Historical Price Movements Research Articles

Classification of Stock Price Using Fundamental and Technical Analysis

Investors who want to make well-informed decisions face problems due to the constantly shifting nature of financial markets. Pattern identification becomes more difficult when analyzing high-dimensional data because quality patterns become more complex. Various machine learning approaches are frequently used in this complex situation to efficiently anticipate and categorize future data. However, customizing a computer for a particular portion of the dataset usually comes at a high cost. This study suggests a deep learning method to recognize various price patterns in the stock market by utilizing long short-term memory (LSTM) networks. LSTM networks are superior to conventional methods in capturing temporal dependencies and patterns in time-series data, as they may not require as much training cost for certain dataset segments. A thorough review of a company's data and economic indicators is part of the fundamental analysis component of the study. Technical analysis is also used to look at trading volumes, historical price movements, and different technical indicators. It aims to get over the limitations of traditional approaches by using LSTM model capabilities to find periodic relationships and patterns in stock market data. Keywords : LSTM, Stock Patterns, Machine Learning, Stock Prediction, Technical Analysis

The Impact of Gold, Oil Prices, and their Associated Implied Volatilities on Performance of Pakistan’s Stock Market

This study examined the asymmetrical implications of gold and oil prices, as well as the implied volatility that goes along with them, on the performance of Pakistan's stock market. It was used Chicago Board of Options Exchange’s GVZ and OVX index for measuring volatility in gold market and oil market respectively due to more uncertainty in commodity markets and also took historical price movements, investor’s expectations regarding global prices into account. The monthly data used from October 2009 to January 2023. An ARDL approach was employed for checking short term and long term asymmetrical. The results of ARDL revealed that oil volatility index have significant impact of Pakistan’s stock market in short-run and long-run. The Gold Volatility Index shows significant impact after one month on both stock market capitalization and KSE 100 indexes in the short run. Fluctuations in worldwide commodity prices have a significant influence on underdeveloped economies like Pakistan and have a negative effect on the entire economy. The volatility and fluctuations in oil prices lead to higher production costs, which create uncertainty in companies' cash flows.

A multivariate LSTM-based deep learning model for stock market prediction

Stocks represent ownership in a company and a proportionate claim on its assets and earn-ings. Investors trade stocks via an exchange by buying at a price and selling at a higher price. Due to market volatility forecast it is a necessity for trading to determine the direc-tion of the stock price in order to maximize profit and minimize loss. Traditional methods of stock price predictions include technical and fundamental analysis. The technical deals with historical price movement while fundamental analysis uses the relationship between financial information about the company. However, these predictions methods sometimes fail to yield desired result sometimes due to the influence of factors such as national poli-cies, global and regional economics, psychological, human among many. This work propos-es a prediction model for stock market using LSTM algorithm. Multivariate time series stock price data is obtained from Nigerian Stock Exchange Index to implement the model. The experimental result of the technique is measured using MAPE, MAE, MSE and rRMSE performance metrics. The accuracy of the result shows that the proposed system outper-forms existing traditional and deep learning methods.

Price Dynamics and Interactions between the Chinese and European Carbon Emission Trading Markets

The European carbon emission trading market is the largest and most mature market, while China’s carbon market has a short history. Institutionally, cross-market transaction is infeasible between the two markets. This paper investigates the long-run trend between the two markets as well as the price dynamics. Results show that a long-run trend exists between the Chinese and European carbon markets. Both markets possess self-correction capability in reducing price deviations, signaling a certain level of market efficiency. However, both markets also exhibit pricing inefficiency as historical price movements are able to impact prices. The European market informationally leads the Chinese market. Policy implications are that China should further upgrade its information disclosure system, such as unifying information disclosure standards across industries, and further develop its carbon derivatives markets to improve market transparency and market competition.

Stock Price Prediction Using Machine Learning

In Stock Market Prediction, the aim is to predict for future value of the financial stocks of a company. The recent trend in stock market prediction technologies is the use of machine learning which makes predictions based on the values of current stock market by training on their previous values. Machine learning itself employs different models to make prediction easier. The paper focuses on Regression and LSTM based Machine learning to predict stock values. Factors considered are open, close, low, high and volume. In order to predict market movement, the stock prices and stock indicators in addition to the news related to these stocks. Most of the previous work in this industry focused on either classifying the released market news and demonstrating their effect on the stock price or focused on the historical price movement and predicted their future movement. In this work, we propose an automated trading system that integrates mathematical functions, machine learning, and other external factors such as news’ sentiments for the purpose of a better stock prediction accuracy and issuing profitable trades. The aim to determine the price of a certain stock for the coming end-of-day considering the first several trading hours of the day.

Etkin Piyasa Hipotezinin Geçerliliği: G7 Ülkeleri Örneği

Bu çalışmanın amacı Fama’nın ortaya koyduğu etkin piyasa hipotezinin geçerliliğinin G7 ülkeleri için incelenmesidir. Bu doğrultuda, zayıf formada etkinlik testi 1990-2020 dönemi için G7 ülkeleri kapsamında durağan olmayan panel birim kök testleri yardımıyla yapılmıştır. Öncelikle serilerde yatay kesit bağımlılığı CD lm testi ile incelenmiştir. Yatay kesit bağımlığının varlığı sonucunda yatay kesit bağımlılığını dikkate alan CADF ve Hadri Kurozumi ikinci nesil durağan olmayan panel birim kök testlerinden yararlanılmıştır. Elde edilen ampirik bulgular doğrultusunda G7 ülkelerinde piyasaların zayıf formda etkin olduğu sonucuna ulaşılmıştır. Bu sonuca göre herhangi bir finansal varlığın geçmişteki sahip olduğu tüm bilgiler finansal varlığın fiyatına yansımaktadır ve herhangi bir finansal aracın geçmişteki fiyat hareketine bakarak gelecekteki fiyatını belirlemek mümkün değildir. Rassal yürüyüşe sahip olan zayıf formda etkin piyasalarda finansal varlık fiyatlarının durağan olmaması, gelecekteki finansal varlık piyasalarının geçmiş fiyatlara dayalı olarak tahmin edilemeyeceği anlamına gelir.Anahtar Kelimeler: Etkin Piyasa Hipotezi, Panel Veri Analizi, Panel Birim Kök Testi.JEL Sınıflandırması: C23, F30, F37

Hisse Senedi Piyasalarının Zayıf Form Piyasa Etkinliğinin Küresel Ölçekte Karşılaştırılması: G-20 Üyeleri Üzerine Ampirik Bir Çalışma

This paper analyzes stock markets of G-20 members in terms of comparing return predictability, in other words, weak-form market efficiency using stock indexes weekly data of the G-20 members between 07.06.2009 and 09.02.2020. As a result of the wild bootstrap automatic variance ratio test analysis developed by Kim (2009), it is found that the stock markets of Brazil, South Africa, and Germany were weak-form efficient in the date range within the scope of the study, so the returns are unpredictable, while the weak-form efficiency (return predictability) of other markets are time-varying. In addition to Brazil, South Africa, and Germany, there is a very low chance to estimate returns with historical price movements or returns in Russia, France, Italy, United States, United Kingdom, and Canada stock markets. It is also found that the return predictability periods of Japan, Australia, China, Saudi Arabia, and especially Mexico’s stock markets are higher than other markets and the chance of success in estimating returns by using historical price information in these markets is quite high.

Speculative trading in Chinese housing market: a panel regression method

ABSTRACT The major Chinese cities experienced dramatic increases in their house prices in the recent years. This paper derives the fundamental value of the housing markets based on the personal disposable income of individual cities. By controlling macroeconomic variables and government intervention, we detect speculative trading based on fundamental value and historical price movements. Fundamentalists expect house prices to converge to the fundamental values while chartists hold a momentum trading expectation. Further differentiating the cities into tier-1 and non-tier-1, the non-tier-1 cities are found to be subject to a risk of plummeting arising from the interaction terms between the fundamentalists and chartists.

Recommending Cryptocurrency Trading Points with Deep Reinforcement Learning Approach

The net profit of investors can rapidly increase if they correctly decide to take one of these three actions: buying, selling, or holding the stocks. The right action is related to massive stock market measurements. Therefore, defining the right action requires specific knowledge from investors. The economy scientists, following their research, have suggested several strategies and indicating factors that serve to find the best option for trading in a stock market. However, several investors’ capital decreased when they tried to trade the basis of the recommendation of these strategies. That means the stock market needs more satisfactory research, which can give more guarantee of success for investors. To address this challenge, we tried to apply one of the machine learning algorithms, which is called deep reinforcement learning (DRL) on the stock market. As a result, we developed an application that observes historical price movements and takes action on real-time prices. We tested our proposal algorithm with three—Bitcoin (BTC), Litecoin (LTC), and Ethereum (ETH)—crypto coins’ historical data. The experiment on Bitcoin via DRL application shows that the investor got 14.4% net profits within one month. Similarly, tests on Litecoin and Ethereum also finished with 74% and 41% profit, respectively.

Dynamics of the European sovereign bonds and the identification of crisis periods

We develop an empirical model of heterogeneous agents to study the dynamics of the European sovereign bonds market. Agents make use of different information from the CDS market and historical price movements of the sovereign bonds for their trading decisions. Subject to the perceived sovereign risk, agents exhibit changing trading behaviors in high-risk periods and tranquil times. To compare the ability of our model to identify crises periods, we also run a generalized sup ADF test as suggested in Phillips et al. (Int Econ Rev 56(4):1043–1078, 2015). Our results indicate that the smooth transition regression framework may provide additional valuable information regarding the timing of crisis events.

Systemic risk network of Chinese financial institutions

The Chinese stock market crash in June 2015 has demonstrated necessary to improve understanding of systemic risk from the perspective of financial network. This study constructs a tail risk network to present overall systemic risk of Chinese financial institutions, given the macroeconomic and market externalities. Employing the Least Absolute Shrinkage and Selection Operator (LASSO) method of high-dimensional models, our results show that firm's idiosyncratic risk can be affected by its connectedness with other institutions. The risk spillover effect from other companies is the main driving factor of firm-specific risk, comparing with macroeconomic state, firm characteristics and historical price movement. The number of connections between institutions significantly increases during June 2014 to June 2016. Moreover, we utilize the Kolmogorov-Smirnov statistic to test significance of systemic risk beta based on tail risk and further rank the systemic risk contribution. Finally, we test the determinants of systemic risk contribution in a forward-looking way. Regulators could detect those firms that are most threatening to the stability of system.

Systemic Risk Network of Chinese Financial Institutions

The Chinese stock market crash in June 2015 has demonstrated necessary to improve understanding of systemic risk from the perspective of financial network. This study constructs a tail risk network to present overall systemic risk of Chinese financial institutions, given the macroeconomic and market externalities. Employing the Least Absolute Shrinkage and Selection Operator (LASSO) method of high-dimensional models, our results show that firm’s idiosyncratic risk can be affected by its connectedness with other institutions. The risk spillover effect from other companies is the main driving factor of firm-specific risk, comparing with macroeconomic state, firm characteristics and historical price movement. The number of connections between institutions significantly increases during June 2014 to June 2016. Moreover, we utilize the Kolmogorov-Smirnov statistic to test significance of systemic risk beta based on tail risk and further rank the systemic risk contribution. Regulators could detect those firms that are most threatening to the stability of system.

Measuring Price Risk in Rating Revenue Coverage: BS or No BS?

AbstractThe Black‐Scholes (BS) option pricing model has been a cornerstone of modern financial theories since its introduction by Black and Scholes (1973) and its subsequent refinement by Merton (1973). The model has realized widespread adoption for a number of purposes. Inherent in the model are a number of assumptions. An important and potentially restrictive assumption is that the underlying asset price is log–normally distributed. Among the many diverse uses of the BS model, the model and underlying theory are used to derive measurements of the variance of expected (harvest‐time) prices for use in rating revenue coverage in the federal crop insurance program. Revenue coverage currently accounts for about 80% of the total liability insured in the program. This liability frequently exceeds $100 billion and thus the accuracy of revenue premium rates is of vital importance. The use of the BS model by the Risk Management Agency (RMA) of the USDA has been the focus of recent criticisms of the program. Critics have argued in favor of retrospective measures of price variability that are based on historical price movements or have recommended other approaches to measuring price risk. This article reports on a contracted review of revenue insurance rating methodology commissioned by RMA. We evaluate a number of alternative approaches to measuring expected price variability, including several approaches recommended by critics of the federal program. Our results suggest that the BS model is preferred to recommended alternatives on the basis of numerous criteria.

Cyclical non-stationarity in commodity prices

This paper applies the Hylleberg et al. (J Econom 44(1):215–238, 1990) parametric seasonal unit root test to test for cyclical non-stationarity in commodity prices. The testing procedure is simple and involves evaluating various linear restrictions on lagged price levels in an error correction model of prices, equivalent to the Augmented Dickey–Fuller test. Unit root behaviour at low frequencies implies cyclical non-stationarity. In our empirical application, we fail to reject unit roots at frequencies associated with 3- to 5-year-long price cycles for 7 of 16 major commodities. Our results suggest that longer cycles in many commodity prices are highly stochastic, and care should be taken when interpreting the regularity and out-of-sample predictability of such cycles using historical price movements.

Have We Learned from Previous Stock Meltdowns?

We have witnessed three major stock market meltdowns over the past three decades. This paper assesses the market shocks of 1987, 1997 and 2008. In particular, we review the history of modern finance and assess whether the role of quantitative finance has developed to reduce the likelihood of future meltdowns. We see that the role of models based on historical price movement often ignore the possibility of fat tails, that risk free arbitrage may exist in normal, but not tumultuous markets and that asset returns and correlations result in extreme values more frequently than predicted by the standard bell curve. Moreover, the desire for outsized returns has driven many money managers to leverage their returns beyond prudent levels, dramatically increasing portfolio risk. In addition, many in Wall Street sell and create new derivative products that are often sold without the necessary due diligence and properly conducted stress tests. The same quantitative courses are taught and similar derivative products are sold as during the three previous meltdowns. Unfortunately, the SEC and academia have taken little permanent action to reduce the odds of further stock meltdowns.

Simple stochastic order-book model of swarm behavior in continuous double auction

In this study, we present a simple stochastic order-book model for investors’ swarm behaviors seen in the continuous double auction mechanism, which is employed by major global exchanges. Our study shows a characteristic called “fat tail” seen in the data obtained from our model that incorporates the investors’ swarm behaviors. Our model captures two swarm behaviors: one is investors’ behavior to follow a trend in the historical price movement, and another is investors’ behavior to send orders that contradict a trend in the historical price movement. In order to capture the features of influence by the swarm behaviors, from price data derived from our simulations using these models, we analyzed the price movement range, that is, how much the price is moved when it is continuously moved in a single direction. Depending on the type of swarm behavior, we saw a difference in the cumulative frequency distribution of this price movement range. In particular, for the model of investors who followed a trend in the historical price movement, we saw the power law in the tail of the cumulative frequency distribution of this price movement range. In addition, we analyzed the shape of the tail of the cumulative frequency distribution. The result demonstrated that one of the reasons the trend following of price occurs is that orders temporarily swarm on the order book in accordance with past price trends.

Pengujian Efisiensi Dan Peningkatan Efisiensi Bentuk Lemah Bursa Efek Indonesia Pada Saat Dan Sesudah Krisis Moneter Pada Saham-Saham LQ-45

Efficient markets can be classified into three forms: weak, semi-strong, and strong. Weak-form efficiency suggests that security prices reflect all trade-related information, such as historical security price movements and volume of securities trades, so they don’t relate with current price and volume. In other words, historical price movements independent or random over time. Thus, test of weak-form efficiency is ralated with random walk theory. This research has two objectives. The first objective is to analyze whether Indonesian capital market has been efficient (weak-form). The second one is to analyze increasing efficient market in two different periode. The study was carried out on the 10 stock in the LQ-45 index, based on crisis and after crisis during 1998 and 2006 period. The first objective was analyzed by using run and autocorrelation test. The result shows that most stock are random in two different period. The second one was analyzed by searching number stocks that is random in crisis and after crisis period. The result shows there is not increasing weak-form efficiency

The Establishment of the Forecasting Model for Regime Switching in Time Series

Efficient market hypothesis implies that the past price movements do not help forecast future price movements. Thus, it is impossible to consistently benefit by a technical trading strategy. On the other hand, technical analysts claim that the historical price movements are useful in predicting future price movements. These two lines of arguments are mutually contradictory. This paper reasonably assumes that the more efficient markets are, the worse will be the investment performance of technical analysis, and that as financial market‘s trading volume grows and with the elapse of time, the efficiency of markets should improve. This implies that after the launch of a new financial asset, market efficiency would improve with increased trading and elapsed time. In this paper, the duration analysis technique is used as a forecasting model and applied to measure the efficiency of Korean futures market and the won/dollar exchange rate market.

European Price Momentum and Analyst Behavior

Previous studies have found evidence that selecting stocks with positive price momentum is effective in the U.S., European, and emerging stock markets for periods up to a year. The reasons that historical price momentum forecasts the direction and magnitude of stock returns, however, are not clear. Insight into the determinants of price momentum would allow investors to judge whether and how price momentum should play a role in their investment strategies. Studying the European stock markets, we found that positive price momentum is caused by analyst underreaction to new earnings information. We found earnings surprises, expected earnings growth, and earnings revisions to be systematically related to historical price movements. Importantly, the data show that European price momentum is distinct from the widely documented value and size effects. Our findings clarify the benefits of assessing analyst behavior to predict whether momentum investing might work in the next period.

Forecasting stock market prices in a thin security market

Stock market efficiency is a crucial concept when forecasting of future stock price behaviour is discussed. In the literature, a distinction is made between three potential levels of efficiency. Under a weak form of efficiency, information on historical price movements is of no value for predicting the future price development. Similarly, a semi-strong form of efficiency holds that no publicly available information can be successfully used in the prediction of prices. And finally, a strong form of efficiency means that the share prices fully reflect all relevant information including data not yet publicly available. Stock market efficiency has been extensively studied in different countries. On a thin security market, like in the Helsinki Stock Exchange, many anomalies and deviations from market efficiency have been obtained. This paper aims to contribute to that discussion. It is shown in the paper that both the monthly and quarterly stock market prices (the general stock market index) can be adequately forecasted using either univariate time-series analysis or multivariate econometric modelling. The univariate ARIMA-models seem to be slightly outperformed by the econometric models. It is further shown that the forecasting accuracy of the models can be improved when time-series and econometric forecasts are combined into a composite forecast. The empirical results obtained indicate an absence of efficiency on the Finnish security market.