Time Series Forecasting Research Articles

Dengue Prediction using Short-Term Memory

Dengue is a severe infectious disease on the rise in Malaysia, and there is a demand for artificial intelligence to support the health system. However, the application of deep learning, specifically Long Short-Term Memory (LSTM) time series forecasting, has not been explored by many in dengue prediction studies. However, considering the availability of daily weather data being collected, the ability of LSTM to capture long term dependencies can be leveraged in forecasting dengue cases. Therefore, this study investigates the performance and viability of LSTM time series forecasting on predicting dengue cases. An LSTM model is developed and evaluated to be compared to a Support Vector Regression (SVR) model by utilising the availability of a dengue dataset consisting of weather and climate data. The results indicated LSTM time series forecasting performed better than SVR, with R2 and MAE scoring 0.75 and 8.76. In short, LSTM has shown better performance and, in addition, capturing trends in the rise and fall of dengue cases. Altogether, this research could contribute to the fight against the increase of dengue cases without relying on forecasted weather data but instead, history.

Cyber Attacks Detection And Mitigation Using Machine Learning In Smart Grid Systems

The increasing complexity and interconnectedness of smart grid systems have heightened their vulnerability to cyber threats, necessitating advanced solutions for securing these critical infrastructures. This study aims to explore the potential of AI-driven predictive analytics in enhancing the cybersecurity and operational efficiency of smart grids. By leveraging the systematic approach of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a comprehensive review of 1,526 initial articles was conducted, which was subsequently narrowed down through rigorous screening and evaluation to a final set of 127 high-quality studies. The review reveals that machine learning models, such as neural networks and time series forecasting, significantly enhance the early detection and mitigation of cyber threats, allowing grid operators to take proactive measures to safeguard against disruptions. Additionally, the integration of AI with real-time data analytics was found to optimize load forecasting, predict equipment failures, and improve overall grid resilience, leading to reduced downtime and operational costs. However, significant challenges related to data privacy, scalability, and integration with legacy systems persist. The findings suggest that techniques like federated learning and blockchain integration could address these challenges, though further research is needed to enhance model robustness and efficiency. This review provides critical insights into the practical applications of AI in smart grid cybersecurity, highlighting both the benefits and the barriers that must be overcome to achieve widespread adoption.

Predictive Modeling for Bike Rental Demand: Enhancing Operational Efficiency and User Satisfaction in Urban Mobility

This project focuses on developing a predictive model to forecast bike rental demand by analyzing historical rental data, weather information, and temporal variables. The model will employ machine learning techniques, such as regression analysis, time series forecasting, and ensemble methods, to capture the complex relationships between these factors and rental demand.

Forecasting economic growth by combining local linear and standard approaches

Today, developing economies are of major importance for global macroeconomic development. However, the empirical analysis and especially the forecasting of macroeconomic time series remain difficult due to a lack of sufficient data, data frequency, high volatility, and non-linear developments. These difficulties require more sophisticated approaches to obtain reliable forecasts. Therefore, we propose an improved forecasting method especially for growth data based on a data-driven local linear trend estimation with an extended iterative plug-in algorithm for determining the bandwidth endogenously. This approach allows a smooth trend estimation that takes care of temporary changes in trend processes. Further, the naïve random walk model is extended for forecasting by including a local linear, time-varying drift. We apply this method to GDP development for six developing and two advanced economies and compare different forecast combinations. The combinations that include the local linear approach and the random walk with a local linear trend improve forecasting accuracy and reduce variance.

Big Data Analytics for Forecasting Tourism Recovery in Bali Island Using Multivariate Time Series

Bali is a famous tourist area and can significantly contribute to the Indonesian tourism sector. The COVID-19 pandemic has made Indonesian tourism, including Bali tourism, experience a decline. In March 2022, COVID-19 cases decreased, and the government began to relax some policies. The tourism sector is vital in economic recovery efforts after the COVID-19 pandemic. Therefore, it is necessary to identify tourism recovery to determine strategies and policies related to Indonesian tourism, especially in Bali. Multivariate time series forecasting of tourism demand can be used to identify tourism recovery using several significant data sources. The methods used are Vector Autoregressive (VAR), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The data used are the monthly official number of tourists, room occupancy rate, Google Trends, number of booking.com user reviews, and nighttime light intensity in Bali Province from January 2019 to December 2022. The results show that the best forecasting method is VAR, and modeling with multivariate time series forecasting can improve the performance of forecasting results. In addition, big data can be used as a source of supporting data that can provide better forecasting results, and the size of the dataset affects the selection of the best model. Furthermore, the descriptive and forecasting analysis results show that Bali tourism has experienced post-pandemic tourism recovery. The strategies and policies of the Bali government to restore Bali tourism faster are good enough.

Forecasting techniques based on the use of time series models for forecasting expenditures on social protection and social security

In the context of a military conflict, it is growing the number of people who are in difficult life circumstances and need state assistance. Therefore, the issue of forecasting spending on social protection and social security is becoming increasingly relevant. The aim of the paper is to consider modern methods of analyzing and forecasting time series and propose their application to determine the need for spending on social protection and social security. The article provides a brief overview of regression models, their advantages and features of use for analyzing and predicting nonlinear and linear processes described by time series of statistical indicators used in the population social protection system. The paper offers a combination of predictions that can be made based on locally linear and nonlinear models, such as threshold autoregression (TAR) and exponential autoregression (ExAR), which have known quality characteristics. This approach primarily concerns time series that contain data on structural changes in the analyzed processes. Using combined predictions, it is possible to estimate the contribution of each component for both different and selected time points using variable weights. To build forecasts, depending on the scenario of distribution of social protection and social security expenditures, it is proposed to use Bayes networks. Their advantages are flexibility, high quality of results, the possibility of structural and parametric optimization and adaptation to new data and conditions, support for quality assessment by appropriate sets of statistical criteria, which makes it possible to analyze thoroughly intermediate and final results. It helps to increase the adequacy of models and the high quality of the final result of their application.

IFNN: Intuitionistic Fuzzy Logic Based Neural Network Model for Time Series Forecasting

IFNN: Intuitionistic Fuzzy Logic Based Neural Network Model for Time Series Forecasting

CAST: An innovative framework for Cross-dimensional Attention Structure in Transformers

Dominant Transformer-based approaches rely solely on attention mechanisms and their variations, primarily emphasizing capturing crucial information within the temporal dimension. For enhanced performance, we introduce a novel architecture for Cross-dimensional Attention Structure in Transformers (CAST), which presents an innovative approach in Transformer-based models, emphasizing attention mechanisms across both temporal and spatial dimensions. The core component of CAST, the cross-dimensional attention structure (CAS), captures dependencies among multivariable time series in both temporal and spatial dimensions. The Static Attention Mechanism (SAM) is incorporated to simplify and enhance multivariate time series forecasting performance. This integration effectively reduces complexity, leading to a more efficient model. CAST demonstrates robust and efficient capabilities in predicting multivariate time series, with the simplicity of SAM broadening its applicability to various tasks. Beyond time series forecasting, CAST also shows promise in CV classification tasks. By integrating CAS into pre-trained image models, CAST facilitates spatiotemporal reasoning. Experimental results highlight the superior performance of CAST in time series forecasting and its competitive edge in CV classification tasks.

ATPAM: Adversarial Temporal Pattern Attention Mechanism

Abstract. Time series forecasting has a large number of applications in daily life, for instance the prediction of stock prices, electricity consumption, exchange rate changes etc. However, the existing time series prediction methods have limitations. The most significant one is that when all the prediction models get the predicted value, a new round of iteration starts after the loss function is calculated with the corresponding real data. This may cause the accumulation of errors, since there is only one loss function to measure the difference between the predicted value and the ground truth, it will make the connection weak and mainly depend on the accuracy of the prediction model. Unfortunately, there are few time series prediction models with high accuracy in reality. To solve the issue, in this paper, we propose a new time series forecasting model Adversarial Temporal Pattern Attention Mechanism (ATPAM), which based on Generative Adversarial Nets (GANs). ATPAM adopts a Temporal Pattern Attention model as the generator to learn time-invariant temporal patterns, and use a discriminator to improve the prediction performance and do auxiliary adversarial training. Extensive experiments on several real-world datasets show the effectiveness of our method.

Explainable deep learning on multi-target time series forecasting: an air pollution use case

Urban air pollution represents a significant threat to public health and the environment, with nitrogen oxides, ozone, and particulate matter being among the most harmful pollutants. These contribute to respiratory and cardiovascular diseases, particularly in urban areas with high traffic and elevated temperatures. Machine learning, especially deep learning, shows promise in enhancing the prediction accuracy of prediction of pollutant's concentrations. However, the “black box” nature of these models often limits their interpretability, which is crucial for informed decision-making. Our study introduces a Temporal Selection Layer technique within deep learning models for time series forecasting to tackle this issue. This technique not only improves prediction accuracy by embedding feature selection directly into the neural network, but also enhances interpretability and reduces computational costs. In particular, we applied this method to hourly concentration data of pollutants, including particulate matter, ozone, and nitrogen oxides, from five urban monitoring sites in Graz, Austria. These concentrations were used as target variables to predict, while identifying the most relevant features and periods that affect prediction accuracy. Comparative analysis with other embedded feature selection methods showed that the Temporal Selection Layer significantly enhances both model effectiveness and transparency. Additionally, we applied explainable techniques to evaluate the impact of weather and time-related factors on air pollution, which also helped assess feature importance. The results show that our approach improves both prediction accuracy and model interpretability, leading finally to more effective pollution management strategies.

Forecast of consumption of natural gas in U.S. based on time series analysis and ARIMA model

Natural gas is a widely used fossil fuel, playing a vital role in both industrial and economic sectors. As a widely used fossil fuel, the prediction of natural gas consumption is crucial for industrial and economics and hence many scholars have been researched on the topic. Due to the weather variation and the sensitivity of industrial demand, a precise consumption forecast is difficult. In the article, ARIMA model, a widely used model in time series analysis and forecasts would be considered in the prediction for consumption for future one year. It turns out that, in the next year, the consumption of natural gas in the coming year is stable and will stay at a still level and the overall trend of the series is increasing, with no significant short-term fluctuations. Therefore, the article suggested that long-term investment in industries related to natural gas is recommended. Besides, short-term investment is not suggested compared to the long-term due to the still level of the consumption within one year.

Interpretable Multi-Horizon Time Series Forecasting of Cryptocurrencies by Leverage Temporal Fusion Transformer

This research delves into the obstacles and difficulties associated with predicting cryptocurrency movements in the volatile global financial market. This study develops and evaluates an advanced Deep Learning-Enhanced Temporal Fusion Transformer (ADE-TFT) model to estimate Bitcoin values more accurately. This research employs cutting-edge artificial intelligence (AI) and machine learning (ML) techniques to comprehensively examine various aspects of cryptocurrency forecasting, including geopolitical implications, market sentiment analysis, and pattern detection in transactional datasets. The study demonstrates that the ADE-TFT model outperforms its lower-layer counterparts in terms of forecasting accuracy, with reduced Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and Root Mean Square Error (RMSE) values, particularly when using a higher hidden layer configuration (h=8). The study emphasizes the importance of experimenting with different normalization strategies and utilizing various market-related data to enhance the model's performance. The results suggest that improving forecasting accuracy may require addressing these limitations and incorporating additional factors, such as market sentiment. By providing investors with more precise market predictions, the techniques and information presented in this research have the potential to significantly increase investor power in an unpredictable digital currency market, enabling wise investment choices.

The Capacity and Robustness Trade-Off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting

The Capacity and Robustness Trade-Off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting

Multi-Resolution Expansion of Analysis in Time-Frequency Domain for Time Series Forecasting

Multi-Resolution Expansion of Analysis in Time-Frequency Domain for Time Series Forecasting

AutoML and Automated Data Science by Democratizing AI through End-to-End Automation

The rise of data-driven decision-making has led to a significant demand for data science and machine learning (ML) solutions across industries. However, developing these solutions requires extensive expertise in data preprocessing, feature engineering, model selection, hyperparameter tuning and evaluation. AutoML (Automated Machine Learning) and Automated Data Science (AutoDS) have emerged as transformative approaches that aim to democratize data science by automating the endto-end ML pipeline. This paper explores the foundational concepts of AutoML, highlighting key techniques and algorithms, such as neural architecture search (NAS), hyperparameter optimization and meta-learning. We delve into AutoDS's broader scope, which seeks to fully automate tasks from data acquisition to deployment. Real-world applications, such as predictive modeling, anomaly detection and time series forecasting, are examined to demonstrate the impact of these technologies. Additionally, the paper analyzes the current frameworks and platforms facilitating automation, including Auto-sklearn, Google AutoML and H2O.ai and evaluates their performance across different tasks. While the potential to accelerate data science workflows and make AI accessible to non-experts is evident, challenges remain, particularly regarding transparency, interpretability and ethical considerations in fully automated systems. This research provides insights into current trends, future opportunities and the transformative role of AutoML and AutoDS in driving innovation in the data science landscape.

MAML-Enhanced LSTM for Air Quality Time Series Forecasting

MAML-Enhanced LSTM for Air Quality Time Series Forecasting

Evaluation of the implementation of Main Distribution Material (MDU) spare part procurement at seven customer service unit (ULP) in Semarang are using ABC analysis and time series forecasting

Evaluation of the Implementation of Main Distribution Material (MDU) Spare Part Procurement at Seven Customer Service Units (ULP) in Semarang Area using ABC Analysis and Time Series Forecasting (Case Study: PT PLN (Persero) UP3 Semarang) Time series forecasting is a method used to predict the number of future needs in a time series. This research was conducted at the company PT PLN (Persero) UP3 Semarang, where the author tried to deal with the company's problems related to the procurement of Main Distribution Material (MDU) which often occurs overstock or lack of stock. The author uses ABC analysis to classify goods based on value ratings ranging from the highest value so that three parts with group A are obtained for forecasting, kWH meters, 2 × 10 mm2 PWR cables, and 4A MCBs. Forecasting is done with four methods, the Multiplicative Decomposition method, the Holt-Winters method, the Moving Average method, and the Exponential Smoothing method. From the results of the error calculation, it is obtained that the Holt-Winters method obtains the lowest percentage error with results of 10% - 20% or is good to use for forecasting. The comparison between the forecasting results and the overall actual demand is above 70%, which means that the forecasting results are close to the actual demand that occurs, thus increasing the accuracy of the Holt-Winters forecasting method. Suggestions for improvement that can be given to the company are to apply the Holt-Winters forecasting method in forecasting MDU spare part inventory at PT PLN (Persero) UP3 Semarang.

Machine Learning Algorithms Based on Time Series Pre-Clustering for Nocturnal Glucose Prediction in People with Type 1 Diabetes.

Background: Machine learning offers new options for glucose prediction and real-time glucose management. The aim of this study was to develop a machine learning-based algorithm that takes into account glucose dynamics patterns for predicting nocturnal glucose in individuals with type 1 diabetes. Methods: To identify glucose patterns, we applied a hierarchical clustering algorithm to real-time continuous glucose monitoring data obtained from 570 adult patients. Machine learning algorithms with or without pre-clustering were used for modeling. Results: Eight clusters without nocturnal hypoglycemia and six clusters with at least one low-glucose episode were identified by the cluster analysis. When forecasting time series without hypoglycemia with a prediction horizon (PH) of 15 or 30 min, gradient boosting trees (GBTs) with pre-clustering and random forest (RF) with pre-clustering outperformed algorithms based on medoids of time series clusters, the Holt model, and GBTs without pre-clustering. When forecasting time series with low-glucose episodes, a model based on the pre-clustering and GBTs provided the highest predictive accuracy at PH = 15 min, and a model based on RF with pre-clustering was the best at PH = 30 min. Conclusions: The results indicate that the clustering of glucose dynamics can enhance the efficacy of machine learning algorithms used for glucose prediction.

Assessing the Profit Impact of ARIMA and Neural Network Demand Forecasts in Retail Inventory Replenishment

This study investigates the integration of demand forecasting and inventory replenishment strategies to enhance retail profitability. A deterministic optimal replenishment model is utilized to analyze the predictive performance of various neural network architectures and ARIMA models using real sales data. The predictive accuracy and subsequent influence on optimal firm profits over a multi-period planning horizon is assessed. The Integer Programming model devised optimizes daily replenishment across multiple retail routes, taking into account sales revenue, supply costs, inventory holding, sales loss, and transportation expenses. The study is distinctive in its dual assessment: it evaluates both the accuracy of forecasting methods and their direct impact on profitability through systematic inventory decisions. Neural network architectures selected for minimizing error in product sales predictions have 6% lower mean squared error compared to Akaike Information Criterion minimizing ARIMA models. For longer horizon predictions necessary in performance gap grows larger, e.g., with %60 difference for predictions 15 days ahead. Predictions reflect as 1.6% higher profits on average, when neural network predictions and more efficient longer planning horizons of the optimization model are preferred. Planning 30 days ahead, optimizing with neural network predictions elicits 2.3% higher profits compared to profits attainable based on ARIMA predictions. Our findings illustrate how different forecasting methods can affect firm profitability by shaping inventory replenishment strategies. By merging mathematical optimization with time series forecasting, this research provides a comprehensive evaluation of how advanced predictive technologies can enhance retail inventory practices and improve profitability.

An XGBoost Approach to Predictive Modelling of Rift Valley Fever Outbreaks in Kenya Using Climatic Factors

Reports of Rift Valley fever (RVF), a highly climate-sensitive zoonotic disease, have been rather frequent in Kenya. Although multiple empirical analyses have shown that machine learning methods outperform time series models in forecasting time series data, there is limited evidence of their application in predicting disease outbreaks in Africa. In recent times, the literature has reported several applications of machine learning in facilitating intelligent decision-making within the healthcare sector and public health. However, there is a scarcity of information regarding the utilization of the XGBoost model for predicting disease outbreaks. Within the provinces of Kenya, the incidence of Rift Valley fever was more prominent in the Rift Valley (26.80%) and Eastern (20.60%) regions. This study investigated the correlation between the occurrence of RVF (rapid vegetation failure) and several climatic variables, including humidity, clay content, elevation, slope, and rainfall. The correlation matrix revealed a modest linear dependence between different climatic variables and RVF cases, with the highest correlation, a mere 0.02903, observed for rainfall. The XGBoost model was trained using these climate variables and achieved outstanding performance measures including an AUC of 0.8908, accuracy of 99.74%, precision of 99.75%, and recall of 99.99%. The analysis of feature importance revealed that rainfall was the most significant predictor. These findings align with previous studies demonstrating the significance of weather conditions in RVF outbreaks. The study’s results indicate that incorporating advanced machine learning models that consider several climatic variables can significantly enhance the prediction and management of RVF incidence.