Search

• We propose a novel hybrid model namely MEEMD-Mix-KELM to forecast crude oil price. • The emerging MEEMD, with mode-splitting prevention, is used to decompose oil price. • We create a new mix-kernel for ELM by absorbing merits of local and global kernels. • Empirical results show that the proposed hybrid model achieves significant effects. It is of vital importance for governments, enterprises, and investors to forecast crude oil prices accurately, while this task is beset with difficulties and challenges due to the complex patterns in oil prices. This paper aims to propose a novel hybrid method to model and forecast the crude oil price by integrating median ensemble empirical mode decomposition (MEEMD) and mix-kernel extreme learning machine (Mix-KELM). Firstly, the emerging MEEMD is employed to decompose the crude oil price into several simple subseries. Secondly, a novel mix-kernel is developed for extreme learning machine (ELM) by combining the advantage of the local kernel (i.e., Radial Basis Function in learning ability) and global kernel (i.e., Sigmoid in generalization ability), with weights of the kernels optimized through genetic algorithm. Thirdly, the proposed Mix-KELM is applied to forecast the subseries of crude oil price, and the sub-forecasting results are integrated to generate the final results. The empirical results show that our proposed MEEMD-Mix-KELM model with different forecasting horizons significantly outperforms the benchmarks in terms of forecasting accuracy and robustness test. Taking one-step-ahead forecasting as an example, the proposed model exhibits the lowest prediction errors in terms of mean absolute error, symmetric mean absolute percentage error, and root mean squared error with values of 1.1767, 0.0135, and 1.5717, respectively. [ABSTRACT FROM AUTHOR]

With the emergence of artificial intelligence, deep learning techniques have been widely deployed in forecasting stock markets. However, existing deep-learning-based models for news-based forecasts of stock trends are mostly black-box and difficult to explain. The procedure by which how final predictions are made within models keeps unknown, making it hard to interpret why one prediction should be better than the other. To provide explanations on predictions, this paper proposes to inject causal inference into model procedures and causally interpret predictions. We first generate a causal graph from financial news, and then integrate the information in the causal graph into a neural network model for stock trend prediction. Moreover, in order to better extract keywords from financial news we introduce a novel keyword extraction method named Distinguishable Word Filtering by Kolmogorov–Smirnov Test (DWF-KST). The experiment results on five financial datasets demonstrate that not only our proposed model explicitly provides an interpretation of prediction results, but also outperforms the state-of-art methods. the achieved results boost predictions of S&P 500 2-category from 89.7% to 97.4%, 3-category from 77.4% to 82.5%, and 5-category from 61.5% to 71.6%. For the other two indexes, the performances of Dow index improve from 86.2% to 90.2% and Nasdaq index improve from 76.4% to 78.9%. • We propose a method for stock trend prediction. • We use causal inference based on unstructured data. • Improve the interpretability of DL-based stock prediction models. • We propose DWF-KST for keyword selection in financial news. [ABSTRACT FROM AUTHOR]

High-dose single exposures of long-wavelength ultraviolet-A (UV-A) radiation may trigger severe biological and skin tissue damage in humans and animals, as well as photosynthetic damage in plants. In humans, the highly abundant UV-A is also linked to an increased risk of skin cancer. This paper develops a new forecasting framework tailored for very short-term UV-A predictions using a Bayesian optimized ensemble Neural Basis Expansion Analysis for Interpretable Time Series (B-E-NBEATS) method, integrated with cloud cover predictors and the solar zenith angle. The design phase of the proposed model entails feature selection using an efficient neighborhood component analysis algorithm and hyperparameter tuning with a Bayesian optimizer. To further enhance the predictive performance and reliability, the B-E-NBEATS model is calibrated via uncertainty quantification by adopting an ensemble approach with single-point models trained on three key loss functions. The prescribed model generates interpretable forecasts of 20-minute ahead UV-A by empowering the ensemble members to learn seasonal and trend components in UV-A datasets. With respect to the four benchmark models, the statistical metrics and visual infographics of predicted and observed UV-A reveal a superior forecasting capability of the proposed B-E-NBEATS model. The model yields a comparatively high correlation coefficient of 0.910, 0.869, 0.933, and 0.900 for the spring, summer, autumn, and winter testing phases, respectively. The superior performance by the newly designed hybrid ensemble model ascertains its potential utility in UV-A monitoring and mitigating subsequent harmful exposure risk for the general public, and animal and plant life. [Display omitted] • An interpretable AI method is designed to predict solar ultraviolet-A radiation. • Deep learning ensemble approach is adopted to enhance forecasting performance. • The model is optimized with neighborhood component analysis and Bayesian optimizer. • Model calibration by quantifying uncertainty offers reliable ultraviolet-A forecasts. • The proposed model predicts cloud-affected solar ultraviolet-A with high accuracies. [ABSTRACT FROM AUTHOR]

Abstract: Support vector machine is a new tool from Artificial Intelligence (AI) field has been successfully applied for a wide variety of problem especially in time-series forecasting. In this paper, least square support vector machine (LSSVM) is an improved algorithm based on SVM, with the combination of self-organizing maps(SOM) also known as SOM-LSSVM is proposed for time-series forecasting. The objective of this paper is to examine the flexibility of SOM-LSSVM by comparing it with a single LSSVM model. To assess the effectiveness of SOM-LSSVM model, two well-known datasets known as the Wolf yearly sunspot data and the Monthly unemployed young women data are used in this study. The experiment shows SOM-LSSVM outperforms the single LSSVM model based on the criteria of mean absolute error (MAE) and root mean square error (RMSE). It also indicates that SOM-LSSVM provides a promising alternative technique in time-series forecasting. [Copyright &y& Elsevier]

Cellular networks are important for the success of modern communication systems, which support billions of mobile users and devices. Powered by artificial intelligence techniques, cellular networks are becoming increasingly smarter, and cellular traffic prediction is an important basis for realizing various applications that have originated from this trend. In this survey, we review the relevant studies on cellular traffic prediction and classify the prediction problems as the temporal and spatiotemporal prediction problems. The prediction models with artificial intelligence are categorized into statistical, machine learning, and deep learning models and then compared. Various applications based on cellular traffic prediction are summarized along with their current progress. The potential research directions are pointed out for future research. To the best of our knowledge, this paper is the first comprehensive survey on cellular traffic prediction. • Artificial intelligence for cellular traffic prediction is reviewed comprehensively. • Cellular traffic prediction problems, models, and evaluation metrics are classified. • The potential applications and directions for future research are pointed out. [ABSTRACT FROM AUTHOR]

In this paper, we present a method to use advance demand information (ADI), taking the form of request for quotation (RFQ) data, in B2B sales forecasting. We apply supervised machine learning and Natural Language Processing techniques to analyze and learn from RFQs. We apply and test our approach in a case study at a large after-sales service and maintenance provider. After evaluation we found that our approach identifies ∼ 70% of actual sales (recall) with a precision rate of ∼ 50%, which represents a performance improvement of slightly more than a factor 2.5 over the current labor-intensive manual process at the service and maintenance provider. Our research contributes to literature by giving step-by-step guidance on incorporating artificial intelligence in B2B sales forecasting and revealing potential pitfalls along the way. Furthermore, our research gives an indication of the performance improvement that can be expected when adopting supervised machine learning into B2B sales forecasting. [ABSTRACT FROM AUTHOR]

Abstract: Forecasting future color trend is a crucially important and challenging task in the fashion industry including design, production and sales. In particular, the trend of fashion color is highly volatile. Without advanced methods, it is very hard to make fashion color trend forecasting with reasonably high accuracy, and it is a handicap for development of the intelligent expert systems in fashion industry. As a result, many prior works have employed traditional regression models like ARIMA or intelligent models such as artificial neural network (ANN) and grey model (GM) for conducting color trend forecasting. However, the reported accuracies of these forecasting methods vary a lot, and there are controversies in the literature on these models’ performances. As a result, in this paper, we systematically compare the performances of ARIMA, ANN and GM models and their extended family methods. With real data analysis, our results show that the ANN family models, especially for Extreme Learning Machine (ELM) with Grey Relational Analysis (GRA), outperform the other models for forecasting fashion color trend. [Copyright &y& Elsevier]

Abstract: Though the hi-tech industry has focused on value innovation and improving the quality of the new product development (NPD) process to drive new product performance, new product success has not changed dramatically over the years. This study presents a novel approach based on structural equation modeling (SEM) and adaptive neuro-fuzzy inference system (ANFIS) to forecast value innovation and the effects of the quality of the NPD process on NPD performance. Results demonstrate that value innovation directly affects NPD performance as well as the nonlinear relationships between the quality of NPD processes and NPD performance, and that ANFIS achieves better forecasting performance than the SEM technique. The ANFIS model effectively explains the nonlinear relationships that SEM cannot. This paper thus offers a new perspective on forecasting and modeling useful to both researchers and practitioners. [Copyright &y& Elsevier]

Abstract: Many forecasting models based on the concepts of fuzzy time series have been proposed in the past decades. These models have been applied to predict enrollments, temperature, crop production and stock index, etc. In this paper, we present a simple heuristic time-invariant fuzzy time series forecasting model, which uses prediction accuracy of model observations to train the trend predictor in the training phase, and uses these trend predictor to generate forecasting values in the testing phase. This model can capture the trends of the time series more accurately and hence improve the forecasting results. The proposed method is applied for forecasting university enrollment of Alabama and the Taiwan Futures Exchange (TAIFEX). It is shown that the proposed model achieves a significant improvement in forecasting accuracy as compared to other fuzzy time series forecasting models. [ABSTRACT FROM AUTHOR]

Abstract: Artificial neural networks (ANNs) are flexible computing frameworks and universal approximators that can be applied to a wide range of time series forecasting problems with a high degree of accuracy. However, despite all advantages cited for artificial neural networks, their performance for some real time series is not satisfactory. Improving forecasting especially time series forecasting accuracy is an important yet often difficult task facing forecasters. Both theoretical and empirical findings have indicated that integration of different models can be an effective way of improving upon their predictive performance, especially when the models in the ensemble are quite different. In this paper, a novel hybrid model of artificial neural networks is proposed using auto-regressive integrated moving average (ARIMA) models in order to yield a more accurate forecasting model than artificial neural networks. The empirical results with three well-known real data sets indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by artificial neural networks. Therefore, it can be used as an appropriate alternative model for forecasting task, especially when higher forecasting accuracy is needed. [Copyright &y& Elsevier]

This paper considers the detrimental effect of promotions on the supply chain (SC), one of the main causes of the bullwhip effect. A genetic algorithm (GA) is proposed to reduce these negative effects. In order to validate the GA, it is used to determine the optimal ordering policy in an online version of the MIT beer distribution game. Subsequently, the GA is applied in a number of experiments involving deterministic and random demand and lead times combined with sales promotions. It is shown how GAs can be used to dampen the impact of the bullwhip effect and can be used to assist supply managers in predicting reorder quantities along the supply chain. [Copyright &y& Elsevier]

Abstract: A given observation in time series does not only depend on preceding one but also previous ones in general. Therefore, high order fuzzy time series approach might obtain better forecasts than does first order fuzzy time series approach. Defining fuzzy relation in high order fuzzy time series approach are more complicated than that in first order fuzzy time series approach. A new proposed approach, which uses feed forward neural networks to define fuzzy relation in high order fuzzy time series, is introduced in this paper. The new proposed approach is applied to well-known enrollment data for the University of Alabama and obtained results are compared with other methods proposed in the literature. It is found that the proposed method produces better forecasts than the other methods. [Copyright &y& Elsevier]

• Confident itemsets are used to discretize the whole model into subspaces. • Concise instance-wise explanations approximate the behavior of the black-box. • Class-wise explanations approximate the black-box's behavior in different subspaces. • Confident itemsets explanations improve the fidelity by 9.3% over other methods. • Confident itemsets explanations improve the interpretability by 8.8% Black-box Artificial Intelligence (AI) methods, e.g. deep neural networks, have been widely utilized to build predictive models that can extract complex relationships in a dataset and make predictions for new unseen data records. However, it is difficult to trust decisions made by such methods since their inner working and decision logic is hidden from the user. Explainable Artificial Intelligence (XAI) refers to systems that try to explain how a black-box AI model produces its outcomes. Post-hoc XAI methods approximate the behavior of a black-box by extracting relationships between feature values and the predictions. Perturbation-based and decision set methods are among commonly used post-hoc XAI systems. The former explanators rely on random perturbations of data records to build local or global linear models that explain individual predictions or the whole model. The latter explanators use those feature values that appear more frequently to construct a set of decision rules that produces the same outcomes as the target black-box. However, these two classes of XAI methods have some limitations. Random perturbations do not take into account the distribution of feature values in different subspaces, leading to misleading approximations. Decision sets only pay attention to frequent feature values and miss many important correlations between features and class labels that appear less frequently but accurately represent decision boundaries of the model. In this paper, we address the above challenges by proposing an explanation method named Confident Itemsets Explanation (CIE). We introduce confident itemsets, a set of feature values that are highly correlated to a specific class label. CIE utilizes confident itemsets to discretize the whole decision space of a model to smaller subspaces. Extracting important correlations between the features and the outcomes of the classifier in different subspaces, CIE produces instance-wise and class-wise explanations that accurately approximate the behavior of the target black-box. Conducting a set of experiments on various black-box classifiers, and different tabular and textual data classification tasks, we show that our CIE method performs better than the previous perturbation-based and rule-based explanators in terms of the descriptive accuracy (an improvement of 9.3%) and interpretability (an improvement of 8.8%) of the explanations. Subjective evaluations demonstrate that the users find the explanations of CIE more understandable and interpretable than those of the other comparison methods. [ABSTRACT FROM AUTHOR]