Search Results (25)

Financial sustainability in higher education is increasingly fragile due to policy shifts, rising costs, and funding volatility. Legacy early-warning systems based on static thresholds or rules struggle to adapt to these dynamics and often overlook fairness and interpretability—two essentials in public-sector governance. We propose a university financial risk early-warning framework that couples a causal-attention Transformer with Multi-Objective Bayesian Optimization (MBO). The optimizer searches a constrained Pareto frontier to jointly improve predictive accuracy (AUC↑), fairness (demographic parity gap, DP_Gap↓), and computational efficiency (time↓). A sparse kernel surrogate (SKO) accelerates convergence in high-dimensional tuning; a dual-head output (risk probability and health score) and SHAP-based attribution enhance transparency and regulatory alignment. On multi-year, multi-institution data, the approach surpasses mainstream baselines in AUC, reduces DP_Gap, and yields expert-consistent explanations. Methodologically, the design aligns with LLM-style time-series forecasting by exploiting causal masking and long-range dependencies while providing governance-oriented explainability. The framework delivers earlier, data-driven signals of financial stress, supporting proactive resource allocation, funding restructuring, and long-term planning in higher education finance. Full article

Accurate and efficient cryptocurrency price prediction is vital for investors in the volatile crypto market. This study comprehensively evaluates nine models—including baseline, zero-shot, and deep learning architectures—on 21 major cryptocurrencies using daily and hourly data. Our multi-dimensional evaluation assesses models based on prediction accuracy (MAE, RMSE, MAPE), speed, statistical significance (Diebold–Mariano test), and economic value (Sharpe Ratio). Our research found that the optimally fine-tuned TimeGPT model (without variables) demonstrated superior performance across both Daily and Hourly datasets, with its statistical leadership confirmed by the Diebold–Mariano test. Fine-tuned Chronos excelled in daily predictions, while TFT was a close second to TimeGPT for hourly forecasts. Crucially, zero-shot models like TimeGPT and Chronos were tens of times faster than traditional deep learning models, offering high accuracy with superior computational efficiency. A key finding from our economic analysis is that a model’s effectiveness is highly dependent on market characteristics. For instance, TimeGPT with variables showed exceptional profitability in the volatile ETH market, whereas the zero-shot Chronos model was the top performer for the cyclical BTC market. This also highlights that variables have asset-specific effects with TimeGPT: improving predictions for ICP, LTC, OP, and DOT, but hindering UNI, ATOM, BCH, and ARB. Recognizing that prior research has overemphasized prediction accuracy, this study provides a more holistic and practical standard for model evaluation by integrating speed, statistical significance, and economic value. Our findings collectively underscore TimeGPT’s immense potential as a leading solution for cryptocurrency forecasting, offering a top-tier balance of accuracy and efficiency. This multi-dimensional approach provides critical, theoretical, and practical guidance for investment decisions and risk management, proving especially valuable in real-time trading scenarios. Full article

The neural architecture search technique is used to automate the engineering of neural network models. Several studies have applied this approach, mainly in the fields of image processing and natural language processing. Its application generally requires very long computing times before converging on the optimal architecture. This study proposes a hybrid approach that combines transfer learning and dynamic search space adaptation (TL-DSS) to reduce the architecture search time. To validate this approach, Long Short-Term Memory (LSTM) models were designed using different evolutionary algorithms, including artificial bee colony (ABC), genetic algorithm (GA), differential evolution (DE), and particle swarm optimization (PSO), which were developed to predict trends in global horizontal irradiation data. The performance measures of this approach include the performance of the proposed models, as evaluated via RMSE over a 24-h prediction window of the solar irradiance data trend on one hand, and CPU search time on the other. The results show that, in addition to reducing the search time by up to 89.09% depending on the search algorithm, the proposed approach enables the creation of models that are up to 99% more accurate than the non-enhanced approach. This study demonstrates that it is possible to reduce the search time of a neural architecture while ensuring that models achieve good performance. Full article

Multivariate Time Series Forecasting (MTSF) has been innovated with a series of models in the last two decades, ranging from traditional statistical approaches to RNN-based models. However, recent contributions from deep learning to time series problems have made huge progress with a series of Transformer-based models. Despite the breakthroughs by attention mechanisms applied to deep learning areas, many challenges remain to be solved with more sophisticated models. Existing Transformers known as attention-based models outperform classical models with abilities to capture temporal dependencies and better strategies for learning dependencies among variables as well as in the time domain in an efficient manner. Aiming to solve those issues, we propose a novel Transformer—SegmentedCrossformer (SCF), a Transformer-based model that considers both time and dependencies among variables in an efficient manner. The model is built upon the encoder–decoder architecture in different scales and compared with the previous state of the art. Experimental results on different datasets show the effectiveness of SCF with unique advantages and efficiency. Full article

This systematic literature review explores the application of artificial intelligence (AI) and machine learning (ML) in financial market forecasting, with a focus on four asset classes: equities, cryptocurrencies, commodities, and foreign exchange markets. Guided by the PRISMA methodology, the study identifies the most widely used predictive models, particularly LSTM, GRU, XGBoost, and hybrid deep learning architectures, as well as key evaluation metrics, such as RMSE and MAPE. The findings confirm that AI-based approaches, especially neural networks, outperform traditional statistical methods in capturing non-linear and high-dimensional dynamics. However, the analysis also reveals several critical research gaps. Most notably, current models are rarely embedded into real or simulated trading strategies, limiting their practical applicability. Furthermore, the sensitivity of widely used metrics like MAPE to volatility remains underexplored, particularly in highly unstable environments such as crypto markets. Temporal robustness is also a concern, as many studies fail to validate their models across different market regimes. While data covering one to ten years is most common, few studies assess performance stability over time. By highlighting these limitations, this review not only synthesizes the current state of the art but also outlines essential directions for future research. Specifically, it calls for greater emphasis on model interpretability, strategy-level evaluation, and volatility-aware validation frameworks, thereby contributing to the advancement of AI’s real-world utility in financial forecasting. Full article

This article describes a robust Gaussian Prior process state space modeling (GPSSM) approach to assess the impact of an intervention in a time series. Numerous applications can benefit from this approach. Examples include: (1) time series could be the stock price of a company and the intervention could be the acquisition of another company; (2) the time series under concern could be the noise coming out of an engine, and the intervention could be a corrective step taken to reduce the noise; (3) the time series could be the number of visits to a web service, and the intervention is changes done to the user interface; and so on. The approach we describe in this article applies to any times series and intervention combination. It is well known that Gaussian process (GP) prior models provide flexibility by placing a non-parametric prior on the functional form of the model. While GPSSMs enable us to model a time series in a state space framework by placing a Gaussian Process (GP) prior over the state transition function, probabilistic recurrent state space models (PRSSM) employ variational approximations for handling complicated posterior distributions in GPSSMs. The robust PRSSMs (R-PRSSMs) discussed in this article assume a scale mixture of normal distributions instead of the usually proposed normal distribution. This assumption will accommodate heavy-tailed behavior or anomalous observations in the time series. On any exogenous intervention, we use R-PRSSM for Bayesian fitting and forecasting of the IoT time series. By comparing forecasts with the future internal temperature observations, we can assess with a high level of confidence the impact of an intervention. The techniques presented in this paper are very generic and apply to any time series and intervention combination. To illustrate our techniques clearly, we employ a concrete example. The time series of interest will be an Internet of Things (IoT) stream of internal temperatures measured by an insurance firm to address the risk of pipe-freeze hazard in a building. We treat the pipe-freeze hazard alert as an exogenous intervention. A comparison of forecasts and the future observed temperatures will be utilized to assess whether an alerted customer took preventive action to prevent pipe-freeze loss. Full article

Time series forecasting has witnessed a rapid proliferation of novel neural network approaches in recent times. However, performances in terms of benchmarking results are generally not consistent, and it is complicated to determine in which cases one approach fits better than another. Therefore, we propose adopting a data-centric perspective for benchmarking neural network architectures on time series forecasting by generating ad hoc synthetic datasets. In particular, we combine sinusoidal functions to synthesize univariate time series data for multi-input-multi-output prediction tasks. We compare the most popular architectures for time series, namely long short-term memory (LSTM) networks, convolutional neural networks (CNNs), and transformers, and directly connect their performance with different controlled data characteristics, such as the sequence length, noise and frequency, and delay length. Our findings suggest that transformers are the best architecture for dealing with different delay lengths. In contrast, for different noise and frequency levels and different sequence lengths, LSTM is the best-performing architecture by a significant amount. Based on our insights, we derive recommendations which allow machine learning (ML) practitioners to decide which architecture to apply, given the dataset’s characteristics. Full article

Models are a core element in performing local estimation of the climate change input. In this work, a novel approach to perform a fast downscaling of global temperature anomalies on a regional level is presented. The approach is based on a set of data-driven models linking global temperature anomalies and regional and global emissions to regional temperature anomalies. In particular, due to the limited number of available data, a linear autoregressive structure with exogenous input (ARX) has been considered. To demonstrate their relevance to the existing literature and context, the proposed ARX models have been employed to evaluate the impact of temperature anomalies on rice production in a socially, economically, and climatologically fragile area like Southeast Asia. The results show a significant impact on this region, with estimations strongly in accordance with information presented in the literature from different sources and scientific fields. The work represents a first step towards the development of a fast, data-driven, holistic approach to the climate change impact evaluation problem. The proposed ARX data-driven models reveal a novel and feasible way to downscale global temperature anomalies to regional levels, showing their importance in comprehending global temperature anomalies, emissions, and regional climatic conditions. Full article

We present a technique to solve the linear integer model with variable bounding. By using the continuous optimal solution of the linear integer model, the variable bounds for the basic variables are approximated and then used to calculate the optimal integer solution. With the variable bounds of the basic variables known, solving a linear integer model is easier by using either the branch and bound, branch and cut, branch and price, branch cut and price, or branch cut and free algorithms. Thus, the search for large numbers of subproblems, which are unnecessary and common for NP Complete linear integer models, is avoided. Full article

Deep learning models have revolutionized research fields like computer vision and natural language processing by outperforming traditional models in multiple tasks. However, the field of time series analysis, especially time series forecasting, has not seen a similar revolution, despite forecasting being one of the most prominent tasks of predictive data analytics. One crucial problem for time series forecasting is the lack of large, domain-independent benchmark datasets and a competitive research environment, e.g., annual large-scale challenges, that would spur the development of new models, as was the case for CV and NLP. Furthermore, the focus of time series forecasting research is primarily domain-driven, resulting in many highly individual and domain-specific datasets. Consequently, the progress in the entire field is slowed down due to a lack of comparability across models trained on a single benchmark dataset and on a variety of different forecasting challenges. In this paper, we first explore this problem in more detail and derive the need for a comprehensive, domain-unspecific overview of the state-of-the-art of commonly used datasets for prediction tasks. In doing so, we provide an overview of these datasets and improve comparability in time series forecasting by introducing a method to find similar datasets which can be utilized to test a newly developed model. Ultimately, our survey paves the way towards developing a single widely used and accepted benchmark dataset for time series data, built on the various frequently used datasets surveyed in this paper. Full article

Aiming for the forecasting and predictability of their future development, corporations have developed appropriate strategies as a result of the necessity to optimize the distribution networks of new IT products over time. The necessity of diversifying manufacturing was brought on by the fierce competition between businesses and the sophisticated consumer demand trends for personalized items. For businesses looking to create more effective distribution networks for their products, mass adaptability may be advantageous. Fuzzy cognitive mapping (FCM), associations developed from web analytics data, and simulation results based on dynamic and agent-based simulation models work together to practically aid digital marketing experts, decision-makers and analysts in offering answers to their corresponding problems. In order to apply the measures in agent-based modeling, the current work is based on the gathering of web analysis data over a predetermined time period, as well as on identifying the influence correlations between measurements. Full article

The selection of an accurate performance metric is highly important to evaluate the quality of a forecasting method. This evaluation may help to select between different forecasting tools of forecasting outputs, and then support many decisions within a company. This paper proposes to evaluate the sensitivity and reliability of forecasts performance metrics. The methodology is tested using multiple time series of different scales and demand patterns, such as intermittent demand. The idea is to add to each series a noise following a known distribution to represent forecasting models of a known error distribution. Varying the parameters of the distribution of the noise allows to evaluate how sensitive and reliable performance metrics are to changes in bias and variance of the error of a forecasting model. The experiments concluded that sRMSE is more reliable than MASE in most cases on those series. sRMSE is especially reliable for detecting changes in the variance of a model and sPIS is the most sensitive metric to the bias of a model. sAPIS is sensible to both variance and bias but is less reliable. Full article

The techniques of hybridisation and ensemble learning are popular model fusion techniques for improving the predictive power of forecasting methods. With limited research that instigates combining these two promising approaches, this paper focuses on the utility of the Exponential Smoothing-Recurrent Neural Network (ES-RNN) in the pool of base learners for different ensembles. We compare against some state-of-the-art ensembling techniques and arithmetic model averaging as a benchmark. We experiment with the M4 forecasting dataset of 100,000 time-series, and the results show that the Feature-Based FORecast Model Averaging (FFORMA), on average, is the best technique for late data fusion with the ES-RNN. However, considering the M4’s Daily subset of data, stacking was the only successful ensemble at dealing with the case where all base learner performances were similar. Our experimental results indicate that we attain state-of-the-art forecasting results compared to Neural Basis Expansion Analysis (N-BEATS) as a benchmark. We conclude that model averaging is a more robust ensembling technique than model selection and stacking strategies. Further, the results show that gradient boosting is superior for implementing ensemble learning strategies. Full article

Compared to other industries, fashion apparel retail faces many challenges in predicting future demand for its products with a high degree of precision. Fashion products’ short life cycle, insufficient historical information, highly uncertain market demand, and periodic seasonal trends necessitate the use of models that can contribute to the efficient forecasting of products’ sales and demand. Many researchers have tried to address this problem using conventional forecasting models that predict future demands using historical sales information. While these models predict product demand with fair to moderate accuracy based on previously sold stock, they cannot fully be used for predicting future demands due to the transient behaviour of the fashion industry. This paper proposes an intelligent forecasting system that combines image feature attributes of clothes along with its sales data to predict future demands. The data used for this empirical study is from a European fashion retailer, and it mainly contains sales information on apparel items and their images. The proposed forecast model is built using machine learning and deep learning techniques, which extract essential features of the product images. The model predicts weekly sales of new fashion apparel by finding its best match in the clusters of products that we created using machine learning clustering based on products’ sales profiles and image similarity. The results demonstrated that the performance of our proposed forecast model on the tested or test items is promising, and this model could be effectively used to solve forecasting problems. Full article

Image classification is widely used to build predictive models for breast cancer diagnosis. Most existing approaches overwhelmingly rely on deep convolutional networks to build such diagnosis pipelines. These model architectures, although remarkable in performance, are black-box systems that provide minimal insight into the inner logic behind their predictions. This is a major drawback as the explainability of prediction is vital for applications such as cancer diagnosis. In this paper, we address this issue by proposing an explainable machine learning pipeline for breast cancer diagnosis based on ultrasound images. We extract first- and second-order texture features of the ultrasound images and use them to build a probabilistic ensemble of decision tree classifiers. Each decision tree learns to classify the input ultrasound image by learning a set of robust decision thresholds for texture features of the image. The decision path of the model predictions can then be interpreted by decomposing the learned decision trees. Our results show that our proposed framework achieves high predictive performance while being explainable. Full article