scholarly journals A Novel Trading Strategy Framework Based on Reinforcement Deep Learning for Financial Market Predictions

Mathematics ◽  
2021 ◽  
Vol 9 (23) ◽  
pp. 3094
Author(s):  
Li-Chen Cheng ◽  
Yu-Hsiang Huang ◽  
Ming-Hua Hsieh ◽  
Mu-En Wu
Keyword(s):  
Stock Market ◽  
Financial Market ◽  
Stock Prices ◽  
Trading Volume ◽  
Prediction Models ◽  
Trading Strategies ◽  
Q Learning ◽  
Price Prediction ◽  
Market Trends ◽  
Stock Market Investors

The prediction of stocks is complicated by the dynamic, complex, and chaotic environment of the stock market. Investors put their money into the financial market, hoping to maximize profits by understanding market trends and designing trading strategies at the entry and exit points. Most studies propose machine learning models to predict stock prices. However, constructing trading strategies is helpful for traders to avoid making mistakes and losing money. We propose an automatic trading framework using LSTM combined with deep Q-learning to determine the trading signal and the size of the trading position. This is more sophisticated than traditional price prediction models. This study used price data from the Taiwan stock market, including daily opening price, closing price, highest price, lowest price, and trading volume. The profitability of the system was evaluated using a combination of different states of different stocks. The profitability of the proposed system was positive after a long period of testing, which means that the system performed well in predicting the rise and fall of stocks.

scholarly journals Is Abnormally Large Volume a Clue?

2016 ◽  
Vol 8 (9) ◽  
pp. 226
Author(s):  
Tsung-Hsun Lu ◽  
Jun-De Lee
Keyword(s):  
Stock Market ◽  
Large Volume ◽  
Stock Prices ◽  
Stock Price ◽  
Trading Volume ◽  
Sensitive Analysis ◽  
Support Level ◽  
Out Of Sample ◽  
Sample Test ◽  
Abnormal Trading Volume

This paper investigates whether abnormal trading volume provides information about future movements in stock prices. Utilizing data from the Taiwan 50 Index from October 29, 2002 to December 31, 2013, the researchers employ trading volume rather than stock price to test the principles of resistance and support level employed by technical analysis. The empirical results suggest that abnormal trading volume provides profitable information for investors in the Taiwan stock market. An out-of-sample test and a sensitive analysis are conducted for the robustness of the results.

scholarly journals Understanding the Interdependency between the Nifty 50 Future Index and the Advanced Future Stock Market through Econometrics

2019 ◽  
Vol 8 (4) ◽  
pp. 3660-3664
Keyword(s):  
Hong Kong ◽  
Stock Market ◽  
Granger Causality ◽  
Foreign Exchange ◽  
Financial Market ◽  
Stock Prices ◽  
Economic Condition ◽  
The Future ◽  
Bidirectional Movement ◽  
High Degree

In recent times the stock market is accepted as a tool to measure the economic condition of a nation. It is found that the Indian financial market as highly volatile due to the lower value of rupees in foreign exchange with the dollar. This motivated the researchers to measure the interdependencies of [Nifty 50 future (India), Nikkei 225(Japan), NASDAQ 100 Futures (USA), Dow Jones 30 (USA), SSEC (China), Hang Seng Future (Hong Kong), and FTSE 100 (London)]. The analysis covers monthly stock prices for a period of 10years from April 2008 to March 2018. The measurement of interdependencies is studied through granger causality and correlation after the confirmation of the non-normality of data and stationary of data. The result shows a high degree of correlation between NASDAQ and Dow Jones shows 98.76% followed by 96.89% between Nifty 50 future and NASDAQ. The co-movement result of Nifty 50 future through granger causality states Nifty 50 future can explain the future stock market of Nikkei (Japan) and SSEC (China) and the Hang Seng future (Hong Kong) has a bidirectional movement with Nifty 50 futures. The study is useful for the investors to identify the interdependencies of the indices and understand the movement in a significant manner.

scholarly journals Review on Machine Learning Techniques for Stock-Market Forecasting

2020 ◽  
pp. 34-47
Author(s):  
Sushma Jaiswal ◽  
Tarun Jaiswal
Keyword(s):  
Stock Market ◽  
Soft Computing ◽  
Stock Prices ◽  
Machine Learning Techniques ◽  
Market Values ◽  
Stock Market Forecasting ◽  
Soft Computing Method ◽  
Learning Techniques ◽  
Stock Market Investors ◽  
Computing Method

Stock marketplace tradeoff is an endless investment implementation worldwide. It has capabilities to produce maximum profits on stockholders’venture. In the globe, the stock-market forecasting is a very puzzling job for the stock-market investors. The task is very challenging because of the ambiguity and precariousness of the stock market values. Due to commercialization and data mining modules the growth of stock marketplaces, it is essential to predict marketplace variations quick and easy way. Recently, ANN is very famous and attracted to investors for its easy-going process in the stock-market. ANN plays a very imperative part in today’s stock-market for decision making and prediction. The Multi-Layer-Perceptron methods are outperformed then other methods. Also, these approaches have countless likelihoods to envisage with high accuracy than other approaches. In this review paper, neural-based envisage implements are measured to foresee the imminent stock-prices and their enactment dimensions will be assessed. Here we deliver a broad impression of the soft computing based stock-market likelihood with emphasis on enabling technologies, issues and application issues. Soft computing is attracting a lot of researchers and industrial innovation. The purpose of this paper is to presents a survey of the existing soft computing method applied to stock market prediction, their comparison and possible solution. From the reviewed articles, it is obvious that investigators have resolutely intensive on the growth of fusion forecast representations and considerable effort has also been completed on the use of broadcasting data for stock marketplace forecast. It is also enlightening that most of the literature has focused on the forecast of stock prices in developing marketplace.

scholarly journals Formulation of a Prediction Index with the Help of WEKA Tool for Guiding the Stock Market Investors

2016 ◽  
Vol 9 (3) ◽  
pp. 212-225 ◽  
Author(s):  
Aseema Kulkarni ◽  
Ajit More
Keyword(s):  
Decision Making ◽  
Stock Market ◽  
Stock Prices ◽  
Machine Learning Techniques ◽  
Algorithmic Trading ◽  
Stock Market Forecasting ◽  
Learning Techniques ◽  
Stock Market Investors ◽  
Automated Decision Making ◽  
Radical Transformation

Prediction of stock prices using various computer programs is on rise. Popularly known in the field of finance as algorithmic trading, a radical transformation has taken place in the field of stock markets for decision making through automated decision making agents. Machine learning techniques can be applied for predicting stock prices. This paper attempts to study the various stock market forecasting processes available in the forecasting plugin of the WEKA tool. Twenty experiments have been conducted on twenty different stocks to analyse the prediction capacity of the tool.

Trading Volume and Cross-Autocorrelations of Stock Returns in Emerging Markets: Evidence from the Taiwan Stock Market

2004 ◽  
Vol 07 (04) ◽  
pp. 509-524
Author(s):  
Wen-Hsiu Kuo ◽  
Hsinan Hsu ◽  
Chwan-Yi Chiang
Keyword(s):  
Stock Market ◽  
Stock Returns ◽  
Stock Prices ◽  
Trading Volume ◽  
Price Limits ◽  
Speed Of Adjustment ◽  
New Information ◽  
Weak Evidence ◽  
Market Inefficiency ◽  
Daily Returns

This study empirically investigates the interaction between trading volume and cross-autocorrelations of stock returns in the Taiwan stock market. The result shows that returns on high trading volume portfolios lead returns on low trading volume portfolios when controlled for firm size, indicating that trading volume determines lead-lag cross-autocorrelations of stock returns. Overall, the empirical findings of this study demonstrate similar results for both monthly and daily returns, suggesting that nonsynchronrous trading is not the main reason for the lead-lag cross-autocorrelations presented in this study. Consequently, the empirical results presented here support the speed of adjustment hypothesis, and suggest that some market inefficiency exists in the Taiwan stock market. Additionally, compared with evidence of lead-lag cross-autocorrelations in the larger, less regulated US stock market, as examined by Chordia and Swaminathan (2000), Taiwan stock market displays less evidence of VARs and Dimson beta regressions. We conjecture that this weak evidence may result from the regulations limiting daily price movements in the Taiwan stock market. Although the price limits policy lowers risk and stabilizes stock prices, it also prevents stock prices and trading volume from instantaneously and fully reflecting new information.

scholarly journals Pension funds, large capital inflows and stock returns in a thin market

2018 ◽  
Vol 18 (3) ◽  
pp. 347-387
Author(s):  
JANUSZ BRZESZCZYŃSKI ◽  
MARTIN T. BOHL ◽  
DOBROMIŁ SERWA
Keyword(s):  
Stock Market ◽  
Stock Returns ◽  
Stock Prices ◽  
Pension Funds ◽  
Price Impact ◽  
Capital Inflows ◽  
Policy Implications ◽  
Private Pension ◽  
Long Run ◽  
Stock Market Investors

Using unique data about capital flows from the public social security institute ZUS (Zakład Ubezpieczeń Społecznych) to private pension funds OFEs (Otwarte Fundusze Emerytalne) in Poland, we find that their impact, as a group of large institutional investors, on stock returns is statistically significant in short-term but no such effect exists in the long-run. This result is consistent with the temporary price pressure hypothesis of Ben-Rephael et al. (2011). We analyze the capital transfers, in the form of the aggregated pension contributions collected from all employees in the entire Polish economy, from the ZUS to the private pension funds, which further invest this capital on the stock market. The average time for the subsequent reaction of stock prices is found to be 4 days. The trading strategy based on this result generates superior outcomes in comparison with the passive strategy, which further confirms the price impact of capital inflows. Our findings are not only relevant for stock market investors but they also have broader policy implications for stock market regulators and for the national pension regulators.

scholarly journals Using a Genetic Algorithm to Build a Volume Weighted Average Price Model in a Stock Market

2021 ◽  
Vol 13 (3) ◽  
pp. 1011
Author(s):  
Seung Hwan Jeong ◽  
Hee Soo Lee ◽  
Hyun Nam ◽  
Kyong Joo Oh
Keyword(s):  
Genetic Algorithm ◽  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Trading Volume ◽  
Weighted Average ◽  
Market Liquidity ◽  
Average Price ◽  
Volume Data ◽  
The Impact

Research on stock market prediction has been actively conducted over time. Pertaining to investment, stock prices and trading volume are important indicators. While extensive research on stocks has focused on predicting stock prices, not much focus has been applied to predicting trading volume. The extensive trading volume by large institutions, such as pension funds, has a great impact on the market liquidity. To reduce the impact on the stock market, it is essential for large institutions to correctly predict the intraday trading volume using the volume weighted average price (VWAP) method. In this study, we predict the intraday trading volume using various methods to properly conduct VWAP trading. With the trading volume data of the Korean stock price index 200 (KOSPI 200) futures index from December 2006 to September 2020, we predicted the trading volume using dynamic time warping (DTW) and a genetic algorithm (GA). The empirical results show that the model using the simple average of the trading volume during the optimal period constructed by GA achieved the best performance. As a result of this study, we expect that large institutions will perform more appropriate VWAP trading in a sustainable manner, leading the stock market to be revitalized by enhanced liquidity. In this sense, the model proposed in this paper would contribute to creating efficient stock markets and help to achieve sustainable economic growth.

scholarly journals Exploring frequency of price overreactions in the Ukrainian stock market

2018 ◽  
Vol 15 (3) ◽  
pp. 157-168 ◽  
Author(s):  
Alex Plastun ◽  
Inna Makarenko ◽  
Lyudmila Khomutenko ◽  
Yanina Belinska ◽  
Maryna Domashenko
Keyword(s):  
Stock Market ◽  
Stock Returns ◽  
Statistical Tests ◽  
Trading Strategies ◽  
Market Prices ◽  
Price Prediction ◽  
Crisis Events ◽  
Augmented Dickey Fuller ◽  
Causality Tests ◽  
Static Approach

This paper explores the frequency of price overreactions in the Ukrainian stock market by focusing on the PFTS Index over the period 2006–2017 and UX index over the period 2008–2017, as well as some “blue chips” (BAVL, UNAF, MSICH, CEEN) for the period of 2013–2015. Using static approach to detect overreactions, a number of hypotheses are tested: the frequency of price overreactions is informative about crisis events in the economy (H1), can be used for price prediction purposes (H2), and exhibits seasonality (H3). To do this, various statistical tests (both parametric and non-parametric), including correlation analysis, augmented Dickey-Fuller tests (ADF), Granger causality tests, and regression analysis with dummy variables, are carried out. Hypotheses H1 and H2 are confirmed: frequency of price overreactions can be used as a crisis predictor (a sharp increase in the number of overreactions is associated with a crisis period) and could be used to predict stock returns. No seasonality in the overreactions frequency is found. Implications of this research include crisis prediction and stock market prices forecasting and can be used for designing trading strategies.

scholarly journals Multi-Factorized Semi-covariance of Stock Markets and Gold Price

2021 ◽  
Author(s):  
Jun Huang ◽  
Mei Huang ◽  
Lin Yang ◽  
Yun Shi
Keyword(s):  
Stock Market ◽  
Financial Market ◽  
Gold Price ◽  
Fractional Dimension ◽  
Significant Interest ◽  
Calculation Results ◽  
Complex Models ◽  
Market Leader ◽  
Market Trends ◽  
Insight Into

Complex models have received significant interest in recent years and are being increasingly used to explain the stochastic phenomenon with upward and downward fluctuation such as the stock market. Different from existing semi-variance methods in traditional integer dimension construction for two variables, this paper proposes a simplified multi-factorized fractional dimension derivation with the exact Excel tool algorithm involving the fractional center moment extension to covariance, which is a complex parameter average that is a multi-factorized extension to Pearson covariance. By examining the peaks and troughs of gold price averages, the proposed algorithm provides more insight into revealing underlying stock market trends to see who is the financial market leader during good economic times. The calculation results demonstrate that the complex covariance is able to distinguish subtle differences among stock market performances and gold prices for the same field that the two variable covariance may overlook. We take the London, Tokyo, Shanghai, Toronto and Nasdaq as the representative examples.

Sign in / Sign up

Export Citation Format

Share Document