Traditional Forecasting Models Research Articles

Analyzing Amazon Stock Volatility: Market Returns and Macroeconomic Factors

Against the backdrop of globalization and changing financial markets, investors and policymakers need accurate market volatility forecasts to guide decision-making. Traditional forecasting models are difficult to fully explain the complex market volatility, thus requiring more refined research methods. This study provides an in-depth analysis of the impact of market returns and macroeconomic indicators on Amazon stock volatility by constructing a two-factor model to provide more accurate forecasts. A quantitative approach is used to construct the model, with market returns represented by the CAPM and selected macroeconomic indicators introduced as the second factor. The model parameters are estimated from historical data and empirical analyses verify the predictive effectiveness of the model in different market environments. Preliminary results show that market returns and macroeconomic indicators significantly influence Amazon stock volatility. Market factors dominate volatility in the short term, while macroeconomic factors may have a more significant impact in the long term. This finding contributes to a better understanding of Amazon stock price drivers and provides investors with more targeted decision support.

Predictive value of triglyceride glucose index in acute kidney injury in patients with severe traumatic brain injury

Background At present, the relationship between the Triglyceride-glucose index (TyG index) and Acute kidney injury (AKI) in traumatic brain injury patients in the Intensive Care Unit (ICU) is still unclear. Currently, the relationship between TyG index and AKI occurred within 7 days in the ICU is a highly researched and trending topic. Objective In this study, we conducted in-depth exploration of the relationship between the development of AKI in traumatic brain injury (TBI) patients in the ICU and changes in TyG index, as well as its relevance. Methods A cross-sectional study was conducted with a total of 492 individuals enrolled in the Medical Information Mart for Intensive Care IV(MIMIC-IV) database. Multivariate model logistic regression, smoothed curve fitting and forest plots were utilized to confirm the study objectives. The predictive power of the TyG index for outcome indicators was assessed using subject work characteristics (ROC) curves. As well as comparing the Integrated Discriminant Improvement Index and the Net Reclassification Index of the traditional forecasting model with the addition of the TyG index. Results Of all eligible subjects, 55.9% were male and the incidence of AKI was 59.3%. There was a statistically significant difference in the incidence of AKI within 7 days in the ICU between the different TyG index groups. The difference between TyG index and the risk of AKI within 7 days in the ICU remained significant after adjustment for logistic multifactorial modeling (OR = 2.07, 95% CI = 1.41–3.05, P < 0.001). A similar pattern of associations was observed in subgroup analyses (P values for all interactions were greater than 0.05). The addition of TyG index to the traditional risk factor model improved the predictive power of the risk of AKI within 7 days in ICU (P < 0.05). Conclusion The findings of this study demonstrate a strong association between the TyG index and the occurrence of AKI within 7 days in ICU patients. The TyG index can potentially be used as a risk stratification tool for early identification and prevention of AKI. Implementing preventive strategies targeting patients with a high TyG index may help reduce the burden of AKI in the ICU. Further prospective studies are warranted to validate these findings and explore the clinical utility of the TyG index in AKI prevention.

Product Demand Forecasting For Inventory Management with Freight Transportation Services Index Using Advanced Neural Networks Algorithm

Purpose: Accurate demand forecasting is critical for optimizing inventory management, improving customer satisfaction, and maximizing profitability in the retail sector. Traditional forecasting models predominantly utilize micro-level variables, such as historical sales data and promotional activities, often neglecting the influence of macroeconomic conditions. Materials and Methods: This study addresses this gap by integrating Freight Transportation Services Index (TSI) which is an indicator for overall economic health with time series data of retail product sales. Utilizing an advanced neural networks model, we demonstrate that incorporating macroeconomic variables significantly enhances the model's predictive accuracy and explanatory power. Findings: The results reveal that the model with the TSI index outperforms conventional models, highlighting its potential for practical application in the industry. Implications to Theory, Practice and Policy: This approach offers a more comprehensive understanding of demand dynamics, enabling businesses to make more informed decisions, adapt to market fluctuations, and maintain a competitive edge.

Data-driven forecasting of embankment settlements on soft soils using constant rate of strain test data

Geotechnical engineers continually seek accurate methodologies for predicting the time-dependent settlement of embankments on soft soils. This paper introduces a novel data-driven approach that utilises constant rate of strain (CRS) test data to forecast embankment settlements. The proposed framework circumvents the requirement to subjectively assign soil parameters used in traditional forecasting models by directly integrating CRS test data into an automated analytical process, thereby significantly reducing manual effort and user-dependent variation in forecast results. The accuracy of the method is demonstrated through applications to real-world trial embankments in Australia and the Netherlands. All data used in this study are freely available in digital format from Datamap.

Hybrid Time Series Model for Advanced Predictive Analysis in COVID-19 Vaccination

This study aims to enhance the prediction of COVID-19 vaccination trends using a novel integrated forecasting model, facilitating better public health decision-making and resource allocation during the pandemic. As the COVID-19 pandemic continues to impact global health, accurately forecasting vaccination trends is critical for effective public health response and strategy development. Traditional forecasting models often fail to capture the complex dynamics of pandemic-driven vaccination rates. The analysis utilizes a comprehensive dataset comprising over 68,487 entries, detailing daily vaccination statistics across various demographics and geographic locations. This dataset provides a robust foundation for modeling and forecasting efforts. It utilizes advanced time series analysis techniques and machine learning algorithms to accurately predict future vaccination patterns based on the Hybrid Harvest model, which combines the strengths of ARIMA and Prophet models. Hybrid Harvest exhibits superior performance, with mean-square errors (MSEs) of 0.1323, and root-mean-square errors (RMSEs) of 0.0305. Based on these results, the model is significantly more accurate than traditional forecasting methods when predicting vaccination trends. It offers significant advances in forecasting COVID-19 vaccination trends through integration of ARIMA and Prophet models. The model serves as a powerful tool for policymakers to plan vaccination campaigns efficiently and effectively.

Enhancing photovoltaic energy forecasting: a progressive approach using wavelet packet decomposition

Abstract Accurate photovoltaic (PV) energy forecasting plays a crucial role in the efficient operation of PV power stations. This study presents a novel hybrid machine-learning (ML) model that combines Gaussian process regression with wavelet packet decomposition to forecast PV power half an hour ahead. The proposed technique was applied to the PV energy database of a station located in Algeria and its performance was compared to that of traditional forecasting models. Performance evaluations demonstrate the superiority of the proposed approach over conventional ML methods, including Gaussian process regression, extreme learning machines, artificial neural networks and support vector machines, across all seasons. The proposed model exhibits lower normalized root mean square error (nRMSE) (2.116%) and root mean square error (RMSE) (208.233 kW) values, along with a higher coefficient of determination (R2) of 99.881%. Furthermore, the exceptional performance of the model is maintained even when tested with various prediction horizons. However, as the forecast horizon extends from 1.5 to 5.5 hours, the prediction accuracy decreases, evident by the increase in the RMSE (710.839 kW) and nRMSE (7.276%), and a decrease in R2 (98.462%). Comparative analysis with recent studies reveals that our approach consistently delivers competitive or superior results. This study provides empirical evidence supporting the effectiveness of the proposed hybrid ML model, suggesting its potential as a reliable tool for enhancing PV power forecasting accuracy, thereby contributing to more efficient grid management.

TIME SERIES FORECASTING MODEL FOR SOLVING COLD START PROBLEM VIA TEMPORAL FUSION TRANSFORMER

Time series forecasting is an important tool in many businesses. It can range from efficiently allocating resources for web traffic, predicting patient needs for staffing requirements, to forecasting a company's product sales. A particular use case, known as "cold start" forecasting, involves making predictions for time series that have little or no historical data, like a new product just entering the retail market. The key assumption of cold start forecasting is that products with similar characteristics should have similar time series trajectories. In such scenarios, traditional forecasting models that heavily rely on past observations may face challenges, necessitating the development of innovative approaches that can effectively make predictions in the absence of a substantial historical dataset. In this paper, Temporal fusion transformer neural network architecture was applied for solving cold start time series forecasting task. Modeling of the method was based on the use of a dataset contained in an open repository. After the preprocessing procedures, the dataset has about 370 time series, each of which has different length of series and has one categorical feature. Categorical feature have only 4 types of different values. For model training was performed to search for optimal hyperparameters across such parameters as: number of attention heads, learning rate, dropout percentage and hidden size.Model performed pretty well on this task. For model comparison were chosen metrics: MAE, RMSE, SMAPE. As can be seen from comparison with such popular models as DeepAR and LSTM, the proposed approach demonstrated the smallest forecasting error. Only one downside is that it can have more problems with anomalies in time series than DeepAR. But at the same time still provide interpretability of results.

Inflation prediction in emerging economies: Machine learning and FX reserves integration for enhanced forecasting

The present study makes two significant contributions to the extended body of literature in the context of International Finance. First, it forecasts the inflation in an emerging economy by employing a combination of traditional forecasting and Machine Learning models to test whether machine learning models outperform traditional forecasting models. Second, it explicitly includes an often-neglected variable i.e. foreign exchange reserves into the forecasting models to ascertain whether its inclusion enhances predictive accuracy. The outcomes of the study revealed interesting findings. It is observed that machine learning models consistently outperform traditional models, with Random Forest and Gradient Boosting are the top performers across different sets of determinants. Moreover, the study unveils that the inclusion of foreign exchange reserves into the models as a determinant has a positive impact on the predictive effectiveness of both traditional and machine learning-based inflation forecasting models.

Multi-Step Internet Traffic Forecasting Models with Variable Forecast Horizons for Proactive Network Management.

The ISP (Internet Service Provider) industry relies heavily on internet traffic forecasting (ITF) for long-term business strategy planning and proactive network management. Effective ITF frameworks are necessary to manage these networks and prevent network congestion and over-provisioning. This study introduces an ITF model designed for proactive network management. It innovatively combines outlier detection and mitigation techniques with advanced gradient descent and boosting algorithms, including Gradient Boosting Regressor (GBR), Extreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGB), CatBoost Regressor (CBR), and Stochastic Gradient Descent (SGD). In contrast to traditional methods that rely on synthetic datasets, our model addresses the problems caused by real aberrant ISP traffic data. We evaluated our model across varying forecast horizons-six, nine, and twelve steps-demonstrating its adaptability and superior predictive accuracy compared to traditional forecasting models. The integration of the outlier detection and mitigation module significantly enhances the model's performance, ensuring robust and accurate predictions even in the presence of data volatility and anomalies. To guarantee that our suggested model works in real-world situations, our research is based on an extensive experimental setup that uses real internet traffic monitoring from high-speed ISP networks.

Prediction of Intermittent Demand Occurrence using Machine Learning

Demand forecasting plays a pivotal role in modern Supply Chain Management (SCM). It is an essential part of inventory planning and management and can be challenging at times. One of the major issues being faced in demand forecasting is insufficient forecast accuracy to predict the expected demand and fluctuation in actual vs. the predicted demand results in fore-casting errors. This problem is further exaggerated with slow-moving and intermittent demand items. Every organization encounters large proportions of items that have small ir-regular demand with long periods of zero demand, which are known as intermittent demand Items. Demand for such items occur sporadically and with considerable fluctuation in the size of the demand. Forecasting of the intermittent demand entails the prediction of demand series that is characterized by the time interval between demand being significantly greater than the unit forecast period. Because of this there are multiple periods of no demand in the intermittent demand time series. The challenge with these products with low irregular demand is that these items need to be stocked and replenished at regular interval irrespective of the demand cycle, thus adding to the cost of holding the inventory. Since the demand is not continuous, Traditional Forecasting models are unable to provide reliable estimate of required inventory level and replenishment point. Forecast errors would resulting in obsolescent stock or unfulfilled demand. The current paper presents a simple yet powerful approach for generating a demand forecasting and replenishment process for such low volume intermittent demand items to come up with a recommendation for dynamic re-order point, thus, improving the inventory performance of these items. Currently, the demand forecast is generally based on past usage patterns. The rise of Artificial Intelligence/Machine Learning (AI/ML) has provided a strong alternative to solve the problem of forecasting Intermittent Demand. The intention is to highlight that machine learning algorithm is more efficient and accurate than traditional forecasting method. As we move forward to industry 4.0, the digital supply chain is considered as the most essential com-ponent of the value chain wherein the inventory size is controlled, and the demand predicted.

Accounting journal entries as a long‐term multivariate time series: Forecasting wholesale warehouse output

AbstractLess than 2 years ago, many small entrepreneurs in the commodities trading business faced price volatility, which had not been the case for the last few decades. Generally, the income section of the profit and loss statement was not the main problem, especially in building material commodities trading, due to the recent growth in real estate demand. Logistic disorders, raw material shortages, inflation, and interest rate growth caused difficulties in supply management and warehouse balancing, which were reflected in a particular significant expense called the cost of goods sold. The real problem of its forecasting was identified, and data from accounting books likely contain information about previous warehouse dynamics. This paper presents how accounting data are prepared and shaped into time series suitable for machine learning algorithms, the relevant literature that helped in algorithm selection, and the development and description of the forecasting model, as well as its benchmarking with traditional forecasting models. Visualization and mean squared error loss measured on unseen data show that the model has proven more successful than expected. Based on data from four journal accounts spanning over 14 years, the model predicts the debit and credit sides of the wholesale warehouse for 150 working days.

ENSEMBLE OF ADAPTIVE PREDICTORS FOR MULTIVARIATE NONSTATIONARY SEQUENCES AND ITS ONLINE LEARNING

Context. In this research, we explore an ensemble of metamodels that utilizes multivariate signals to generate forecasts. The ensemble includes various traditional forecasting models such as multivariate regression, exponential smoothing, ARIMAX, as well as nonlinear structures based on artificial neural networks, ranging from simple feedforward networks to deep architectures like LSTM and transformers.&#x0D; Objective. A goal of this research is to develop an effective method for combining forecasts from multiple models forming metamodels to create a unified forecast that surpasses the accuracy of individual models. We are aimed to investigate the effectiveness of the proposed ensemble in the context of forecasting tasks with nonstationary signals.&#x0D; Method. The proposed ensemble of metamodels employs the method of Lagrange multipliers to estimate the parameters of the metamodel. The Kuhn-Tucker system of equations is solved to obtain unbiased estimates using the least squares method. Additionally, we introduce a recurrent form of the least squares algorithm for adaptive processing of nonstationary signals.&#x0D; Results. The evaluation of the proposed ensemble method is conducted on a dataset of time series. Metamodels formed by combining various individual models demonstrate improved forecast accuracy compared to individual models. The approach shows effectiveness in capturing nonstationary patterns and enhancing overall forecasting accuracy.&#x0D; Conclusions. The ensemble of metamodels, which utilizes multivariate signals for forecast generation, offers a promising approach to achieve better forecasting accuracy. By combining diverse models, the ensemble exhibits robustness to nonstationarity and improves the reliability of forecasts.

WHALE SWARM OPTIMIZATION BASED ANFIS FOR PREDICTION IN FORECASTING APPLICATION

This paper proposes a novel approach for solar power forecasting using an Adaptive Neuro-Fuzzy Inference System (ANFIS) enhanced with Whale Swarm Optimization (WSO). The synergy between ANFIS and WSO aims to overcome the limitations of traditional forecasting models by controlling the collective intelligence of a whale-inspired swarm algorithm. The WSO optimizes the parameters of the ANFIS, leading to improved accuracy in solar power predictions. The integration of WSO introduces a parallelism and exploration-exploitation balance inspired by the natural behaviors of whales, enhancing the ANFIS model’s adaptability to dynamic solar power generation patterns. The experimental results demonstrate the superiority of the proposed Whale Swarm-based ANFIS over conventional methods, showcasing its ability to handle non-linear and complex relationships in solar power data. This research contributes to the field of renewable energy forecasting by presenting an innovative hybrid model that leverages the strengths of both ANFIS and WSO for more reliable and precise solar power predictions.

A hybrid electricity load prediction system based on weighted fuzzy time series and multi-objective differential evolution

With advances in science and technology, the demand for electricity is increasing dramatically. Consequently, reliable short-term power load prediction is critical to ensure the safety, efficiency, and cost-effectiveness of electricity grids. However, owing to the volatility and randomness of power load time series, traditional forecasting models have struggled to meet the current power system requirements for load prediction precision and stability. In light of this, this study proposes a new hybrid short-term electricity load prediction system that combines the variational modal decomposition (VMD) technique, multi-objective differential evolutionary algorithm (MODE), and weighted fuzzy time series (WFTS) prediction model to increase load prediction precision and stability. Four Belgian datasets (spring, summer, autumn, and winter) were used for short-term power load prediction experiments and were compared with prevalent prediction methods. The experimental results indicate that the designed system obtains MAPESpring=0.6670%, MAPESummer=0.5835%, MAPEAutumn=0.7049%, MAPEWinter=0.7123% and STDSpring=60.2575, STDSpring=62.6573, STDSpring=72.7393, STDSpring=71.5549, which are obviously superior to the comparison models in terms of prediction accuracy and stability.

The asymmetric volatility spillover across Shanghai, Hong Kong and the U.S. stock markets: A regime weighted measure and its forecast inference

Based upon generalized spillover index method under Markov switching vector auto-regression (MS-VAR) framework, this paper aims at a regime dependent measure of the volatility spillover asymmetry across Shanghai, Hong Kong and the U.S. stock markets. For that, we apply a regime weighted measure of spillover and its asymmetry. The empirical results show that there existed evident negative asymmetric effect of spillover across the three markets, and it was regime dependent and time-varying: it got intensified under high volatility regime and turned out stronger after the Program of Shanghai-Hong Kong stock connect. The regime weighted measure of spillover asymmetry is found to be reliable; it could be explained appropriately with the economic policy uncertainty and investors' fear in the U.S., extreme shocks like crash of Shanghai stock market and COVID-19 as well as the capital flow through the Program. From in-sample evidence and out-of-sample forecast of Shanghai stock market, we infer that traditional forecast models could be improved if regime dependent spillover and its asymmetry are considered as additional factors.

Enhanced machine learning model via twin support vector regression for streamflow time series forecasting of hydropower reservoir

The non-stationary, complex, and non-linear characteristics of streamflow time series have a significant impact on the simulation results of the conventional hydrological forecasting models. To improve the performances, this paper develops an enhanced machine learning model for streamflow time series forecasting, where the twin support vector regression (TSVR) is combined with singular spectrum analysis (SSA) and grey wolf optimizer (GWO). Specially, the SSA method is set as the data preprocessing tool for pattern identification; the TSVR model is set as the basic forecasting module for each pattern and the GWO method is used as the optimizer to select feasible parameter combination. Multi-step-ahead streamflow forecasting tasks are used to examine the feasibility and predictability of the proposed model. The results indicate that the proposed model can yield superior results compared with the traditional forecasting models. Thus, a robust and reliable tool is provided for streamflow time series forecasting under uncertainty.

Long-term probabilistic streamflow forecast model with “inputs–structure–parameters” hierarchical optimization framework

Accurate, reliable, and stable streamflow forecasts are essential for risk assessment and decision making in water resources management. Owing to the limited value of deterministic forecasting, probabilistic forecasting incorporating probability and confidence intervals is achieved by optimizing the predictors and forecast equation while identifying forecast error features. The combination of deterministic forecasts and error identification can facilitate water resources management. This study improved the traditional forecast model’s inputs selection, structure designation, and error parameters calibration to propose a long-term probabilistic streamflow forecast model with hierarchical optimization of the predictors, forecast equation, and errors characteristics. The model develops information entropy theory to screen the driving predictor set, the long short-term memory (LSTM) model to conduct deterministic forecasts, and the generalized autoregressive conditional heteroskedasticity (GARCH) model to identify time-varying errors. The proposed model, used in some case studies to forecast the monthly streamflow of two lakes, Hongze and Luoma lakes in China, was evaluated using the multidimensional index method considering “accuracy–reliability–stability” performance. The results revealed the following: (1) Predictor screening based on information entropy investigates the statistical characteristics of predictors, thereby improving the reliability of streamflow forecasts. (2) The LSTM model exploits the response between the driving predictors and streamflow, whereas GARCH model identifies the time-varying features of forecast errors effectively, which reduces the probability of forecast failure and increases the accuracy and stability of probabilistic forecasts. (3) Under current meteorological observation conditions and forecasting capability, the proposed forecasts can extend the maximum forecast lead time from 1 month to 3 months. (4) The proposed model improves the accuracy (root mean square error: 6.7%–34.8%), reliability (Brier score: 15.3%–27.9%), and stability (mistaken distance: 36.4–52.6%) in comparison with the benchmark of the two case studies, indicating that “inputs–structure–parameters” hierarchical optimization provides effective forecast information for water resources management.

A hybrid model of neural network with VMD–CNN–GRU for traffic flow prediction

An effective traffic flow prediction can serve as a foundation for control decisions on intelligent transportation. However, in view of the nonstationarity and complexity of traffic flow sequences, it is impossible to fully extract the dynamic change laws of time-series based on traditional forecasting models. Traffic flow data are often disturbed by noise during the collection. The existence of noise data may affect the features of the sequence itself or cover the real change trend of the series, resulting in the decline of prediction reliability. A hybrid prediction model based on variational mode decomposition–convolutional neural network–gated recurrent unit (VMD–CNN–GRU) is presented to increase the predictability of traffic flow, which is combined by VMD, CNN and GRU. First, the original time-series is decomposed into K components by VMD, and the noise part is eliminated to improve the modeling accuracy. Next, the time characteristics of traffic flow are mined by constructing the CNN–GRU network in Keras, a deep learning framework. Each sub-sequence is trained and predicted separately as an input vector. The total expected value of traffic flow is then calculated by superimposing the predicted value of each subsequence. The model performance is verified by the open-source dataset of actual England highways. The results show that compared with other models, the hybrid model established in this paper significantly raises the precision of traffic flow forecasting. The results could offer some useful insights for predicting traffic flow.

A Novel First-Order Fuzzy Rules-Based Forecasting System Using Distance Measures Approach for Financial Market Forecasting

The precise estimates about finance, atmospheric science, power sector, industries, agriculture, and other science help governments and institutions economically in making the relevant policies regarding import-export, demand, consumption, storage, and local industries. Due to the uncertainty and nondeterministic behavior of data series with respect to time, the foremost challenge is to develop and identify the practical method to handle the above stated complex issues. As an illustration, this study presented an analysis of a new fuzzy time-series (FTS) approach and comparison with traditional forecasting models for prediction of gram pulse production. Taking into consideration the theory of fuzzy sets, FTS, fuzzy rules, triangular membership functions, distance measures, and modified weighted average method, a robust and effective fuzzy rules-based methodology was developed for the prediction of time-series data regarding crop production and share prices. Conventional statistical forecasting methods such as Holt’s linear trend, Holt’s exponential trend, and Holt’s damped exponential trend models were also applied on time-series data for comparison. To identify the primacy of modeling and forecasting, the techniques of root mean squared error (RMSE) and mean absolute error (MAE) were used as a criterion. The numerical values of RMSE and MAE such as 106.51 and 74.8897 clearly demonstrated that the proposed fuzzy rules-based method is robust for forecasting of production and market share prices in the environment of uncertainty.

RF-BiLSTM Neural Network Incorporating Attention Mechanism for Online Ride-Hailing Demand Forecasting

Accurately predicting online ride-hailing demand can help operators allocate vehicle resources on demand, avoid idle time, and improve traffic conditions. However, due to the randomness and complexity of online ride-hailing demand data, which are affected by many factors and mostly time-series in nature, it is difficult to forecast accurately and effectively based on traditional forecasting models. Therefore, this study proposes an online ride-hailing demand forecasting model based on the attention mechanism of a random forest (RF) combined with a symmetric bidirectional long short-term memory (BiLSTM) neural network (Att-RF-BiLSTM). The model optimizes the inputs and can use past and future data to forecast, improving the forecasting precision of online ride-hailing demand. The model utilizes a random forest to filter and optimize the input variables to reduce the neural network complexity, and then an attention mechanism was incorporated into the BiLSTM neural network to construct a demand forecasting model and validate it using actual Uber pickup data from New York City. Compared with other forecasting models (Att-XGBoost-BiLSTM, Att-BiLSTM, and pure LSTM), the results show that the proposed symmetrical Att-RF-BiLSTM online ride-hailing demand forecasting model has a higher forecasting precision and fitting degree, which indicates that the proposed model can be satisfactorily applied to the area of online ride-hailing demand.