A predictive system integrating intrinsic mode functions,artificial neural networks,and genetic algorithms for forecasting S&P500 intra‐day data

There is an abundant literature on the design of intelligent systems to forecast stock market indices. In general, the existing stock market price forecasting approaches can achieve good results. The goal of our study is to develop an effective intelligent predictive system to improve the forecasting accuracy. Therefore, our proposed predictive system integrates adaptive filtering, artificial neural networks (ANNs), and evolutionary optimization. Specifically, it is based on the empirical mode decomposition (EMD), which is a useful adaptive signal‐processing technique, and ANNs, which are powerful adaptive intelligent systems suitable for noisy data learning and prediction, such as stock market intra‐day data. Our system hybridizes intrinsic mode functions (IMFs) obtained from EMD and ANNs optimized by genetic algorithms (GAs) for the analysis and forecasting of S&P500 intra‐day price data. For comparison purposes, the performance of the EMD‐GA‐ANN presented is compared with that of a GA‐ANN trained with a wavelet transform's (WT's) resulting approximation and details coefficients, and a GA‐general regression neural network (GRNN) trained with price historical data. The mean absolute deviation, mean absolute error, and root‐mean‐squared errors show evidence of the superiority of EMD‐GA‐ANN over WT‐GA‐ANN and GA‐GRNN. In addition, it outperformed existing predictive systems tested on the same data set. Furthermore, our hybrid predictive system is relatively easy to implement and not highly time‐consuming to run. Furthermore, it was found that the Daubechies wavelet showed quite a higher prediction accuracy than the Haar wavelet. Moreover, prediction errors decrease with the level of decomposition.     

Deep networks for predicting direction of change in foreign exchange rates

Trillions of dollars are traded daily on the foreign exchange (forex) market, making it the largest financial market in the world. Accurate forecasting of forex rates is a necessary element in any effective hedging or speculation strategy in the forex market. Time series models and shallow neural networks provide acceptable point estimates for future rates but are poor at predicting the direction of change and, hence, are not very useful for supporting profitable trading strategies. Machine learning classifiers trained on input features crafted based on domain knowledge produce marginally better results. The recent success of deep networks is partially attributable to their ability to learn abstract features from raw data. This motivates us to investigate the ability of deep convolution neural networks to predict the direction of change in forex rates. Exchange rates for the currency pairs EUR/USD, GBP/USD and JPY/USD are used in experiments. Results demonstrate that trained deep networks achieve satisfactory out‐of‐sample prediction accuracy.     

HIGH‐FREQUENCY EXCHANGE‐RATE PREDICTION WITH AN ARTIFICIAL NEURAL NETWORK

This paper examines how market microstructure variables can be used to forecast foreign exchange (FX) rates at frequencies of one to several minutes. We use a unique FX dataset of global inter‐dealer electronic transactions and applied the artificial neural network (ANN) as the predicting model. The immediately preceding bid and ask prices are significant factors in these predictions, which is in keeping with market microstructure theory. These microstructure factors have not been tested in an ANN model before. High‐frequency trading strategies based on the ANN model are shown to be profitable even when transaction costs are included. Copyright © 2012 John Wiley & Sons, Ltd.     

Stock price prediction using DEEP learning algorithm and its comparison with machine learning algorithms

Security indices are the main tools for evaluation of the status of financial markets. Moreover, a main part of the economy of any country is constituted of investment in stock markets. Therefore, investors could maximize the return of investment if it becomes possible to predict the future trend of stock market with appropriate methods. The nonlinearity and nonstationarity of financial series make their prediction complicated. This study seeks to evaluate the prediction power of machine‐learning models in a stock market. The data used in this study include the daily close price data of iShares MSCI United Kingdom exchange‐traded fund from January 2015 to June 2018. The prediction process is done through four models of machine‐learning algorithms. The results indicate that the deep learning method is better in prediction than the other methods, and the support vector regression method is in the next rank with respect to neural network and random forest methods with less error.     

Time series analysis for financial market meltdowns

There appears to be a consensus that the recent instability in global financial markets may be attributable in part to the failure of financial modeling. More specifically, it is alleged that current risk models have failed to properly assess the risks associated with large adverse stock price behavior. In this paper, we first discuss the limitations of classical time series models for forecasting financial market meltdowns. Then we set forth a framework capable of forecasting both extreme events and highly volatile markets. Based on the empirical evidence presented in this paper, our framework offers an improvement over prevailing models for evaluating stock market risk exposure during distressed market periods.     

Making trading decisions for financial‐engineered derivatives: a novel ensemble of neural networks using information content

Over the last decades, there has been a growing interest in applying artificial intelligence techniques to solve a spectrum of financial problems. A number of studies have shown promising results in using artificial neural networks (ANNs) to guide investment trading. Given the expanding role of ANNs in financial trading, this paper proposes the use of a hybrid neural network, which consists of two independent ANN architectures, and comparatively evaluates its performance against independent ANNs and econometric models in the trading of a financial‐engineered (synthetic) derivative composed of options on foreign exchange futures. We examine the financial profitability and the market timing ability of the competing neural network models and statistically compare their attributes with those based on linear and nonlinear statistical projections. A random walk model and the option pricing method are also included as benchmarks for comparison. Our empirical investigation finds that, for each of the currencies analysed, trading strategies guided by the proposed dual network are financially profitable and yield a more stable stream of investment returns than the other models. Statistical results strengthen the notion that diffusion of information contents and cross‐validation between the independent components within the dual network are able to reduce bias and extreme decision making over the long run. Moreover, the results are robust with respect to different levels of transaction costs. Copyright © 2009 John Wiley & Sons, Ltd.     

TSFDC: A trading strategy based on forecasting directional change

Directional Change (DC) is a technique to summarize price movements in a financial market. According to the DC concept, data is sampled only when the magnitude of price change is significant according to the investor. In this paper, we develop a contrarian trading strategy named TSFDC. TSFDC is based on a forecasting model which aims to predict the change of the direction of market's trend under the DC context. We examine the profitability, risk and risk‐adjusted return of TSFDC in the FX market using eight currency pairs. The results suggest that TSFDC outperforms the buy and hold approach and another DC‐based trading strategy.     

Episodic Liquidity Crises: Cooperative and Predatory Trading

We describe how episodic illiquidity arises from a breakdown in cooperation between market participants. We first solve a one‐period trading game in continuous‐time, using an asset pricing equation that accounts for the price impact of trading. Then, in a multi‐period framework, we describe an equilibrium in which traders cooperate most of the time through repeated interaction, providing apparent liquidity to one another. Cooperation breaks down when the stakes are high, leading to predatory trading and episodic illiquidity. Equilibrium strategies that involve cooperation across markets lead to less frequent episodic illiquidity, but cause contagion when cooperation breaks down.     

Persistence and Predictability in UK House Price Movements

This paper extends the analysis of predictability and persistence of inflation-adjusted house price movements in the UK housing market both on a regional level across 13 regions and on a nationwide level. Applying a univariate time series approach, the results from the quarterly transaction-based Nationwide Building Society indices from 1974 to 2009 provide empirical evidence for a high persistence of house price movements. In addition to conducting parametric and non-parametric tests, we provide technical trading strategies as a robustness check to compare predictability across markets and to test whether or not the detected persistence can also be used for detecting turning points in the market. The empirical findings from the technical trading strategies support the results from the statistical tests. Moving average-based trading strategies perform extremely well in the southern regions, while trading strategies are less profitable for the northern regions and Wales. Thus, from an investors’ perspective, there are excess real returns from moving average-based strategies compared to a buy-and-hold strategy for most regional markets. From a household perspective, the findings support the importance of derivative markets where households could hedge their risk exposure from being homeowner.     

An evolutionary multi‐objective optimization of trading rules in call markets

We evaluate an agent‐based model featuring near‐zero‐intelligence traders operating in a call market with a wide range of trading rules governing the determination of prices and which orders are executed, as well as a range of parameters regarding market intervention by market makers and the presence of informed traders. We optimize these trading rules using a multi‐objective population‐based incremental learning algorithm seeking to maximize the trading volume and minimize the bid–ask spread. Our results suggest that markets should choose a small tick size if concerns about the bid–ask spread are dominating and a large tick size if maximizing trading volume is the main aim. We also find that unless concerns about trading volume dominate, time priority is the optimal priority rule. Copyright © 2011 John Wiley & Sons, Ltd.     

Limited information limits accuracy: Whether ensemble empirical mode decomposition improves crude oil spot price prediction?

A reliable crude oil price forecast is important for market pricing. Despite the widespread use of ensemble empirical mode decomposition (EEMD) in financial time series forecasting, the one-time decomposition on the entire time series leads the in-sample data to be affected by the out-of-sample data. Consequently, the forecasting accuracy is overstated. This study incorporates a rolling window into two prevalent EEMD-based modeling paradigms, namely decomposition-ensemble and denoising, to ensure that only in-sample time series is processed by EEMD and used for model training. Given the time-consuming process of stepwise preprocessing and model fitting, two non-iterative machine learning algorithms, random vector functional link (RVFL) neural network and extreme learning machine (ELM), are used as predictors. Hence, we develop the rolling decomposition-ensemble and rolling denoising paradigms, respectively. Contrary to the majority of prior studies, empirical results based on monthly spot price time series for the Brent and West Texas Intermediate (WTI) markets indicate that EEMD plays a weak role in improving crude oil price forecasts when only the in-sample set is preprocessed. This is compatible with the weak form of the efficient market hypothesis (EMH). Nevertheless, the suggested rolling EEMD-denoising model has an advantage over other employed models for long-term forecasting.     

Does fair value accounting contribute to market price volatility? An experimental approach

This paper contributes to the debate on the impact of accounting measurement rules for financial assets. We examine the association between fair value accounting for financial assets and market price volatility for nonfinancial firms in an experimental setting. One group of participants was provided with financial statements where held‐for‐trading securities were reported at fair market value (FVA). Another group received financial statements with investments reported at historical cost (HCA). Controlling for accounting data, we find no systematic difference between FVA and HCA for three different measures of market price volatility, despite higher earnings volatility and marginally heavier trading under FVA.     

Is momentum a self-fulfilling prophecy?

The author shows in a simple framework that momentum trading can exist in equilibrium and that momentum trading is profitable. A property of the model is that the relation between risk, reward, and the intensity of momentum trading provides a natural limit to the amount of momentum trading that will exist in equilibrium. Properties of the model fit the empirics well. First, the model captures in a parsimonious manner both short-term overreaction and long-term reversals. Second, it predicts that momentum and long-term reversals should be observed in any market where there is noise. Thus, the model gives theoretical support to the empirical evidence that these anomalies are not artifacts of data snooping and to the extant empirical evidence that these anomalies are pervasive. Momentum traders observe noise shocks and trade on it as information. This trading incorporates a predictive role to the noise. That is, if agents believe a past price change to be informative of future price changes and act on this belief, it will be true and trading on this belief will be profitable. Thus, momentum trading is a self-fulfilling action.     

On the intraday return curves of Bitcoin: Predictability and trading opportunities

Motivated by the potential inferences from intraday price data in the controversial Bitcoin market, we apply functional data analysis techniques to study cumulative intraday return (CIDR) curves. First, we indicate that Bitcoin CIDR curves are stationary, non-normal, uncorrelated, but exhibit conditional heteroscedastic, although we find that the projection scores of CIDR curves could be serially correlated during some certain periods. Second, we show the possibility of predicting the CIDR curves of Bitcoins based on the projection scores and then assess the forecasting performance. Finally, we utilize the functional forecasting methods to explore the intraday trading opportunities of Bitcoins and the results provide evidence of profitable trading opportunities based on intraday trading strategies, which confronts the efficient market hypothesis.     

An analysis of commodity markets: What gain for investors?

In this paper we study whether the commodity futures market predicts the commodity spot market. Using historical daily data on four commodities—oil, gold, platinum, and silver—we find that they do. We then show how investors can use this information on the futures market to devise trading strategies and make profits. In particular, dynamic trading strategies based on a mean–variance investor framework produce somewhat different results compared with those based on technical trading rules. Dynamic trading strategies suggest that all commodities are profitable and profits are dependent on structural breaks. The most recent global financial crisis marked a period in which commodity profits were the weakest.     

Interim Reporting Frequency and Financial Analysts' Expenditures

This paper relates interim financial reporting frequency in a multiperiod Kyle framework to securities prices, trading volume, market liquidity, and analysts' information acquisition expenditures. The model supports conventional wisdom that more frequent interim reporting improves the information content of securities prices, reduces reporting day price volatility and trading volume, and enhances market liquidity. However , the model suggests that more frequent financial reporting induces analysts to increase their redundant information acquisition expenditures, which may be socially wasteful.     

Interpreting financial market crashes as earthquakes: A new Early Warning System for medium term crashes

We propose a modeling framework which allows for creating probability predictions on a future market crash in the medium term, like sometime in the next five days. Our framework draws upon noticeable similarities between stock returns around a financial market crash and seismic activity around earthquakes. Our model is incorporated in an Early Warning System for future crash days. Testing our EWS on S&P 500 data during the recent financial crisis, we find positive Hanssen–Kuiper Skill Scores. Furthermore our modeling framework is capable of exploiting information in the returns series not captured by well known and commonly used volatility models. EWS based on our models outperform EWS based on the volatility models forecasting extreme price movements, while forecasting is much less time-consuming.     

Technological bias at the exchange rate market

Prediction of exchange rates has been a topic for debate in economic literature since the late 1980s. The recent development of machine learning techniques has spurred a plethora of studies that further improves the prediction models for currency markets. This high-tech progress may create challenges for market efficiency along with information asymmetry and irrationality of decision-making. This technological bias emerges from the fact that recent innovative approaches have been used to solve trading tasks and to find the best trading strategies. This paper demonstrates that traders can leverage technological bias for financial market forecasting. Those traders who adapt faster to the changes in market innovations will get excess returns. To support this hypothesis we compare the performance of deep learning methods, shallow neural networks with baseline prediction methods and a random walk model using daily closing rate between three currency pairs: Euro and US Dollar (EUR/USD), British Pound and US Dollar (GBP/USD), and US Dollar and Japanese Yen (USD/JPY). The results demonstrate that deep learning achieves higher accuracy than alternate methods. The shallow neural network outperforms the random walk model, but cannot surpass ARIMA accuracy significantly. The paper discusses possible outcomes of the technological shift for financial market development and accounting conforming also to adaptive market hypothesis.     

A SIMULATION ANALYSIS OF HERDING AND UNIFRACTAL SCALING BEHAVIOUR

We model the financial market using a class of agent‐based models in which agents’ expectations are driven by heuristic forecasting rules (in contrast to the rational expectations models used in traditional theories of financial markets). We show that, within this framework, we can reproduce unifractal scaling with respect to three well‐known power laws relating (i) moments of the absolute price change to the time‐scale over which they are measured, (ii) magnitude of returns with respect to their probability and (iii) the autocorrelation of absolute returns with respect to lag. In contrast to previous studies, we systematically analyse all three power laws simultaneously using the same underlying model by making observations at different time‐scales and higher moments. We show that the first two scaling laws are remarkably robust to the time‐scale over which observations are made, irrespective of the model configuration. However, in contrast to previous studies, we show that herding may explain why long memory is observed at all frequencies. Copyright © 2013 John Wiley & Sons, Ltd.