Intraday Movements Research Articles

Prediction of Equities Basis Intraday Movement

Abstract: Data is a significant driver for several business decisions in this current era due to advent of big data and Stock markets are a great playground for deep learning and AI due to their high uncertainty. Although there are several tools in the market that aim to predict the future stock values with a prediction accuracy of almost 85%, none of them is fool proof and pave way and create scope for better accuracy. The current suite of tools predicts intraday buy /sell prices but are not capable of generating the pattern of day trade and stock swing, which when predicted, can generate 12X revenues for a full-time trader. The work focuses on the intraday trend and aims to predict the flow of Intraday trade, to gain larger profits and minimize losses in time in case of adverse conditions.

A granular machine learning framework for forecasting high-frequency financial market variables during the recent black swan event

This paper analyses highly voluminous 1-minute intraday movements of the closing prices of Bitcoin, crude oil, the Dow Jones Industrial Average (DJIA) and the euro–U.S. dollar exchange rate in various non-overlapping regimes spanning across the COVID-19 pandemic, a recent black swan event. The empirical characteristics of the intraday dynamics of chosen assets are gauged using nonlinear modelling tools and tests. The proposed methodological framework utilises maximal overlap discrete wavelet transformation, Bayesian structural time series forecasting and random walk with drift to evaluate the quantum of predictability of select variables in different phases across the pandemic horizon. The framework survives a series of performance and statistical checks to justify the efficacy of drawing highly accurate predictions from big data setups. The findings suggest that, despite chaotic traces, all variables can be precisely forecast across different sub-regimes, eliminating the adverse effects of the first and second waves of the COVID-19 pandemic. High-frequency movements of Bitcoin and Euro–U.S. dollar exchange rates are relatively better predictable, signifying resilience during the pandemic. Finally, the outcome of this research will help mitigate financial risk during volatile periods.

Early prediction of Ibex 35 movements

AbstractIn this paper, we examine the early predictability of the market's directional movement using intraday high‐frequency data (695,764 observations) from an stock index (Ibex 35 Index) to provide, either private or institutional investors, an early warning system based on an “early indicator” of the financial market fluctuations with an optimal combination of the two more relevant variables for this strategy, accuracy, and earliness. A novel supervised machine learning early classification technique (Artificial Intelligence) has been applied, for the first time, to the high‐frequency time series of both price and certain technical indicators.The results obtained allow us to assert that the intraday movement of the Ibex 35 can be predicted with acceptable levels of accuracy 24 min after the start of the session and to establish certain informative intraday hourly patterns. Consequently, different indicators of precision and earliness in the session are generated, obtaining that, after a certain point in the session, no gains in precision are generated.

A complex networks based analysis of jump risk in equity returns: An evidence using intraday movements from Pakistan stock market

We employ a multi-stage methodology combining complex network analytics and financial risk modelling to unveil the correlation structures amongst the price jump risks of companies forming the KSE-100 index in Pakistan. We identify the most influential companies in terms of jump risk, and identify communities — clusters of companies with similar price movement characteristics or with highly correlated price jumps. We find that equities in Pakistan stock market experience jumps in different time periods that are correlated to varying degrees within and across industries resulting in 19 different communities, four of which are strongly connected. While Oil & Gas, Cement and Banking sectors exhibit a significant representation of firms in communities, the automobile industry, however, seems to play an important role in risk propagation. These results provide an interesting insight to investors and other stakeholders from an emerging market viewpoint identifying the major sectors driving the volatility of KSE-100 index.

Forecaster Heterogeneity, Surprises and Financial Markets

We analyze the impact of US macroeconomic surprises and forecaster heterogeneity on the USD/EUR exchange rate and US and German long-term interest rates from 1999 to 2014. We show how a direct proxy of macroeconomic disagreement, given by the heterogeneity of beliefs among forecasters regarding the upcoming macroeconomic release, matters to explain the daily and intra-day movements. Surprises impact more strongly long-term yields and the exchange rate when forecaster heterogeneity is smaller. This result, holds for the main US macroeconomic surprises and is robust to the frequency of the data used in the estimation. However the sensitivity changes with the sample. To this end, we show how estimating the same regressions in a pre-crisis period, a crisis period, and an unconventional monetary policy period there is evidence of time variation in the responses: unconventional monetary policies attenuated the response of the exchange rate to US macroeconomic news, while no major change occurred for long-term interest rates in the US and in the euro area. The disagreement regimes remain relevant in determining an asymmetric response of these asset prices. Our finding underscores the importance of considering beliefs heterogeneity to describe the behavior of asset prices even at high frequency.

Foreign News and Spillovers in Emerging European Stock Markets

AbstractWe analyze foreign news and spillovers in the emerging EU stock markets (the Czech Republic, Hungary, and Poland). We employ high‐frequency five‐minute intraday data on stock market index returns and four classes of EU and US macroeconomic announcements during 2004–07. We account for the difference of each announcement from its market expectation and we jointly model the volatility of the returns accounting for intraday movements and day‐of‐the‐week effects. Our findings show that intraday interactions on the new EU markets are strongly determined by mature stock markets as well as the macroeconomic news originating thereby. We show that strong contemporaneous links across markets are present even after controlling for macroeconomic announcements. Finally, in terms of specific announcements, we are able to show the exact sources of macro news spillovers from the developed foreign markets to the three new EU markets under research.

The Effects of US Macroeconomic Surprises on the Intraday Movements of Foreign Exchange Rates: Cases of USD-EUR and USD-JPY Exchange Rates

This paper characterizes the intraday dynamics of the high frequency US Dollar (USD)–Euro (EUR) and US Dollar (USD)–Japanese Yen (JPY) foreign exchange rates that have been subject to macroeconomic fundamentals. Even though the FIGARCH model with a normality assumption is found to be a good starting point, it appears to be inappropriate to represent the underlying movements of the high frequency returns due to the occurrences of jumps. Hence, this paper relies on the FIGARCH model with the mixture distribution that allows for the time-varying jumps that are determined by the US macroeconomic surprises. This paper generally finds that the US macroeconomic surprises are closely related to the intraday movements in the volatility process of the high frequency returns process through the jumps. In particular, the US macroeconomic surprises appear to affect the movements in the volatility process of the foreign exchange rates asymmetrically depending on the signs of the surprises and spuriously increasing the long memory persistence in the volatility process due to the jumps.

Foreign News and Spillovers in Emerging European Stock Markets

We analyze foreign news and spillovers in the emerging EU stock markets (the Czech Republic, Hungary, and Poland). We employ high-frequency five-minute intraday data on stock market index returns and four classes of EU and U.S. macroeconomic announcements during 2004–2007. We account for the difference of each announcement from its market expectation and we jointly model the volatility of the returns accounting for intraday movements and day-of-the-week effects. Our findings show that intraday interactions on the new EU markets are strongly determined by mature stock markets as well as the macroeconomic news originating thereby. We show that strong contemporaneous links across markets are present even after controlling for macroeconomic announcements. Finally, in terms of specific announcements, we are able to show the exact sources of macro news spillovers from the developed foreign markets to the three new EU markets under research.

Intraday Price Discovery in Emerging European Stock Markets

We characterize the price discovery in three emerging EU stock markets — the Czech Republic, Hungary, and Poland — by employing high-frequency five-minute intraday data on stock market index returns and four classes of EU and U.S. macroeconomic announcements during 2004–2007. We account for the difference of each announcement from its market expectation and we jointly model the volatility of the returns accounting for intra-day movements and day-of-the-week effects. Our findings show that real-time interactions on the new EU markets are strongly determined by matured stock markets as well as the macroeconomic news originating thereby. Monetary news has virtually no impact on stock returns while U.S. prices affect all three markets. The real economy announcements have varying effects but the news on the EU current account affects all three markets in a uniform manner. Only some EU economic climate and confidence announcements affect stock returns. In general, differences in results across markets are driven by differences in key market participants. Volatility of the returns is accounted for at the beginning and end of the trading session and it declines dramatically during the rest of the day. All three markets also show a decrease in volatility by the middle of the business week. Our findings yield insights into the process of stock market integration in the EU as well as portfolio allocation on the new EU markets.

Intraday stock returns and performance of a simple market model

With enhancements in information technology, increased institutional and automated trading, and previously unmatched availability of online trading grew the attention to intraday movements of security prices and tests associated with them. This study analyses the properties of both observed 5-minute stock returns and of excess returns obtained by using a variety of alternative models common to event studies. Using observed 5-minute returns, various event study methodologies are simulated and repeatedly applied to samples which have been created by random selection of securities and random assignment of event dates to each security. The study examines the probability of rejecting the null hypothesis of no average abnormal performance when it is true and the probability of detecting a given abnormal performance, which is introduced to the data at the randomly selected event dates.

A duscrete-time model of high-frequency stock returns

A model of intraday financial time series is developed. The model is a dynamic factor model consisting of two equations. First, a rate of return of a ‘stock’ in a single day is assumed to be generated by serveral common factors plus some additive erros (‘intraday equation’). Secondly, the joint distribution of those common factors is assumed to depend on the hidden state of the day, which fluctuates according to a Markov chain (‘day-by-day equation’). Together the equations compose a hidden Markov model. We investigate properties of the model. Among them is a central limit theorem for cumulative returns, which agrees with the well-known empirical phenomenon in the stock markets that the distributions of longer-horizon returns are closer to the normal. We propose a two-step procedure consisting of the method of principal components and the EM algorithm to estimate the model parameters as well as the unboservable states. In addition, we propose a procedure for predicting intraday returns. Finally, the model is fitted to empirical data, the Standard&Poors 500 Index 5 min return data, to see if the model is capable of describing intraday movements of the index.

Using Daily High/Low Time to Test for Intraday Random Walk in Two Index Futures Markets

This paper investigates the time of the daily high/low price in the Hang Seng and S&P 500 index futures and uses it to test for deviation from the predictive behavior of an intraday random walk model. Theoretical distributions of the daily high/low time under the random walk model are derived assuming either uniform or time-varying intraday trading speed. We show that under a random walk model, daily high/low time is more likely to occur near market open/close than in the middle of the trading day. Empirical distributions of the daily high/low time are compared with its theoretical distributions to test for the random walk model. It is found that for the intraday movement of the S&P 500 futures, the random walk hypothesis cannot be rejected. However, it is discovered that in the Hong Kong market, daily high/low time tends to appear significantly more often than is predicted by the random walk model in the first 15-minute time interval when the market opens in the morning or in the afternoon. The results remain valid even after we have taken the time-varying trading speed into account. By comparing the price behavior across markets, we can better understand the microstructure of the futures market.

Stochastic properties and predictability of intraday Taiwan exchange rates

This study explores the time-series properties and predictability of intraday movements in the Taiwan exchange rates with respect to its most important trading partner, the United States, using the EGARCH-M model along with the generalized error distribution (GED), allows for variable kurtosis in the data. The study (1) examines whether the Martingale hypothesis of no predictability remains appropriate at the intraday level; (2) tests whether the more general GED, which can account for varying degrees of skewness and kurtosis, provides a better representation of the stochastic behavior of the intraday Taiwan exchange rate series than the normal distribution; (3) addresses the issue of whether knowledge of the trading hour provides incremental information that is useful for forecasting intraday movements of the exchange rate; (4) investigates whether intraday movements in the new Taiwan dollar (NT) are positively (or negatively) influenced by their conditional standard deviations; and (5) tests for the presence of asymmetric volatility in the intraday data. In our experiment, the Martingale hypothesis is rejected at the intraday level and the distribution of the intraday NT/U.S. dollar exchange rate is found to be highly leptokurtic relative to the normal distribution. The GED appears to provide a better characterization of the leptokurtic distribution than the normal distribution. Also, knowledge of the trading hour is shown to provide incremental information that is useful for forecasting intraday movements of the exchange rate. There is evidence to suggest that the conditional standard deviation negatively influences future intraday movements of the NT/U.S. dollar exchange rate. Only weak evidence for asymmetric volatility in the intraday data is found.