Crude oil price forecasting incorporating news text

Sparse and short news headlines can be arbitrary, noisy, and ambiguous, making it difficult for classic topic model LDA (latent Dirichlet allocation) designed for accommodating long text to discover knowledge from them. Nonetheless, some of the existing research about text-based crude oil forecasting employs LDA to explore topics from news headlines, resulting in a mismatch between the short text and the topic model and further affecting the forecasting performance. Exploiting advanced and appropriate methods to construct high-quality features from news headlines becomes crucial in crude oil forecasting. This paper introduces two novel indicators of topic and sentiment for the short and sparse text data to tackle this issue. Empirical experiments show that AdaBoost.RT with our proposed text indicators, with a more comprehensive view and characterization of the short and sparse text data, outperforms the other benchmarks. Another significant merit is that our method also yields good forecasting performance when applied to other futures commodities.     

Mutual excitation between OECD stock and oil markets: A conditional intensity extreme value approach

We analyze the degree of mutual excitation that exists between extreme events across the stock markets of OECD member nations and the Brent and WTI crude oil markets. For this analysis, marked point process models are proposed which are able to capture the dynamics of the intensity of occurrence and comovement during periods of crisis. The results show a significant, negative interdependence between most OECD markets, especially those of the USA, Japan and France. These major oil importing countries display links between equity market losses and positive returns in both oil markets. However, positive interdependence is not observed between any of the OECD countries except for South Korea. The great advantage of this methodology is that, apart from using the size distribution of extreme events, it also uses the occurrence times of extreme events as a source of information. With this information, these models are better able to capture the stylized facts of extreme events in financial markets such as clustering behavior and cross-excitation.     

Parameter-efficient deep probabilistic forecasting

Probabilistic time series forecasting is crucial in many application domains, such as retail, ecommerce, finance, and biology. With the increasing availability of large volumes of data, a number of neural architectures have been proposed for this problem. In particular, Transformer-based methods achieve state-of-the-art performance on real-world benchmarks. However, these methods require a large number of parameters to be learned, which imposes high memory requirements on the computational resources for training such models. To address this problem, we introduce a novel bidirectional temporal convolutional network that requires an order of magnitude fewer parameters than a common Transformer-based approach. Our model combines two temporal convolutional networks: the first network encodes future covariates of the time series, whereas the second network encodes past observations and covariates. We jointly estimate the parameters of an output distribution via these two networks. Experiments on four real-world datasets show that our method performs on par with four state-of-the-art probabilistic forecasting methods, including a Transformer-based approach and WaveNet, on two point metrics (sMAPE and NRMSE) as well as on a set of range metrics (quantile loss percentiles) in the majority of cases. We also demonstrate that our method requires significantly fewer parameters than Transformer-based methods, which means that the model can be trained faster with significantly lower memory requirements, which as a consequence reduces the infrastructure cost for deploying these models.     

A novel text-based framework for forecasting agricultural futures using massive online news headlines

The agricultural futures prices are generally considered difficult to forecast because the causes of fluctuations are incredibly complicated. We propose a text-based forecasting framework, which can effectively identify and quantify factors affecting agricultural futures based on massive online news headlines. A comprehensive list of influential factors can be formed using a text mining method called topic modeling. A new sentiment-analysis-based way is designed to quantify the factors such as the weather and policies that are important yet difficult to quantify. The proposed framework is empirically tested at forecasting soybean futures prices in the Chinese market. Testing was based on 9715 online news headlines from July 19, 2012 to July 9, 2018. The results show that the identified influential factors and sentiment-based variables are effective, and the proposed framework performs significantly better in medium-term and long-term forecasting than the benchmark model.     

Online big data-driven oil consumption forecasting with Google trends

The rapid development of big data technologies and the Internet provides a rich mine of online big data (e.g., trend spotting) that can be helpful in predicting oil consumption — an essential but uncertain factor in the oil supply chain. An online big data-driven oil consumption forecasting model is proposed that uses Google trends, which finely reflect various related factors based on a myriad of search results. This model involves two main steps, relationship investigation and prediction improvement. First, cointegration tests and a Granger causality analysis are conducted in order to statistically test the predictive power of Google trends, in terms of having a significant relationship with oil consumption. Second, the effective Google trends are introduced into popular forecasting methods for predicting both oil consumption trends and values. The experimental study of global oil consumption prediction confirms that the proposed online big-data-driven forecasting work with Google trends improves on the traditional techniques without Google trends significantly, for both directional and level predictions.     

The role of text-extracted investor sentiment in Chinese stock price prediction with the enhancement of deep learning

Whether investor sentiment affects stock prices is an issue of long-standing interest for economists. We conduct a comprehensive study of the predictability of investor sentiment, which is measured directly by extracting expectations from online user-generated content (UGC) on the stock message board of Eastmoney.com in the Chinese stock market. We consider the influential factors in prediction, including the selections of different text classification algorithms, price forecasting models, time horizons, and information update schemes. Using comparisons of the long short-term memory (LSTM) model, logistic regression, support vector machine, and Naïve Bayes model, the results show that daily investor sentiment contains predictive information only for open prices, while the hourly sentiment has two hours of leading predictability for closing prices. Investors do update their expectations during trading hours. Moreover, our results reveal that advanced models, such as LSTM, can provide more predictive power with investor sentiment only if the inputs of a model contain predictive information.     

Targeted growth rates for long-horizon crude oil price forecasts

This paper proposes growth rate transformations with targeted lag selection in order to improve the long-horizon forecast accuracy. The method targets lower frequencies of the data that correspond to particular forecast horizons, and is applied to models of the real price of crude oil. Targeted growth rates can improve the forecast precision significantly at horizons of up to five years. For the real price of crude oil, the method can achieve a degree of accuracy up to five years ahead that previously has been achieved only at shorter horizons.     

How oil price and exchange rate affect stock price in China using Bayesian Quantile_on_Quantile with GARCH approach

We revisit the links of real exchange rate, oil price and stock market price for China using Bayesian Multivariate Quantile_on_Quantile with GARCH approach over the period of September 14, 2001 to June 17, 2022 (a total of 4051 days). Results indicate both the links between stock price and oil price and between stock price and exchange rate varying under different combinations of quantiles. GARCH model also indicate that yesterday news and persistence measures varying with current conditional variance under different quantiles. We further estimate half-life of a shock to our whole markets and find out the half-life of a shock range from 0.415 to 4.015 days. Result not found in previous study. Our study has important policy implications for the investors, practitioners, and the government.     

Crude oil price forecasting based on internet concern using an extreme learning machine

The growing internet concern (IC) over the crude oil market and related events influences market trading, thus creating further instability within the oil market itself. We propose a modeling framework for analyzing the effects of IC on the oil market and for predicting the price volatility of crude oil’s futures market. This novel approach decomposes the original time series into intrinsic modes at different time scales using bivariate empirical mode decomposition (BEMD). The relationship between the oil price volatility and IC at an individual frequency is investigated. By utilizing decomposed intrinsic modes as specified characteristics, we also construct extreme learning machine (ELM) models with variant forecasting schemes. The experimental results illustrate that ELM models that incorporate intrinsic modes and IC outperform the baseline ELM and other benchmarks at distinct horizons. Having the power to improve the accuracy of baseline models, internet searching is a practical way of quantifying investor attention, which can help to predict short-run price fluctuations in the oil market.     

A methodology for the choice of the best fitting continuous-time stochastic models of crude oil price

The crude oil price is generally considered as the fundamental factor in the valuation of undeveloped reserves but it is not the unique one. Undeveloped field value also depends on the uncertainty relating to the convenience yield and the risk-free interest rate. The purpose of this paper is to decide on the best continuous-time stochastic models for these risk factors. The Generalized Method of Moments and the Maximum Likelihood Estimation are implemented to fit the parameters of continuous-time stochastic processes. The results of unit root tests without breaks reveal a mean reversion in convenience yield series. Multiple structural change tests show that the risk-free interest rate can be considered constant. The simulation of continuous-time stochastic processes and the mean error between the simulated prices and the market ones show that the Geometric Brownian Motion with jumps is the best model for the oil price compared to the other commonly used processes.     

Electricity price forecasting: A review of the state-of-the-art with a look into the future

A variety of methods and ideas have been tried for electricity price forecasting (EPF) over the last 15 years, with varying degrees of success. This review article aims to explain the complexity of available solutions, their strengths and weaknesses, and the opportunities and threats that the forecasting tools offer or that may be encountered. The paper also looks ahead and speculates on the directions EPF will or should take in the next decade or so. In particular, it postulates the need for objective comparative EPF studies involving (i) the same datasets, (ii) the same robust error evaluation procedures, and (iii) statistical testing of the significance of one model’s outperformance of another.     

Forecasting election results by studying brand importance in online news

This study uses the semantic brand score, a novel measure of brand importance in big textual data, to forecast elections based on online news. About 35,000 online news articles were transformed into networks of co-occurring words and analyzed by combining methods and tools from social network analysis and text mining. Forecasts made for four voting events in Italy provided consistent results across different voting systems: a general election, a referendum, and a municipal election in two rounds. This work contributes to the research on electoral forecasting by focusing on predictions based on online big data; it offers new perspectives regarding the textual analysis of online news through a methodology which is relatively fast and easy to apply. This study also suggests the existence of a link between the brand importance of political candidates and parties and electoral results.     

News will tell: Forecasting foreign exchange rates based on news story events in the economy calendar

The paper proposes a novel approach to predict intraday directional-movements of currency-pairs in the foreign exchange market based on news story events in the economy calendar. Prior work on using textual data for forecasting foreign exchange market developments does not consider economy calendar events. We consider a rich set of text analytics methods to extract information from news story events and propose a novel sentiment dictionary for the foreign exchange market. The paper shows how news events and corresponding news stories provide valuable information to increase forecast accuracy and inform trading decisions. More specifically, using textual data together with technical indicators as inputs to different machine learning models reveals that the accuracy of market predictions shortly after the release of news is substantially higher than in other periods, which suggests the feasibility of news-based trading. Furthermore, empirical results identify a combination of a gradient boosting algorithm, our new sentiment dictionary, and text-features based-on term frequency weighting to offer the most accurate forecasts. These findings are valuable for traders, risk managers and other consumers of foreign exchange market forecasts and offer guidance how to design accurate prediction systems.     

System economics: Overcoming the pitfalls of forecasting models via a multidisciplinary approach

In areas from medicine to climate change to economics, we are faced with huge challenges and a need for accurate forecasts, yet our ability to predict the future has been found wanting. The basic problem is that complex systems such as the atmosphere or the economy can not be reduced to simple mathematical laws and modeled accordingly. The equations in numerical models are therefore only approximations to reality, and are often highly sensitive to external influences and small changes in parameterisation — they can be made to fit past data, but are less good at prediction. Since decisions are usually based on our best models of the future, how can we proceed? This paper draws a comparison between two apparently different fields: biology and economics. In biology, drug development is a highly inefficient and expensive process, which in the past has relied heavily on trial and error. Institutions such as pharmaceutical companies and universities are now radically changing their approach and adopting techniques from the new field of systems biology to integrate information from disparate sources and improve the development process. A similar revolution is required in economics if models are to reflect the nature of human economic activity and provide useful tools for policy makers. We outline the main foundations for a theory of systems economics.     

A decomposition clustering ensemble learning approach for forecasting foreign exchange rates

A decomposition clustering ensemble (DCE) learning approach is proposed for forecasting foreign exchange rates by integrating the variational mode decomposition (VMD), the self-organizing map (SOM) network, and the kernel extreme learning machine (KELM). First, the exchange rate time series is decomposed into N subcomponents by the VMD method. Second, each subcomponent series is modeled by the KELM. Third, the SOM neural network is introduced to cluster the subcomponent forecasting results of the in-sample dataset to obtain cluster centers. Finally, each cluster's ensemble weight is estimated by another KELM, and the final forecasting results are obtained by the corresponding clusters' ensemble weights. The empirical results illustrate that our proposed DCE learning approach can significantly improve forecasting performance, and statistically outperform some other benchmark models in directional and level forecasting accuracy.     

On the importance of the long-term seasonal component in day-ahead electricity price forecasting with NARX neural networks

Daily and weekly seasonalities are always taken into account in day-ahead electricity price forecasting, but the long-term seasonal component has long been believed to add unnecessary complexity, and hence, most studies have ignored it. The recent introduction of the Seasonal Component AutoRegressive (SCAR) modeling framework has changed this viewpoint. However, this framework is based on linear models estimated using ordinary least squares. This paper shows that considering non-linear autoregressive (NARX) neural network-type models with the same inputs as the corresponding SCAR-type models can lead to yet better performances. While individual Seasonal Component Artificial Neural Network (SCANN) models are generally worse than the corresponding SCAR-type structures, we provide empirical evidence that committee machines of SCANN networks can outperform the latter significantly.     

The nonlinear effect of oil price shocks on financial stress: Evidence from China

This paper examines the nonlinear effects of different types of oil price shocks on China’s financial stress index (FSI). For this purpose, we use newly proposed framework by Ready (2018) to decompose oil prices into supply, demand and risk shocks. Then, we use a Markov regime-switching (MRS) model to investigate the nonlinear effects of these oil price shocks on China’s FSI. The empirical results show that the effects of three oil price shocks are nonlinear under different regimes. In particular, oil supply shocks mainly have a significantly positive effect on China’s FSI in the low-volatility state; demand shocks have negative effects on China’s FSI in different regimes, but this effect is larger in the low-volatility state; the effect of risk shocks on China’s FSI is the opposite, and it is positive in the high-volatility state but negative in the low-volatility state.     

Macroeconomic responses of emerging market economies to oil price shocks: An analysis by region and resource profile

We analyze the impact of oil price shocks on the macroeconomic fundamentals in emerging economies in three regions that have different resource endowments. The existing literature on emerging economies remains inconclusive on how regional factors and resource characteristics affect the response of macroeconomic variables to oil price shocks. We show that (1) exports in Europe and Central Asia are driven by oil more than East Asia and the Pacific and that (2) policy makers in East Asia and the Pacific should be concerned about real exchange appreciation following a positive oil shock to mitigate losses in the non-oil export market. Analysis by resource endowment further reveals that, in less-resource-intensive economies, an oil price shock causes large variations in consumption and has a negative and persistent impact on the real gross domestic product (GDP). In mineral-exporting economies, real GDP and interest rates are driven largely by oil price shocks. The response of real GDP in mineral-exporting economies is short lived. In oil-exporting economies, only real GDP has a large variation in response to oil price shocks. Our findings highlight the need for customized policy responses to oil price shocks, depending on resource endowments, as we show that a “one size fits all" policy does not exist.     

Economic policy uncertainty,oil price volatility and stock market returns: Evidence from a nonlinear model

This paper investigates the nonlinear relationship between economic policy uncertainty, oil price volatility and stock market returns for 25 countries by applying the panel smooth transition regression model. We find that oil price volatility has a negative effect on stock returns, and this effect increases with economic policy uncertainty. Furthermore, there is pronounced heterogeneity in responses. First, oil-exporting countries whose economies depend more on oil prices respond more strongly to oil price volatility than oil-importing countries. Second, stock returns of developing countries are more susceptible to oil price volatility than that of developed countries. Third, crisis plays a crucial role in the relation between oil price volatility and stock returns.     

Forecasting crude oil futures market returns: A principal component analysis combination approach

To improve the predictability of crude oil futures market returns, this paper proposes a new combination approach based on principal component analysis (PCA). The PCA combination approach combines individual forecasts given by all PCA subset regression models that use all potential predictor subsets to construct PCA indexes. The proposed method can not only guard against over-fitting by employing the PCA technique but also reduce forecast variance due to extensive forecast combinations, thus benefiting from both the combination of information and the combination of forecasts. Showing impressive out-of-sample forecasting performance, the PCA combination approach outperforms a benchmark model and many related competing models. Furthermore, a mean–variance investor can realize sizeable utility gains by using the PCA combination forecasts relative to the competing forecasts from an asset allocation perspective.