Daily Trading Volume Research Articles

Enhanced Foreign Exchange Volatility Forecasting Using Ceemdan with Optuna-Optimized Ensemble Deep Learning Model

Foreign Exchange (FX) is the largest financial market in the world, with a daily trading volume that significantly exceeds that of stock and futures markets. The prediction of FX volatility is a critical financial concern that has garnered significant attention from researchers and practitioners due to its far-reaching implications in the financial markets. This paper presents a novel hybrid ensemble forecasting model integrating a decomposition strategy and three deep learning (DL) models: Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Convolutional Neural Network (CNN). This combination addresses individual models' limitations and further improves the accuracy and stability of FX volatility forecasting. The proposed approach utilizes the CEEMDAN technique to decompose volatility into multiple distinct intrinsic mode functions (IMFs) and merges these IMFs with GARCH and EGARCH volatilities to form the input dataset for the DL models. In addition, we employed an attention mechanism to improve the effectiveness of the DL techniques. Furthermore, the hyperparameters for the DL models are optimized using the Optuna algorithm. Finally, a hybrid ensemble model for forecasting exchange rate volatility is developed by combining the predictions of three distinct DL models. The proposed approach is evaluated against various benchmark models using evaluation measures such as MSE, MAE, HMSE, HMAE, RMSE, Q-LIKE, and the model confidence set (MCS) approach. The results demonstrate that our proposed approach provides accurate and reliable forecasts of FX volatility under different forecasting regimes, making it a valuable tool for financial practitioners and researchers.

The Impact Of Daftar Efek Syariah (DES) Announcement To The Asii’s Abnormal Returns And Trading Volume

DES announcement can be an important information for investors in making investment decisions. Islamic investors have to sell their stock when their stocks are excluded from DES. On the other hand, investors who want to invest in Islamic stocks will buy stocks that are included in the DES. The purpose of this study is to examine the impact of ASII stock reentry and exit from and into DES to the abnormal return and trading volume activity. This study uses secondary data obtained from investing.com. The data used in this study are daily stock closing prices, IHSG index and daily stock trading volume. This study follows event study methods. The first event window used in this study is 7 days before November,23,2020 and 7 days after. The second event window used is 7 days before May 24, 2023 and 7 days after. Descriptive statistic and Wilxocon sign ranks is used to analysis the data. The results showed that there was no significant difference in abnormal returns both at the time of ASII exit and reentry. However, trading volume of ASII stock significant difference before and after exit announcement. But when ASII stock reentry to the DES there was no significant difference.

Impacts of analyst coverage initiation on market quality

ABSTRACT We examine whether the initiation of financial analysts’ coverage leads to improved stock-price informativeness and increased market liquidity using the difference-in-differences methodology. The average value of daily total trading volume is significantly higher after than before initiation. The increase in trading volume is higher in the KOSDAQ market than in the KOSPI market, irrespective of investor type. Nonetheless, this increased rate is observed to decline more rapidly over time in the KOSDAQ market. When an analyst initiates coverage on a stock, both price informativeness and market liquidity improve, with different markets driving each effect. The enhancement of price informativeness is significant in the KOSPI, whereas the increase in market liquidity is primarily driven by firms listed on the KOSDAQ.

Capital Market Reaction to the Strengthening of the Rupiah Exchange Rate against the US Dollar Exchange Rate

The purpose of this study is to analyze the response of Indonesian capital markets to differences in average abnormal returns and average trading volume activity before and after the strengthening of the IDR/USD exchange rate. This study is a quantitative study using the event study method. The sample used consists of the stocks included in the LQ45 index. the most active stocks with a large daily trading volume. Hypothesis testing and paired t-test. The results of the hypothesis test show that: there is no significant difference in the average abnormal returns before and after the strengthening of the rupiah against the US dollar because are sig. (2-tailed) value of 0.417 > 0.05; there is no significant difference in the average trading volume activity before and after the strengthening of the rupiah against the US dollar because sig. (2-tailed) value of 0.080 >0.05. Keyword: Market Reaction; Event Study; Abnormal Return; Trading Volume Activity; Exchange Rate

A Time-Varying Mixture Integer-Valued Threshold Autoregressive Process Driven by Explanatory Variables.

In this paper, a time-varying first-order mixture integer-valued threshold autoregressive process driven by explanatory variables is introduced. The basic probabilistic and statistical properties of this model are studied in depth. We proceed to derive estimators using the conditional least squares (CLS) and conditional maximum likelihood (CML) methods, while also establishing the asymptotic properties of the CLS estimator. Furthermore, we employed the CLS and CML score functions to infer the threshold parameter. Additionally, three test statistics to detect the existence of the piecewise structure and explanatory variables were utilized. To support our findings, we conducted simulation studies and applied our model to two applications concerning the daily stock trading volumes of VOW.

Identification of stock market manipulation using a hybrid ensemble approach

Anomaly detection in time series data is a complex data mining issue with many useful, real-world applications. Anomalies in datasets represent deviations in the expected behaviour of a system and can indicate rare but significant events that require intervention. Market manipulation is a serious issue in financial jurisdictions worldwide, with financial regulators such as the SEC constantly trying to prevent it and prosecute those guilty of it. This paper makes use of state-of-the-art deep learning techniques as well as more classical statistical techniques in order to detect anomalies in five real-world datasets. The predictions of these models are then aggregated in two different ensemble models. The results of the individual models as well as the ensemble models, are evaluated, and F1-Score measures performance. Nine individual models, consisting of three models based on LSTM with Dynamic Thresholding, three ARIMA models and three Exponential Smoothing models, were used to generate predictions of anomalies based on daily trading volumes. The individual predictions of these models were then aggregated, with two different ensemble methods being used, namely the majority voting ensemble method and the ensemble averaging aggregation method. While both performed well, the majority voting ensemble method was seen to be the superior method in this study, with an average F1Score of 0.494, compared to an F1Score of 0.414 for the ensemble averaging aggregation method.

An extended exponential SEMIFAR model with application in R

The article at hand provides a detailed description of the esemifar R-package, which is an extension of the already published smoots R-package, enabling the data-driven local-polynomial smoothing of trend-stationary time series with long memory. In this regard, a simple data-driven algorithm is proposed based on the well-known iterative plug-in algorithm for SEMIFAR (semiparametric fractional autoregressive) models. Two new functions for data-driven estimation of the trend and its derivatives in the presence of long memory are introduced. esemifar is applied to various environmental and financial time series with long memory, for example, mean monthly Northern Hemisphere temperature changes, daily observations of the air quality index of London (Britain), quarterly G7-GDP and daily trading volume of the S & P500. It is worth mentioning that this package can be applied to any suitable time series.

Impacts of relatively rational and irrational investor sentiment on realized volatility

AbstractWe adopt intraday data in this study to facilitate an exploration of the influences of relatively rational and irrational investor sentiment on volatility within the Taiwan stock markets. Following the decomposition of daily trading volume within the Taiwan Stock Exchange Capitalization Weighted Stock Index (TWSE) into two subsets, comprising the trading volume of institutional investors and individual investors, we go on to investigate the influence of each subset on realized volatility. We reveal that the relatively rational sentiment of institutional investors plays a stabilizing role in future volatility, whereas the relatively irrational sentiment of individual investors tends to exacerbate such volatility. Therefore, we suggest that our modified model, which takes into account the relatively rational and irrational sentiment of investors, is capable of more accurately predicting volatility than the benchmark model.

Stock Price Reaction Analysis Before And After The Announcement Of The First Covid-19 PSBB Implementation On The Lq-45 Index Listed On The Indonesia Stock Exchange

This study was conducted to determine the reaction of stock prices before and after implementing the PSBB for the first time. Stock price reactions were measured by abnormal returns and trading volume activity using the event study method with an adjusted market model approach. The population used in this arrangement is the number of companies listed on the LQ-45 index for the February-July 2020 period, as many as 45 companies. The sample used a saturated sampling technique for as many as 45 companies. This research data uses secondary data consisting of daily stock closing prices and daily stock trading volumes with an observation period of seven days before the event, one day when the PSBB was implemented, and seven days after the PSBB was implemented. The statistical tools used were the normality test and the one-sample t-test. The results of this study indicate that there is a significant average abnormal return. However, there is no difference in abnormal returns before and after implementing the first PSBB. Besides that, the results show a significant average trading volume activity. However, trading volume activity is the same before and after the first PSBB implementation.

Measuring the Demand Connectedness among China's Regional Carbon Markets.

After years of emission trading in segmented pilots, China operates a unified market in the power system and plans to involve more industries in the coming future. The aim of this study is to detect the commonalities of transaction behaviors across China's regional carbon pilots, so as to provide an empirical basis for a future multi-sectoral expansion of national trading. Based on a dataset of daily trading volume in seven regional markets during 2014-2021, the empirical results from connectedness measures show that the total demand connectedness ranges from 10% to 24%, indicating the existence of interactions among China's regional markets. This not-so-wide range of fluctuation usually shows a trend of rising first and then falling within each year, during which the upward trend is basically related to the accounting, verification and compliance of allowances. After these time nodes, the total connectedness declines. In addition, the directional connectedness could help clarify the specific roles that regional markets play in the variations of total demand connectedness when facing the shocks of these time nodes. Meanwhile, the frequency decomposition reveals that a longer-term component of more than 10 days dominates the connectedness. Based on these findings, some policy implications are provided alongside.

Air quality improvement effect and future contributions of carbon trading pilot programs in China

The carbon trading policy is a market-based tool aimed at reducing carbon emissions and may simultaneously yield a combined air quality improvement effect. This study employs a two-way fixed-effect model to estimate the causal relationship between daily carbon trading volumes and air pollution from 2015 to 2020. Results show that a one percent increase in daily carbon trading volumes leads to a reduction of 0.23% in PM2.5 and 0.26% in PM10. In addition to particulate matter, the carbon market can significantly reduce SO2 and air quality index. We also examine provincial and regional heterogeneities and find an apparent reduction effect in Beijing, Guangdong, Hubei, Tianjin, and cities in the more economically developed eastern region. Notably, our estimations indicate that the carbon market’s impact on reducing air pollution is most significant annually during the carbon quota compliance period and tends to intensify over the years. Furthermore, we predict the carbon trading scale to meet China’s stringent future air quality improvement target, indicating that the carbon trading volumes are projected to be 450 million tons in 2035 under the high contribution scenarios. These findings can provide insightful policy implications for China and other countries to establish more flexible and well-rounded carbon trading policies.

ANALISIS ABNORMAL RETURN DAN TRADING VOLUME ACTIVITY SEBELUM DAN SETELAH PENGUMUMAN DIVIDEN PT.KALBE FARMA SAAT PANDEMI COVID-19

PT. Kalbe Farma became one of the issuers that during the Covid-19 pandemic earned alarge profit per share, so this study aims to see if there is abnormal return and tradingvolume activity around the date of dividend announcement made by PT. Kalbe Farma duringthe Covid-19 pandemic. The event study method is used to study the reaction of theIndonesian Capital Market during the observation period. The observation period is carriedout five days before the dividend announcement and five days after the dividendannouncement of PT. Kalbe Farma. Secondary data used in this study are data on the closingprice of daily shares, daily JCI, daily trading volume, and the number of outstanding shares.The results found that there were abnormal differences in returns before and after dividendannouncements, and there were also differences in trading volume of activity before and afterthe dividend announcement of PT. Kalbe Farma.

The Return of the Call Auction

A call auction is a form of trading that died out in the precomputer age but has made its reentrance in electronic markets and is currently a significant component of major stock markets globally. In contrast with a continuous market in which a transaction is made any time a buy and a sell order meet or cross in price, call auctions batch orders together for execution in multilateral trades at specific points in time. The electronic call, an important innovation in market structure, has unique benefits concerning liquidity provision, intraday volatility control, and price discovery accuracy. NASDAQ introduced electronic calls to open and close its markets in 2004, and the NYSE did the same in 2007. Using data between 2010 and 2021 for these two markets, the authors assess how the opening and closing call auction volumes compare to the daily continuous trading volume and investigate the factors that impact the use of call auctions.

Research on the Feasibility of Applying GRU and Attention Mechanism Combined with Technical Indicators in Stock Trading Strategies

The vigorous development of Time Series Neural Network in recent years has brought many potential possibilities to the application of financial technology. This research proposes a stock trend prediction model that combines Gate Recurrent Unit and Attention mechanism. In the proposed framework, the model takes the daily opening price, closing price, highest price, lowest price and trading volume of stocks as input, and uses technical indicator transition prediction as a label to predict the possible rise and fall probability of future trading days. The research results show that the proposed model and labels designed by this research can effectively predict important stock price fluctuations and can be effectively applied to financial commodity trading strategies.

An Analysis of Stock Splits Trading Volume for BSE 500 Index Companies

With a sample of 65 businesses listed on the Bombay Stock Exchange from 2008 to 2021, the focus of this research is to examine any notable changes in trading volume activity before and after a company's stock split announcements. An event window of 61 days is used to calculate the number of stocks traded on daily basis. According to the findings of the individual company level investigation, trading volume increased for 37 companies, while it decreased for the other 28. However, the results of just 21 of the companies are statistically significant. Trade volume has increased in eight sectors while declining in three others, according to a sectoral analysis of the trading volume. Stock splits enhance post-split liquidity for the vast majority of sample businesses in the month after the split, according to the study's empirical findings, as assessed by daily trading volume and number of shares traded.

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

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.

The Relation Between Trading Volume Concentration and Stock Returns

The Taiwan Stock Exchange discloses data on daily trading volume across brokerage firms for each listed stock. Market practitioners suggest that the concentration of trading volume contains information on the trading behaviors of big players. We use the Gini Coefficient to measure the degree of concentration, upon which a trading strategy is proposed. We conduct an event study to examine whether such a strategy will yield abnormal returns. Our sample contains 375 listed companies with events identified during the sample period from February 2020 to August 2020. The empirical results show that the trading signal based on the Gini coefficient is informative and that most of the average abnormal returns after the event date are significantly positive with the cumulative average abnormal returns increasing almost monotonically up to the end day of the event window. Consistent with prior studies in which different measures of concentration are utilized, our findings provide additional evidence that the Gini Coefficient could help investors to develop profitable stock selection and market timing strategies.

The Relationship between Current COVID-19 and Indonesia Stock Market: Evidence from ARDL Model

This study aims to prove how COVID-19 in response to the Indonesia stock market applying an Auto-Regressive Distributed Lag (ARDL) cointegration method. This study analyzes the relationship between the natural logarithm of daily trading volume of the Indonesia Stock Exchange and the natural logarithm of daily COVID-19 confirmed cases both in the short run and the long run. Bound test and cointegration were used to analyze the data daily from 2 March 2020 until 30 November 2020. The findings result show in the short-run, Indonesia stock market is only influenced by its lag, but not in the long-run. Meanwhile COVID-19 variable proved to be not significantly affected the stock market both in short and long-run. The model is predicted to re-stabilize at least over 1.7 months later

Современные особенности курсообразования валют на примере пары доллар США – евро

The relevance of the research topic is determined by globalization processes, which have a huge impact on our country, as well as on the countries around us and their economies. In modern conditions, it is obvious that the financial difficulties of one country can cause a global crisis. Issues of a qualitative analysis of the monetary system are important for the stability of the economies of countries. The authors of the article emphasize that the monetary system is needed in order to regulate foreign exchange relations. The authors did not choose the EUR/USD pair by chance – it is the most traded currency pair in the Forex market (about 29% of the total daily trading volume). Such popularity is due primarily to the fact that the United States and the European Union are two of the strongest economies in the world. In addition, this pair responds quite predictably to the main economic indicators relating to the United States and the European Union. Based on the analysis, the authors made conclusions, made recommendations on the need to adapt the trading strategy to market volatility. The procedure for forming EUR/USD quotes at various hours, days and months has been studied. EUR/USD is compared with several other currency pairs and their ranges in separate trading sessions. the following conclusions are made: EUR/USD has medium volatility compared to other pairs under consideration, but is clearly inferior to GBPUSD and GBPJPY; the volatility for most couples during the Asian session is low, and in the case of detruding it encourages the use of scalping; during the European and American sessions, volatility is almost doubled.

Stock markets and female participation in the labor force

This paper examines the relation between female participation in the labor force and stock market trading volume. We focus on the first teaching day of the year at kindergartens and primary schools, treating it as an event with characteristics that resemble an exogenous event, and verify this using a web-based survey. We find that the first day of school has lower trading volume than the average daily trading volume during the rest of the year. Moreover, we document that female workforce participation is negatively associated with the trading volume on this day and that, in societies that have legislated gender nondiscrimination laws that govern hiring, this negative effect is even more pronounced. Our main findings document a significant societal phenomenon with a profound effect on stock markets, and specifically on the quality of the information environment, and therefore merit further attention.