Close Price Research Articles

MCS-MCMC for Optimising Architectures and Weights of Higher Order Neural Networks

The standard method to train the Higher Order Neural Networks (HONN) is the well-known Backpropagation (BP) algorithm. Yet, the current BP algorithm has several limitations including easily stuck into local minima, particularly when dealing with highly non-linear problems and utilise computationally intensive training algorithms. The current BP algorithm is also relying heavily on the initial weight values and other parameters picked. Therefore, in an attempt to overcome the BP drawbacks, we investigate a method called Modified Cuckoo Search-Markov chain Monté Carlo for optimising the weights in HONN and boost the learning process. This method, which lies in the Swarm Intelligence area, is notably successful in optimisation task. We compared the performance with several HONN-based network models and standard Multilayer Perceptron on four (4) time series datasets: Temperature, Ozone, Gold Close Price and Bitcoin Closing Price from various repositories. Simulation results indicate that this swarm-based algorithm outperformed or at least at par with the network models with current BP algorithm in terms of lower error rate.

Forecasting the changes in daily stock prices in Shanghai Stock Exchange using Neural Network and Ordinary Least Squares Regression

The research focuses on finding a superior forecasting technique to predict stock movement and behavior in the Shanghai Stock Exchange. The author’s interest is in stock market activities during high volatility, specifically 13 years from 2002 to 2015. This volatile period, fueled by events such as the dot-com bubble, SARS outbreak, political leadership transitions, and the global financial crisis, is of interest. The study aims to analyze changes in stock prices during an unstable period. The author used advanced computer sciences, Machine Learning through information processing and training, and the traditional statistical approach, the Multiple Linear Regression Model, with the least square method. Both techniques are accurate predictors measured by Absolute Percent Error with a range of 1.50% to 1.65%, using a data file containing 3,283 observations generated to record the daily close prices of individual Chinese companies. The t-test paired difference experiment shows the superiority of Neural Network in the finance sector and potentially not in other sectors. The Multiple Linear Regression Model performs equivalent to the Neural Network in other sectors.

Large Dynamic Covariance Matrices: Enhancements Based on Intraday Data

Multivariate GARCH models do not perform well in large dimensions due to the so-called curse of dimensionality. The recent DCC-NL model of Engle et al. (2019) is able to overcome this curse via nonlinear shrinkage estimation of the unconditional correlation matrix. In this paper, we show how performance can be increased further by using open/high/low/close (OHLC) price data instead of simply using daily returns. A key innovation, for the improved modeling of not only dynamic variances but also of dynamic correlations, is the concept of a regularized return, obtained from a volatility proxy in conjunction with a smoothed sign of the observed return.

THE EFFECT OF STOCK SPLIT ANNOUNCEMENT ON THE TRADING VOLUME ACTIVITY, ABNORMAL RETURN, AND BID ASK SPREAD (STUDY ON COMPANIES LISTED ON THE IDX FOR THE PERIOD OF 2015 - 2019)

This research is motivated by companies that carry out corporate actions in the form of stock splits. The corporate action aims to increase the liquidity of the outstanding shares and to give a positive signal to the company's performance in the future. To find out whether this signal is true or not, it is necessary to test market efficiency which proves that the stock split has an effect on changes in stock trading volume, abnormal returns and the bid ask spread. This type of research is the event study research with a quantitative approach. A sample of 66 companies using purposive sampling technique. The company under study is a company that carried out a stock split and is listed on the Indonesia Stock Exchange for the period 2015 - 2019. The type of data used in this study is secondary data in the form of daily data on sales of shares, number of shares outstanding, stock price (close price), price index. joint stock, stock offer and bid during the period 2015 - 2019. The results of the research through the Wilcoxon Signed Ranks Test with the results (1) There is no significant difference between stock trading volume before and after the stock split; (2) There is a significant difference between abnormal returns before and after the stock split; (3) There is no significant difference between the bid ask spread before and after the stock split.

Forecasting of Global Market Prices of Major Financial Instruments

One of the easiest and fastest ways of building a healthy financial future is investing in the global market. However, the prices of the global market are highly volatile due to the impact of economic crises. Therefore, future prediction and comparison lead traders to make the low-risk decisions with price. The present study is based on time series modelling to forecast the daily close price values of financial instruments in the global market. The forecasting models were tested with two sample sizes, namely, 5-year close price values for correlation analysis and 3-year close price values for model building from 2013 January to 2018 January. The forecasting capabilities were compared for both ARIMA and GARCH class models, namely, TGARCH, APARCH, and EGARCH. The best-fitting model was selected based on the minimum value of the Akaike information criterion (AIC) and Bayesian information criteria (BIC). Finally, the comparison was carried out between ARIMA and GARCH class models using the measurement of forecast errors, based on the Root Mean Square Deviation (RMSE), Mean Absolute Error (MAE), and Mean absolute percentage error (MAPE). The GARCH model was the best-fitted model for Australian Dollar, Feeder cattle, and Coffee. The APARCH model provides the best out-of-sample performance for Corn and Crude Oil. EGARCH and TGARCH were the better-fitted models for Gold and Treasury bond, respectively. GARCH class models were selected as the better models for forecasting than the ARIMA model for daily close price values in global financial market instruments.

Application of Cloud Model in Qualitative Forecasting for Stock Market Trends.

Forecasting stock prices plays an important role in setting a trading strategy or determining the appropriate timing for buying or selling a stock. The use of technical analysis for financial forecasting has been successfully employed by many researchers. The existing qualitative based methods developed based on fuzzy reasoning techniques cannot describe the data comprehensively, which has greatly limited the objectivity of fuzzy time series in uncertain data forecasting. Extended fuzzy sets (e.g., fuzzy probabilistic set) study the fuzziness of the membership grade to a concept. The cloud model, based on probability measure space, automatically produces random membership grades of a concept through a cloud generator. In this paper, a cloud model-based approach was proposed to confirm accurate stock based on Japanese candlestick. By incorporating probability statistics and fuzzy set theories, the cloud model can aid the required transformation between the qualitative concepts and quantitative data. The degree of certainty associated with candlestick patterns can be calculated through repeated assessments by employing the normal cloud model. The hybrid weighting method comprising the fuzzy time series, and Heikin–Ashi candlestick was employed for determining the weights of the indicators in the multi-criteria decision-making process. Fuzzy membership functions are constructed by the cloud model to deal effectively with uncertainty and vagueness of the stock historical data with the aim to predict the next open, high, low, and close prices for the stock. The experimental results prove the feasibility and high forecasting accuracy of the proposed model.

Stock Price Trend Forecasting using Long Short Term Memory Recurrent Neural Networks

The prediction of future stock price trend using current and historical stock market data is a research problem for traders and researchers. Recently deep learning methods shown promising performance to extract meaningful information from the given large data. In this paper, we proposed a system to predict the next trading session close price trend from historical stock trading data using long short term memory (LSTM) method. This is a classification problem next trading session close price trend can be uptrend, downtrend, or sideways trend. We built an automated trading system using the results of our classifier. We experimented with the proposed trading system on the American index stocks. Our experimental results show that the proposed method outperforms the buy-and-hold and decision tree-based method.

Application of Enhanced Hidden Markov Model in Stock Price Prediction

The main focus of this research is the enhancement of the Hidden Markov Model by using some features of Neural Networks and the forecasted values of predictors by Seasonal Autoregressive Integrated Moving Average. The enhanced method was used to predict the close price of stocks whose predictors are open price, high price, low price, and volume of Apple and Nokia data. The performance of the method was measured using the Mean Absolute Percentage Error of the predicted price. The result was compared against the actual close price by using the paired T-test. The testing of the hypothesis showed that the Enhanced Hidden Markov Model obtained more than 94% accuracy rate. It also shows that in Apple data, the predicted close price of the Enhanced Hidden Markov Model is significantly better than the predicted close price of Neural Networks. Using Nokia data, the test claims that there is no difference between the performance of Enhanced Hidden Markov Model and Neural Network in prediction.

Tail Risk Transmission: A Study of the Iran Food Industry

This paper extends the extreme downside correlation (EDC) and extreme downside hedge (EDH) methodology to model the interdependence in the sensitivity of assets to the downside risk of other financial assets under severe firm-level and market conditions. The model is applied to analyze both systematic and systemic exposures in the Iranian Food Industry. The empirical application investigates (1) which company is the safest for investors to diversify their investment, and (2) which companies are the “transmitters” and “receivers” of downside risk. We study the return series of 11 companies and the Food Industry index publicly listed on the Tehran Stock Exchange. The data covers daily close prices from 2015–2020. The result shows that Mahram Manufacturing is the safest to hedge equity risk, and Glucosan and Behshahr Industries are the riskiest, while Gorji Biscuit is central to risk transmission, and Pegah Fars Diary is the main “receiver” of risk in turbulent times.

Dynamic Time Warping Application for Financial Pattern Recognition

Close price pattern is one of the widely applied technical indicators in market operations and trading. However, datasets or programming packages including calculation or labeling of close price patterns barely exist in public. With understanding of difficulties and flexibility of identifying a typical close price pattern, we developed a pattern recognition algorithm specially for close price patterns using Featured-based Dynamic Time Warping and Pattern Rule. The algorithm exhibits identified sequences with close resemblance of target financial patterns while incorporating some variations tolerable in human sense.

Bullish and Bearish Engulfing Japanese Candlestick patterns: A statistical analysis on the S&P 500 index

Technical analysts believe that by studying past price action, it is possible to forecast future prices of specific securities. Technical analysts rely on the use of charts, which graphically show the past fluctuations of prices. This study focuses on the chart style known as Japanese candlesticks, which relies on four pieces of information for every session: Open, High, Low and Close prices. It is believed that some candle patterns possess predictive capabilities that can alert investors of imminent price tops, bottoms, or price trend continuations. For this study, we performed a statistical analysis, using historical prices of the S&P 500 index, of the effectiveness of Bullish Engulfing and Bearish Engulfing patterns, which are believed to forecast bottoms and tops respectively. Results indicate that the Bearish Engulfing provide strong short-term forecasting power when using the Open and High criteria but not the Close criterion. Likewise, the Bullish Engulfing offered strong short-term forecasting power when using the Open and Low criteria but not the Close criterion.

Does Black Monday appear on The Indonesia Stock Exchange?

Stock transactions are based on a daily transaction, where Monday beginsmore closed time than other days. For this reason, Monday is more volatile than other days. We find that a positive return opportunity larger (more than 60%) occurs on all trading days. This result indicates the potential for Investment in Indonesia Stock Exchange. We also found “Black Monday” in sectors 1 and 9, indicate Monday Lower Return and Volume compare other days. For both the LQ 45 & sector 4 information flow occurs so that the open price (t) is different from the close price(t-1).

An Attention-Based LSTM Model for Stock Price Trend Prediction Using Limit Order Books

Stock price trend prediction has been a hot issue in the financial field, which has been paid much attention by both academia and industry. It is a challenging task due to the non-stationary and high volatility of the stock prices. Traditional methods for predicting stock price trends are mostly based on the historical OHLC (i.e., open, high, low, and close prices) data. However, it eliminates most of the trading information. To address this problem, in this paper, another type of stock price data, i.e., limit order books (LOBs), is used. For better exploring the relationship of the LOBs and stock price trend, inspired by the successful application of deep learning-based methods, an attention-based LSTM model is applied. The trend of stock price can be predicted by using the LOBs data of the previous day. By using the real stock price data of the China stock market, the effectiveness of the proposed model is validated by experimental results.

Tail Risk Transmission: A Study of Iran Food Industry

This paper extends the extreme downside correlations and hedge (EDC and EDH) methodology of Harris et al. (2019) to model the tail risk co-movement of financial assets under severe firm-level and market conditions. The model is applied to analyze both systematic and systemic exposures in the Iranian food industry. The empirical application address the following questions: 1) which food company is the safest for investors to diversify their investment, and 2) which companies are the risk transmitters and receivers, especially in turbulent times. To this end, we sampled the time series of 11 manufacturing companies and proxy the market indicator with the food industry index, all of which are publicly listed on the Tehran Stock Exchange (TSE). The data covers daily close prices from October 5, 2015, to January 15, 2020. The systematic analysis reveals a positive and statistically significant relationship between the tail risk of the companies and the market index. The centrality analysis of the systemic exposures reveals Mahram Manufacturing as the safest and Behshahr Industries as the riskiest company. We also find evidence that W.Azar.Pegah is the main transmitter of tail risk, while Pegah.Fars.Co is the main receiver of risk.

Clearing price distributions in call auctions

We propose a model for price formation in financial markets based on the clearing of a standard call auction with random orders, and verify its validity for prediction of the daily closing price distribution statistically. The model considers random buy and sell orders, placed employing demand- and supply-side valuation distributions; an equilibrium equation then leads to a distribution for clearing price and transacted volume. Bid and ask volumes are left as free parameters, permitting possibly heavy-tailed or very skewed order flow conditions. In highly liquid auctions, the clearing price distribution converges to an asymptotically normal central limit, with mean and variance in terms of supply/demand-valuation distributions and order flow imbalance. By means of simulations, we illustrate the influence of variations in order flow and valuation distributions on price/volume, noting a distinction between high- and low-volume auction price variance. To verify the validity of the model statistically, we predict a year's worth of daily closing price distributions for five constituents of the Eurostoxx 50 index; Kolmogorov–Smirnov statistics and QQ-plots demonstrate with ample statistical significance that the model predicts closing price distributions accurately, and compares favourably with alternative methods of prediction.

An approach to predict and forecast the price of constituents and index of cryptocurrency using machine learning

At present, cryptocurrencies have become a global phenomenon in financial sectors, as it is one of the most traded financial instruments worldwide. Cryptocurrency is not only one of the most complicated and abstruse fields among financial instruments but also deemed as a perplexing problem in finance due to its high volatility. This work makes an attempt to apply machine learning techniques on the index and constituents of cryptocurrency with a goal to predict and forecast prices thereof. In particular, the purpose of this article is to predict and forecast the close (closing) price of the cryptocurrency index 30 and nine constituents of cryptocurrencies using machine learning algorithms and models so that it becomes easier for people to trade these currencies. We have used several machine learning techniques and algorithms and compared the models with each other to get the best output. We believe that our work will help reduce the challenges and difficulties faced by people who invest in cryptocurrencies. Moreover, the obtained results can play a major role in cryptocurrency portfolio management and in observing the fluctuations in the prices of constituents of cryptocurrency market. We have also compared our approach with similar state of the art works from the literature, where machine learning approaches have been considered for predicting and forecasting the prices of these currencies. In the sequel, we have found that our best approach presents better and competitive results (especially by using ensemble learning method) than the best works from the literature thereby advancing the state of the art. Using such prediction and forecasting methods, people can easily understand the trend and it would be even easier for them to trade in a difficult and challenging financial instrument like cryptocurrency.

Portfolio trading system of digital currencies: A deep reinforcement learning with multidimensional attention gating mechanism

As a hot topic in the financial engineering, the portfolio optimization aims to increase investors’ wealth. In this paper, a portfolio management system based on deep-reinforcement learning is proposed. In contrast to inflexible traditional methods, the proposed system achieves a better trading strategy through Reinforcement learning. The reward signal of Reinforcement learning is updated by action weights from Deep learning networks. Low price, high price and close price constitute the inputs, but the importance of these three features is quite different. Traditional methods and the classical CNN can’t deal with these three features separately, but in our method, a designed depth convolution is proposed to deal with these three features separately. In a virtual currency market, the price rise only occurs in a flash. Traditional methods and CNN networks can’t accurately judge the critical time. In order to solve this problem, a three-dimensional attention gating network is proposed and it gives higher weights on rising moments and assets. Under different market conditions, the proposed system achieves more substantial returns and greatly improves the Sharpe ratios. The short-term risk index of the proposed system is lower than those of the traditional algorithms. Simulation results show that the traditional algorithms (including Best, CRP, PAMR, CWMR and CNN) are unable to perform as well as our approach.

Foreign exchange prediction based on indices and commodities price using convolutional neural network

The level of accuracy in predicting is the key in conducting forex trading activities in gaining profits. Some predictions are made only by using historical currency data to be predicted, this makes predictions less accurate because they do not consider external influences. This study examines external factors that can influence the results of predictions, by looking for the relationship between the value of indices such as NTFSE and S & P 500 and the value of commodities such as gold and silver to the prediction process of EUR / USD. Prediction carried out using a deep learning algorithm with the Convolutional Neural Network method uses 2 1-dimensional convolution layers with ReL activation. The data used is the value of Open, High, Low and Close prices on forex, indices and commodities which are combined into one with the close forex value target for the next 5 days. Testing of EUR / USD test data only gets MSE results of 0.00081894. While the results of testing of the combined test data between EUR / USD, indices and commodities producing MSE vary between 0.00068717 to 0.0109606 where the best combination is a combination of FTSE 100 and Natural Gas values. So it can be concluded that other factors included in predicting have an influence on the results obtained.

Spillover of COVID-19: Impact on the Global Economy

How did a health crisis translate to an economic crisis? Why did the spread of the coronavirus bring the global economy to its knees? The answer lies in two methods by which coronavirus stifled economic activities. First, the spread of the virus encouraged social distancing which led to the shutdown of financial markets, corporate offices, businesses and events. Second, the exponential rate at which the virus was spreading, and the heightened uncertainty about how bad the situation could get, led to flight to safety in consumption and investment among consumers, investors and international trade partners. We focus on the period from the start of 2020 through March when the coronavirus began spreading into other countries and markets. We draw on real-world observations in assessing the restrictive measures, monetary policy measures, fiscal policy measures and the public health measures that were adopted during the period. We empirically examine the impact of social distancing policies on economic activities and stock market indices. The findings reveal that the increasing number of lockdown days, monetary policy decisions and international travel restrictions severely affected the level of economic activities and the closing, opening, lowest and highest stock price of major stock market indices. In contrast, the imposed restriction on internal movement and higher fiscal policy spending had a positive impact on the level of economic activities, although the increasing number of confirmed coronavirus cases did not have a significant effect on the level of economic activities.

Markowitz Model in The Analysis of Optimal Portfolio Establishment on Jakarta Islamic Index (JII) in Indonesian Stock Exchange

This study aims to know the optimal portfolio establishment using Markowitz model on Jakarta Islamic Index (JII) stocks in the period of December 2013-May 2019. The population of this study consisted of the company stocks on Jakarta Islamic Index (JII) in the period of December 2013-May 2019, and there were 59 stocks. While the study sample consisted of 14 company stocks and selected based on purposive sampling method. Data collection used in this study using documentation. Data analysis used in this study using the stages of Markowitz model and started collecting the close price until an optimal portfolio establishment. The result of this study showed that there were 8 company stocks included in the optimal portfolio. Namely AKRA (5,01%), ICBP (9,92%), INDF (3,75%), SMGR (8,61%), TLKM (29,01%), UNTR (20,30%), UNVR (20,88%), WIKA (2,53%). The expected return of the portfolio of 0,84%. Therefore, portfolio risk of 3,16%and smaller than the risk of individual stocks in the research sample.