydarpour
Hossein Ghanbari
Emran Mohammadi
Saeed Shavvalpour
author_facet Mehrdad Heydarpour
Hossein Ghanbari
Emran Mohammadi
Saeed Shavvalpour
author_sort Mehrdad Heydarpour
collection DOAJ
description Algorithmic trading (AT) has become widely used recently because of its high speed and accuracy in implementing diverse and complex strategies. Using algorithms also allows traders to execute their trading strategies in a high volume and numerous transactions without involving human emotions. While AT has many advantages, it also carries some risks due to the uncertain stock market conditions and the impact of news and political, social, and other events. Therefore, forming a stock portfolio and stabilizing against uncertainties, in conjunction with accurate market predictions, can significantly reduce risk.in this paper, For the first time, we developed a robust portfolio optimization model based on LSTM prediction using the AT strategies based on short-term moving average techniques. First, we implement the strategies derived from the VLMA, FLMA, EMA, and SMA algorithms based on the LSTM's predicted price. Secondly, we develop a robust portfolio optimization model using the abovementioned algorithms. The results show that in both stock and crypto portfolios, moving average strategies will perform better than the benchmark strategy (Buy-and-hold). Also, when the model parameters are deterministic, the robust portfolio constructed stocks and crypto will perform better than Buy-and-hold for all algorithms. However, when the variance from certain models increases, VLMA and FLMA (15-day holding) for stocks and FLMA (30-day holding) for the crypto will not be a suitable investment option. Additionally, portfolios constructed using all AT strategies and all assets outperform the benchmark portfolio in certain and non-certain markets.
format Article
id doaj-art-855a8c464a5a4ab4952ce4b02f742544
institution Kabale University
issn 2717-4131
2588-6142
language English
publishDate 2025-07-01
publisher Ferdowsi University of Mashhad
record_format Article
series Iranian Journal of Accounting, Auditing & Finance
spelling doaj-art-855a8c464a5a4ab4952ce4b02f7425442025-08-20T03:47:13ZengFerdowsi University of MashhadIranian Journal of Accounting, Auditing & Finance2717-41312588-61422025-07-019315116910.22067/ijaaf.2025.46039.146646039Robust Portfolio Optimization using LSTM-based Stock and Cryptocurrency Price Prediction: An Application of Algorithmic Trading StrategiesMehrdad Heydarpour0Hossein Ghanbari1Emran Mohammadi2Saeed Shavvalpour3MSc Student in Industrial Engineering, Faculty of Industrial Engineering, Iran University of Science and Technology, Tehran, IranSchool of Industrial Engineering, Iran University of Science and Technology, Tehran, IranIUSTIUSTAlgorithmic trading (AT) has become widely used recently because of its high speed and accuracy in implementing diverse and complex strategies. Using algorithms also allows traders to execute their trading strategies in a high volume and numerous transactions without involving human emotions. While AT has many advantages, it also carries some risks due to the uncertain stock market conditions and the impact of news and political, social, and other events. Therefore, forming a stock portfolio and stabilizing against uncertainties, in conjunction with accurate market predictions, can significantly reduce risk.in this paper, For the first time, we developed a robust portfolio optimization model based on LSTM prediction using the AT strategies based on short-term moving average techniques. First, we implement the strategies derived from the VLMA, FLMA, EMA, and SMA algorithms based on the LSTM's predicted price. Secondly, we develop a robust portfolio optimization model using the abovementioned algorithms. The results show that in both stock and crypto portfolios, moving average strategies will perform better than the benchmark strategy (Buy-and-hold). Also, when the model parameters are deterministic, the robust portfolio constructed stocks and crypto will perform better than Buy-and-hold for all algorithms. However, when the variance from certain models increases, VLMA and FLMA (15-day holding) for stocks and FLMA (30-day holding) for the crypto will not be a suitable investment option. Additionally, portfolios constructed using all AT strategies and all assets outperform the benchmark portfolio in certain and non-certain markets.https://ijaaf.um.ac.ir/article_46039_2cc452aeb68b12518fe4220f0aec055e.pdfrobust portfolio optimizationalgorithmic tradingprice predictionlstm
spellingShingle Mehrdad Heydarpour
Hossein Ghanbari
Emran Mohammadi
Saeed Shavvalpour
Robust Portfolio Optimization using LSTM-based Stock and Cryptocurrency Price Prediction: An Application of Algorithmic Trading Strategies
Iranian Journal of Accounting, Auditing & Finance
robust portfolio optimization
algorithmic trading
price prediction
lstm
title Robust Portfolio Optimization using LSTM-based Stock and Cryptocurrency Price Prediction: An Application of Algorithmic Trading Strategies
title_full Robust Portfolio Optimization using LSTM-based Stock and Cryptocurrency Price Prediction: An Application of Algorithmic Trading Strategies
title_fullStr Robust Portfolio Optimization using LSTM-based Stock and Cryptocurrency Price Prediction: An Application of Algorithmic Trading Strategies
title_full_unstemmed Robust Portfolio Optimization using LSTM-based Stock and Cryptocurrency Price Prediction: An Application of Algorithmic Trading Strategies
title_short Robust Portfolio Optimization using LSTM-based Stock and Cryptocurrency Price Prediction: An Application of Algorithmic Trading Strategies
title_sort robust portfolio optimization using lstm based stock and cryptocurrency price prediction an application of algorithmic trading strategies
topic robust portfolio optimization
algorithmic trading
price prediction
lstm
url https://ijaaf.um.ac.ir/article_46039_2cc452aeb68b12518fe4220f0aec055e.pdf
work_keys_str_mv AT mehrdadheydarpour robustportfoliooptimizationusinglstmbasedstockandcryptocurrencypricepredictionanapplicationofalgorithmictradingstrategies
AT hosseinghanbari robustportfoliooptimizationusinglstmbasedstockandcryptocurrencypricepredictionanapplicationofalgorithmictradingstrategies
AT emranmohammadi robustportfoliooptimizationusinglstmbasedstockandcryptocurrencypricepredictionanapplicationofalgorithmictradingstrategies
AT saeedshavvalpour robustportfoliooptimizationusinglstmbasedstockandcryptocurrencypricepredictionanapplicationofalgorithmictradingstrategies