LSTM-based Deep Learning Model for Stock Prediction and Predictive Optimization Model

Rather, Akhter Mohiuddin

doi:10.1016/j.ejdp.2021.100001

Cited by 30 publications

(12 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A work by Rather proposed a new method of predicting time-series-based stock prices and a new model of an investment portfolio based on forecast results from LSTM model. Their results show that theei model outperforms various standard predictive models [10].…”

Section: Lstmmentioning

confidence: 98%

Application of LSTM and portfolio optimization in Chinese stock market

Zheng¹

2022

BCPBM

View full text Add to dashboard Cite

The purpose of this paper is to examine the application of LSTM and mean variance portfolio optimization in Chinese stock market. 20 stocks are selected from CSI 300 components, we collect their High, Low, Open, Adjust Close and trade volume from June 16th 2020 to June 16th 2022. Then we use LSTM model to forecast the stock price. The forecast results are used to construct 2 portfolios. One portfolio maximize Sharpe ratio, the other portfolio minimize variance. From April 6th to June 16th 2022, the Maximize Sharpe Ratio portfolio outperformed CSI 300 index, the Minimize Variance Portfolio did not beat the market but the return was very close to CSI. Therefore, the combination of LSTM and Mean Variance Portfolio Optimization theory is effective in Chinese stock market.

show abstract

Section: Lstmmentioning

confidence: 98%

Application of LSTM and portfolio optimization in Chinese stock market

Zheng¹

2022

BCPBM

View full text Add to dashboard Cite

show abstract

“…Tese models were estimated for 284 stocks from the S&P 500 stock market index, comparing the MAE obtained from their predictions. Rather [45] proposed a new method of predicting time-series-based stock prices considering the investment portfolio problem. A new regression scheme was implemented on a long-short-term memory-based deep neural network.…”

Section: Literature Reviewmentioning

confidence: 99%

An Approach for a Multi-Period Portfolio Selection Problem by considering Transaction Costs and Prediction on the Stock Market

et al. 2023

View full text Add to dashboard Cite

This paper addresses a method to solve a multi-period portfolio selection on the stock market. The portfolio problem seeks an investor to trade stocks with a finite budget and a given integer number of stocks to hold in a portfolio. The trade must be performed through a stockbroker that charges its respective transaction cost and has its minimum required trade amount. A mathematical model has been proposed to deal with the constrained problem. The objective function is to find the best risk-return rate; thus, Sharpe Ratio and Treynor Ratio are used as objective functions. The returns are the same for these ratios, but the risks are not Sharpe considering covariance and Treynor systematical risk. The returns are predicted using a Neural Net with Long-Short-Term Memory (LSTM). This neural net is compared with simple forecasting methods through Mean Absolute Percentage Error (MAPE). Computational experiments show the quality prediction performed by LSTM. The heteroskedastic risk is estimated by Generalized Autoregressive Conditional Heteroskedasticity (GARCH), adjusting the variance for every period; this risk measure is used in Sharpe Ratio. The experiment contemplates a weekly portfolio selection with 5 and 10 stocks in 122 weekly periods for each Chilean market ratio. The best portfolio is Sharpe Ratio with ten stocks, performing a 62.28% real return beating the market, represented by the Selective Stock Price Index (IPSA). Even the worst portfolio, Treynor Ratio, overcomes the IPSA cumulative yield with ten stocks.

show abstract

“…Researchers have actively conducted stock price prediction studies using the LSTM model, which has shown good prediction results in time series data. Rather [18] proposed an LSTM-based method for predicting NIFTY-50 stock prices traded on the National stock exchange of India and showed that the model outperforms various standard predictive models. Bhandari et al [19] applied an LSTM model that uses fundamental variables, macroeconomic variables, and technical indicators as inputs to make prediction regarding the S&P 500 stock index, and revealed excellent predictive performance.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Long Short-Term Memory-based Prediction Performance of COVID-19 Fear Index on Asset Prices: Stocks vs Cryptocurrencies

Kim¹

2022

APJCRI

View full text Add to dashboard Cite

External shocks to the stock market make investors highly aware of the risk of asset investment and lead them to expect correspondingly higher returns. As a result, risk in the market increases, causing asset prices to fall. Applying a Granger causality test to data from the COVID-19 pandemic period, this study tested whether the COVID-19 fear index is useful in predicting asset prices in the stock and cryptocurrency markets and assessed the COVID-19 fear index's Long Short-Term Memory model-based asset price prediction performance. The Long Short-Term Memory model was developed to deal with the vanishing gradient problem that can emerge when training traditional Recurrent Neural Networks using the cell states. Using data spanning the period from early 2020 when COVID-19 began to April 2022, this study's empirical analysis produced the following results. First, it showed significant negative correlations between the fear index and both stock and cryptocurrency prices. During the COVID-19 pandemic crisis, cryptocurrencies played the role of speculative rather than safe assets. Second, both stock and cryptocurrency prices showed significant Granger causality. Third, the impulse response function indicated that both stocks and cryptocurrencies overreacted to the shock of the COVID-19 pandemic. The degree of overreaction was stronger in the stock market. Fourth, the price prediction performance of the Long Short-Term Memory time series model using price data and the COVID-19 fear index as input variables was excellent. In particular, its forecast performance for medium-and small-sized assets was higher than for large-sized assets such as Bitcoin and largesized KOSPI. While outbreaks of infectious diseases such as COVID-19 directly impact the economy and the stock market, this study's results indicate that COVID-19 had less of an impact on the cryptocurrency market, which is also affected by non-economic factors.

show abstract

LSTM-based Deep Learning Model for Stock Prediction and Predictive Optimization Model

Cited by 30 publications

References 72 publications

Application of LSTM and portfolio optimization in Chinese stock market

Application of LSTM and portfolio optimization in Chinese stock market

An Approach for a Multi-Period Portfolio Selection Problem by considering Transaction Costs and Prediction on the Stock Market

Long Short-Term Memory-based Prediction Performance of COVID-19 Fear Index on Asset Prices: Stocks vs Cryptocurrencies

Contact Info

Product

Resources

About