Search results

Predicting the stock market's prices has always been an interesting topic since its closely related to making money. Recently, the advances in natural language processing (NLP) have opened new perspectives for solving this task. The purpose of this paper is to show a state-of-the-art natural language approach to using language in predicting the stock market.

In this paper, the conventional statistical models for time-series prediction are implemented as a benchmark. Then, for methodological comparison, various state-of-the-art natural language models ranging from the baseline convolutional and recurrent neural network models to the most advanced transformer-based models are developed, implemented and tested.

Experimental results show that there is a correlation between the textual information in the news headlines and stock price prediction. The model based on the GRU (gated recurrent unit) cell with one linear layer, which takes pairs of the historical prices and the sentiment score calculated using transformer-based models, achieved the best result.

This study provides an insight into how to use NLP to improve stock price prediction and shows that there is a correlation between news headlines and stock price prediction.

The crude oil market has experienced an unprecedented overreaction in the first half of the pandemic year 2020. This study aims to show the performance of the global crude oil market amid Covid-19 and spillover relations with other asset classes.

The authors employ various pandemic outbreak indicators to show the overreaction of the crude oil market due to Covid-19 infection. The analysis also presents market connectedness and spillover relations between the crude oil market and other asset classes.

One of the essential findings the authors report is that the crude oil market remains more responsive to pandemic fake news. The shock of the global pandemic panic index and pandemic sentiment index appears to be more promising. It has also been noticed that the energy trader's sentiment (OVX and OIV) was measured at a too high level within the Covid-19 outbreak. Volatility spillover analysis shows that crude oil and other market are closely connected, and the total connectedness index directs on average 35% contribution from spillover. During the initial growth of the infection, other macroeconomic and political events remained to favor the market. The second phase amidst the pandemic outbreak harms the global crude oil market. The authors find that infectious diseases increase investor panic and anxiety.

The crude oil investors' sentiment index OVX indicates fear and panic due to infectious diseases and lack of hedge funds to protect energy investments. The unparalleled overreaction of the investors gauged in OVX indicates market participants have paid an excessive put option (protection) premium over the contagious outbreak of the infectious disease.

The empirical model and result reported amid Covid-19 are novel in terms of employing a news-based index of the pandemic, which are based on the content analysis and text search using natural processing language with the aid of computer algorithms.

原油市場在流行病肆虐的2020年的頭半年經歷史無前例的過度反應。本文旨在顯示全球原油市場在2019冠狀病毒病流行期間的表現及原油市場與其它資產類別之溢出關係.

我們使用各種大流行病爆發的指標，來顯示原油市場因2019冠狀病毒病的感染而過度反應。我們的分析亦涉及市場的關聯性及原油市場與其它資產類別之溢出關係.

我們其中一個基本的發現是: 原油市場仍對大流行病的虛假新聞有更迅速的反應。全球大流行病恐慌性指數及大流行病情緒指數所帶來的震驚似乎是有希望的。大家亦察覺，能源交易商的情緒(OVX及OIV) 在2019冠狀病毒病爆發期間被測量為處於太高的水平。波動溢出分析顯示、原油與其它市場有密切的關係，而總關聯度指數引導平均35%來自溢出量的作用。在感染傳播初期，其它的宏觀經濟和政治事件仍對市場有利。在大流行病爆發期間的第二階段則損害全球原油市場。我們發現，傳染病會增加投資者的恐慌和焦慮.

原油投資者的情緒指數OVX顯示因傳染病及因缺乏對沖基金來保障能源投資而帶來的懼怕和恐慌。於OVX測算到的投資者空前的過度反應顯示市場參與者就這傳染病的感染爆發付出過量的賣權(保障)權利金.

我們的經驗模型和在2019冠狀病毒病肆虐期間匯報的研究結果，從使用以新聞為基礎的流行病指數的角度而言是新穎的。而這些全以內容分析和正文搜尋為基礎、使用自然語言處理，並輔以計算機算法.

The current study aims to investigate the impacts of two behavioral biases, namely, loss aversion and overconfidence on the performance of US companies. First, the impact of loss aversion on the economic performance of companies was assessed. Second, the impact of overconfidence on market performance was discussed.

This study used around 6,777 quarterly observations on the population of US-insured industrial and services companies over the 2006-2016 period. Ordinary least squares (OLS) regression in two panel data models were used to test the hypotheses formulated for the study.

It was documented that the loss-aversion bias negatively affects the economic performance of companies and this is achieved for both sectors. In contrast, the findings suggest that overconfidence positively affects market performance of industrial firms but negatively affects market performance in service firms. Further robust evidence was found that overconfidence bias seems to be dominant, and hence, investors may tend to be more overconfident rather than more loss-averse.

This research can be extended by focusing on the following question: What is the impact of the contradictory (positive and negative) effects of an investor's loss aversion and overconfidence on the US company performance in case of realization of a stock market crisis or stock market crash?

In the 40 years of reform and opening-up toward a more rational micro-economic structure, the proportion of output of state-owned enterprises shows a declining trend. Over the past decade, on one hand, the operational efficiency of state-owned enterprises has tended to be low as compared to other ownership enterprises; on the other hand, the asset–liability ratio of state-owned enterprises has risen against the trend, and still remains high under the recent national policy of “deleveraging.” The paper aims to discuss this issue.

This indicates that the inefficiency of state-owned enterprises that once hindered China’s economic development has not yet been fundamentally solved, and the task of deepening state-owned enterprises reform is still arduous.

In the process of establishing China’s modern economic system, there will be some “new state-owned enterprises” growing into world-class ones. This requires more effort in enhancing the capacity for independent innovation, improving the level of organizational control, expanding international market opportunities and fulfilling enterprise social responsibilities with high standards.

It is more appropriate for China to have a micro-economic structure in which public ownership predominates and diverse forms of ownership enjoy common prosperity and development.

Both investors and the stock markets are believed to behave in a perfectly rational manner, where investors focus on utility maximization and are not subjected to cognitive biases or any information processing errors. However, it has been discovered that the sentiment of the social mood has a significant impact on the stock market. This study aims to analyze how did the protest event of Tesla happened in April 2021 have a significant effect on the company's stock performance as well as its competitors, Nio, under the competitive effect.

The research is based on time series data collected from Tesla and Nio by employing 10 days, 15 days and 20 days anticipation and adjustment period for the event study. This study employed a text sentiment analysis to identify the polarity of the sentiment of the protest event using the Microsoft Azure machine learning tool which utilizes MPQA subjective lexicon.

The findings provide further evidence to show that a company-specific negative event has deteriorating effects on its stock performance, while having an opposite effect on its competitors.

The paper argues that negative sentiments through social media word of mouth (SWOM) affect the stock market not just in the short run but potentially in the longer run. Such negative sentiments might create a snowball effect which causes the market to further scrutinize a company's operations and possibly lose confidence in the company.

This study explores how the Tesla's protest event at Shanghai Auto Show 2021 has a significant impact on Tesla's stock performance and prolonged negative impact although Tesla implemented immediate remedial actions. The remedial actions were not accepted positively and induced a wave of negative news which had a more persistent effect.

For policymakers and participants of financial markets, predictions of trading volumes of financial indices are important issues. This study aims to address such a prediction problem based on the CSI300 nearby futures by using high-frequency data recorded each minute from the launch date of the futures to roughly two years after constituent stocks of the futures all becoming shortable, a time period witnessing significantly increased trading activities.

In order to answer questions as follows, this study adopts the neural network for modeling the irregular trading volume series of the CSI300 nearby futures: are the research able to utilize the lags of the trading volume series to make predictions; if this is the case, how far can the predictions go and how accurate can the predictions be; can this research use predictive information from trading volumes of the CSI300 spot and first distant futures for improving prediction accuracy and what is the corresponding magnitude; how sophisticated is the model; and how robust are its predictions?

The results of this study show that a simple neural network model could be constructed with 10 hidden neurons to robustly predict the trading volume of the CSI300 nearby futures using 1–20 min ahead trading volume data. The model leads to the root mean square error of about 955 contracts. Utilizing additional predictive information from trading volumes of the CSI300 spot and first distant futures could further benefit prediction accuracy and the magnitude of improvements is about 1–2%. This benefit is particularly significant when the trading volume of the CSI300 nearby futures is close to be zero. Another benefit, at the cost of the model becoming slightly more sophisticated with more hidden neurons, is that predictions could be generated through 1–30 min ahead trading volume data.

The results of this study could be used for multiple purposes, including designing financial index trading systems and platforms, monitoring systematic financial risks and building financial index price forecasting.

This study investigates the role of cryptocurrencies in enhancing the performance of portfolios constructed from traditional asset classes. Using a long sample period covering not only the large value increases but also the dramatic declines during the beginning of 2018, the purpose of this paper is to provide a more complete analysis of the dynamic nature of cryptocurrencies as individual investment opportunities, and as components of optimal portfolios.

The mean-variance optimization technique of Merton (1990) is applied to develop the risk and return characteristics of the efficient portfolios, along with the optimal weights of the asset class components in the portfolios.

The authors provide evidence that as a single investment, the best cryptocurrency is Ripple, followed by Bitcoin and Litecoin. Furthermore, cryptocurrencies have a useful role in the optimal portfolio construction and in investments, in addition to their original purposes for which they were created. Bitcoin is the best cryptocurrency enhancing the characteristics of the optimal portfolio. Ripple and Litecoin follow in terms of their usefulness in an optimal portfolio as single cryptocurrencies. Including all these cryptocurrencies in a portfolio generates the best (most optimal) results. Contributions of the cryptocurrencies to the optimal portfolio evolve over time. Therefore, the results and conclusions of this study have no guarantee for continuation in an exact manner in the future. However, the increasing popularity and the unique characteristics of cryptocurrencies will assist their future presence in investment portfolios.

This is one of the first studies that examine the role of popular cryptocurrencies in enhancing a portfolio composed of traditional asset classes. The sample period is the largest that has been used in this strand of the literature, and allows to compare optimal portfolios in early/recent subsamples, and during the pre-/post-cryptocurrency crisis periods.

This study aims to investigate Malaysian stock market efficiency from the view of Sharīʿah-compliant and conventional stocks based on the effectiveness of technical trading strategies.

This study uses unconventional trading strategies that mix buy recommendations of Bursa Malaysia analysts with sell signals generated from 10 selected technical trading strategies (simple moving average, moving average envelopes, Bollinger Bands, momentum, commodity channel index, relative strength index, stochastic, Williams percentage range, moving average convergence divergence oscillator and shooting star) that are detected using ChartNexus. The period from 1 January 2013 until 31 December 2015 produces a total sample consisting of 1,265 buy recommendations of 125 Sharīʿah-compliant stocks and 400 buy recommendations of conventional stocks. The study period is extended until 31 March 2016 to provide an ample time for detecting the sell signal especially for buy recommendations that are released towards the end of 2015.

The resulting Jensen’s alpha show 8 out of 10 strategies are effective in generating abnormal returns in Sharīʿah-compliant samples while only 3 out of 10 strategies are effective in conventional samples. Prominent effectiveness of technical trading strategies in Sharīʿah-compliant stocks implies clear inefficiency in that stock market segment as opposed to those of the conventional stocks.

The results based on unconventional trading strategies provide new insights of Malaysian stock market efficiency especially in Sharīʿah-compliant and conventional stocks. The paper provides more robust findings on market efficiency as firms’ equity level data were focussed together with analysts’ buy recommendations from Bursa Malaysia.

How did investors in the Swedish Premium Pension System (PPS) react to the stock market shock ignited by the COVID-19 pandemic?

The authors use fund-level data from the Swedish Pensions Agency on investment choices in the PPS. For each fund, the authors use monthly information on the number of investors and holdings' market value up to November 2020. The authors also use information on the total number of portfolio changes per day. For analyzing whether PPS investors reacted to the pandemic with claiming their pension, the authors use monthly data on the number of investors of a certain age group who initiate their public pension payment.

Trades more than doubled, and shifted capital from equity funds to low risk interest funds. In economic terms, however, trading stayed at low levels–less than two percent of investors traded in March 2020 and there was no effect on pension withdrawals. The increased trading during the market tumult was disproportionately concentrated among investors in the top of the pension capital distribution.

With fund-level data, the authors cannot investigate what in particular made retirement investors stay calm in the midst of a severe market decline. Either, those investors have a long-term investment horizon as they save for their pension or particular features of the system's choice architecture induce inertia and discourage from trading. The sub-group analyses are more consistent with the explanation that PPS-induced inertia is responsible for the relatively small increase in trading activity, but future research could exploit individual level data to explore this in more detail.

The often-criticized PPS choice architecture provided positive side effects in times of a severe market shock by shielding retail investors from committing trading mistakes when trying to outsmart the market.

The study complements previous evidence on the effects of COVID-19 on investor activity. The small response of PPS investors to COVID-19 is in line with earlier US findings on 401(k) accounts during the 2007 financial crisis (Tang et al., 2012) and industry reports about the COVID-19 period (see, e.g. Mitchell, 2020). The authors find no effects at all on public pension withdrawals in Sweden, while evidence from US 401(k) plans indicates a small share of workers taking COVID-related early withdrawals.

Testing a total of five hypotheses, the paper contributes to overall comparison of the two regimes, as it scrutinises whether these improvements have helped regulate this sector. Although it appears that, for the first time, International Financial Reporting Standards (IFRS) had a more timely effect than US Generally Accepted Accounting Principles (GAAP), multiple parameters must be taken into consideration. The banking system has additional rules that may affect financial statements, such as the Basel Accord which sets many policies closely related to the IFRS, such as deferred tax credits. In this way, this paper aim to enrich the results of these decisions, and illuminate aspects of amendments to IFRS and US GAAP in light of the crisis. Focussing on the financial sector, the author sought to critically evaluate their reactions, and to question some of their fundamental rules in practice. This is vital for accounting researchers and analysts, allowing for the first time to compare IFRS performance between Europe and the US, and make better investment evaluations.

The study sought to detect whether IFRS and US GAAP protected firms from abnormal sales arising from the outbreak of the crisis, whether the reclassification option under IFRS was an answer to the crisis, and whether IFRS and US GAAP succeeded in regulating shadow banking through their amendments. Therefore, it processes five hypotheses. In order to detect the effects of the crisis on accounting regimes, the analysis focused only on companies from the financial sector composed of the banking industry, insurance companies and shadow banking. The author included firms from Australia, Germany, Greece, the UK and the US, and collected information on 679 financial institutions for the period 2009–2013. The author settled on these time frames because the author aimed to capture IFRS performance surrounding the crisis effects in 2008 and the amendments that followed. In this way, the author applied quantitative methods using only numerical data over a given period.

The results suggest that the reclassification option was successful, helping firms to perform better amid the crisis, indicating that the manipulation of the crisis was appropriate. It seems therefore that US GAAP should have activated this option for US firms. However, the US may not have hurried to act because its banking sector seemed to recover more quickly than in Australia and Europe. Either way, both regimes need to consider speculative market cases that might have appeared during the crisis, as the author have detected cases of abnormal returns. Finally, concerning regulation of the shadow banking sector, the results seem to be encouraging only with regard to the latest improvements and only for all countries examined.

The project contributes to debate on the reactions of both IFRS and US GAAP during and after the economic crisis. For this, it addresses several questions to investigate the performance of the financial sector under both regimes, identifying possible additional effects and considerations. More specifically, it answers if the fair value orientation actually contributes to the financial crisis through contagion effects, while it addresses additional questions. Have these two global accounting regimes succeeded in overcoming the consequences of the crisis? Have amendments and the introduction of new standards to IFRS and US GAAP achieved regulation of shadow banking? Which of the two has performed better? As aforementioned, the analysis focused only on companies from the financial sector composed of the banking industry, insurance companies and shadow banking firms from Australia, Germany, Greece, the UK and the US, for the period 2009–2013.