Demand Forecasting Research Articles

Advancing predictive analytics models for supply chain optimization in global trade systems

Global trade systems are becoming increasingly complex due to interconnected markets, fluctuating demand, geopolitical uncertainties, and sustainability concerns. Predictive analytics offers transformative potential in optimizing supply chain operations by leveraging data-driven insights for proactive decision-making. This explores the advancements in predictive analytics models tailored for global trade systems, emphasizing their role in enhancing supply chain efficiency, resilience, and agility. By integrating machine learning algorithms, big data analytics, and real-time data feeds, these models enable accurate forecasting of demand, inventory levels, and transportation routes. Key innovations include the incorporation of artificial intelligence (AI) for pattern recognition, predictive maintenance of assets, and dynamic route optimization. The use of ensemble modeling and deep learning enhances the predictive accuracy, while adaptive algorithms accommodate evolving market trends and disruptions. The review also highlights the challenges of data silos, scalability, and model interpretability, which hinder the full potential of predictive analytics in global supply chains. Ethical considerations such as data privacy and fairness in AI-driven decision-making are addressed to ensure responsible model implementation. Case studies from various industries demonstrate how advanced predictive models mitigate risks, reduce costs, and improve sustainability by optimizing resource utilization and reducing carbon footprints. Emerging trends, such as the integration of blockchain for transparent data sharing and IoT for real-time monitoring, further enrich the predictive capabilities. This underscores the critical need for collaborative frameworks between stakeholders, continuous innovation, and investment in analytical capabilities to future-proof supply chains. By advancing predictive analytics, global trade systems can achieve a new paradigm of efficiency and resilience in a volatile and competitive landscape. Keywords: Predictive Analytics, Models, Supply Chain Optimization, Global Trade Systems.

Cloud-Enabled Innovation in Retail: Transforming Inventory Management and Demand Forecasting

This comprehensive article explores the transformative impact of cloud computing technologies on the retail industry, examining core platform solutions, implementation strategies, and future trends. The article investigates how cloud integration has revolutionized inventory management, demand forecasting, and operational efficiency across the retail sector. Through detailed case studies of major retailers, the research demonstrates the substantial benefits of cloud adoption in areas such as real-time data processing, predictive analytics, and supply chain optimization. The article encompasses technical considerations, best practices, and emerging technologies, providing insights into successful implementation strategies and operational guidelines. The article further evaluates the integration opportunities and standardization initiatives shaping the future of retail cloud computing, highlighting the critical role of artificial intelligence, blockchain, IoT, and advanced analytics in driving industry innovation.

The Impact of Demand Forecasting Accuracy on Customer Satisfaction

Purpose: The aim of the study was to analyze the impact of demand forecasting accuracy on customer satisfaction Methodology: This study adopted a desk methodology. A desk study research design is commonly known as secondary data collection. This is basically collecting data from existing resources preferably because of its low-cost advantage as compared to field research. Our current study looked into already published studies and reports as the data was easily accessed through online journals and libraries. Findings: Accurate demand forecasting significantly enhances customer satisfaction by reducing stockouts, improving delivery reliability, and aligning inventory with consumer needs. Advanced predictive models, such as AI and machine learning, enable businesses to adapt to market dynamics, fostering trust and loyalty. Studies show improved repeat purchase rates and customer retention, highlighting forecasting precision as crucial for competitive advantage. Unique Contribution to Theory, Practice and Policy: Resource-Based View (RBV) Theory, Expectancy-Disconfirmation Theory (EDT) and Systems Theory in supply chain and management maybe used to anchor future studies on the impact of demand forecasting accuracy on customer satisfaction. Research should focus on developing integrative frameworks that combine demand forecasting accuracy with customer satisfaction metrics, emphasizing the role of advanced technologies like AI and machine learning. Companies should also invest in training programs to equip supply chain professionals with the skills to utilize advanced forecasting tools effectively. Governments and regulatory bodies should establish guidelines to encourage secure data sharing between supply chain stakeholders, enhancing forecasting accuracy

Demand Forecasting for Agro Tech Technical Textiles

Demand forecasting is vital in the agrotech industry, merging technology with agriculture to drive innovation and efficiency. Accurate forecasting helps companies predict market trends, optimize resource use, and enhance operations. By anticipating future demand for agricultural products and technological solutions, businesses can make informed decisions on production, inventory, and marketing. However, demand forecasting in agrotech faces challenges such as seasonal variations, limited data, technological complexity, and market uncertainties. Factors like weather patterns, regulatory changes, and shifting consumer preferences add to the difficulty. To address these challenges, methodologies such as statistical techniques, data analytics, and machine learning are employed. Common methods include time series analysis, regression analysis, and hybrid techniques, which use historical data to forecast future trends. Effective demand forecasting improves resource planning, supply chain management, and customer satisfaction. Aligning production with expected demand and optimizing inventory can cut costs, reduce waste, and boost competitiveness. Demand forecasting is essential for strategic planning in agrotech, enabling businesses to predict market trends, meet customer needs, and achieve sustainable growth in a dynamic environment.

AI-Driven Optimization of Last-Mile Delivery

The optimization of last-mile delivery represents a critical challenge in modern e-commerce logistics, consuming a substantial portion of total shipping costs. This comprehensive technical article examines how artificial intelligence and machine learning technologies are revolutionizing last-mile delivery operations through advanced route optimization, demand forecasting, and resource allocation. This article synthesizes findings from recent implementations across major logistics providers, demonstrating that AI-driven route optimization systems significantly reduce delivery times and decrease fuel consumption across diverse operational environments. Analysis of machine learning models deployed by leading e-commerce platforms shows marked improvements in delivery time prediction accuracy, achieving unprecedented precision in estimated delivery windows. This article examines key technical components, including dynamic routing algorithms, predictive demand modeling, and real-time fleet management systems, while also addressing implementation challenges such as data quality and system integration. Case studies from major logistics providers demonstrate substantial ROI improvements following AI implementation, with particular emphasis on neural network architectures optimized for urban delivery scenarios. This article provides a technical framework for understanding how AI technologies transform last-mile logistics while offering insights into future developments, including autonomous delivery systems and smart city integration.

The use of Artificial Intelligence in the restaurant business

The study aimed to explore how artificial intelligence (AI) is applied in the restaurant industry, particularly in enhancing operational efficiency, personalizing customer interactions, and predicting demand. Using qualitative methods, interviews were conducted with industry experts in Odesa, Ukraine, including professionals from major chains and a case study with a Ukrainian chef. Findings revealed that global brands like McDonald’s, Starbucks, and Marriott use AI for demand forecasting, offer personalization, and streamlining communication. Chef Yevhen Klopotenko’s use of AI to prepare a gourmet dinner showcased its innovative potential in cuisine. The research enriches the existing literature on AI in hospitality with practical examples, offering valuable insights for industry professionals. It highlights the significance of AI in predicting demand and automating customer interactions to boost efficiency. The originality of the study lies in its analysis of AI applications and its comprehensive list of AI tools for content generation. However, the qualitative focus and regional scope limit generalizability, suggesting future research could broaden to include other regions and quantitative methods.

Harnessing Technology for Enhanced Efficiency in Supply Chain Operations

The international supply chain environment is quickly changing due to innovations that are reinventing not just the method companies operate. Artificial Intelligence (AI), Internet of Things (IoT), Blockchain, And Automation are some technologies that change the supply chains with more efficiency, better decisions, and live views. The technologies simplify processes like inventory management, demand forecasting, order fulfillment, and logistics optimization, which can keep businesses ahead of the competition in a fast-paced global marketplace. In this paper, we look at how organizations use these technologies to drive operational excellence, entitlement, and responsiveness to customer demand. The report presents some case studies of the successful applications of these technologies and talks about what companies are facing when incorporating these new systems into their existing supply chain process. It also explores strategic best practices in addressing these challenges, beginning with defining clear goals, aligning technology, and ensuring their workforces are ready for change. Finally, the paper looks at the future for supply chain technology. With burgeoning trends such as hyper-automation (driven by AI and IoT), we can expect things to keep improving and improving supply chain performance in years to come. The results show that despite challenges, successfully implementing these technologies increases efficiency and reduces costs, improving customer satisfaction and providing firms with a sustainable comparative advantage. Keywords Supply Chain Management, Technology, Artificial Intelligence, Internet of Things, Blockchain, Automation, Operational Efficiency, Demand Forecasting, Logistics, Inventory Management, Hyper-Automation.

Evaluating Artificial Intelligence Models for Resource Allocation in Circular Economy Digital Marketplace

This study assesses the application of artificial intelligence (AI) algorithms for optimizing resource allocation, demand-supply matching, and dynamic pricing within circular economy (CE) digital marketplaces. Five AI models—autoregressive integrated moving average (ARIMA), long short-term memory (LSTM), random forest (RF), gradient boosting regressor (GBR), and neural networks (NNs)—were evaluated based on their effectiveness in predicting waste generation, economic growth, and energy prices. The GBR model outperformed the others, achieving a mean absolute error (MAE) of 23.39 and an R2 of 0.7586 in demand forecasting, demonstrating strong potential for resource flow management. In contrast, the NNs encountered limitations in supply prediction, with an MAE of 121.86 and an R2 of 0.0151, indicating challenges in adapting to market volatility. Reinforcement learning methods, specifically Q-learning and deep Q-learning (DQL), were applied for price stabilization, resulting in reduced price fluctuations and improved market stability. These findings contribute a conceptual framework for AI-driven CE marketplaces, showcasing the role of AI in enhancing resource efficiency and supporting sustainable urban development. While synthetic data enabled controlled experimentation, this study acknowledges its limitations in capturing full real-world variability, marking a direction for future research to validate findings with real-world data. Moreover, ethical considerations, such as algorithmic fairness and transparency, are critical for responsible AI integration in circular economy contexts.

Reduction of Transportation Cost: Examinig the Moderating Role of Artificial Intelligence (AI) Implementation in Bangladesh

This study investigates the role of logistics strategies Route and Node Optimization, Shipment Consolidation, and Demand Forecasting in reducing transportation costs in the logistics sector of Bangladesh. It also explores the moderating effect of Artificial Intelligence (AI) on the effectiveness of these strategies. With the increasing complexity of logistics operations and the growing need for cost-efficient practices, this research highlights how traditional logistics methods can be augmented with advanced AI technologies to optimize operations and achieve significant cost reductions. Data were collected through structured surveys involving 300 respondents from logistics companies in Bangladesh. Using Principal Component Analysis (PCA) and Multiple Regression Analysis, the relationships between the independent variables (logistics strategies), the moderating variable (AI implementation), and the dependent variable (Transportation Cost Reduction) were evaluated. The results reveal that Shipment Consolidation had the most significant impact on transportation cost reduction, followed by Demand Forecasting and Route and Node Optimization. AI implementation was found to positively moderate these relationships, enhancing the efficiency of each strategy. The findings underscore the transformative potential of AI in logistics operations, particularly in developing economies. The study contributes to both theory and practice by providing actionable recommendations for integrating AI into logistics to achieve cost efficiency. Future research directions are suggested, including exploring longitudinal impacts and expanding the study scope to other regions.

Machine learning‐based multivariate forecasting of electric vehicle charging station demand

AbstractThe exponential rise of electric vehicles (EVs) is transforming the global automobile industry, driving a shift towards greater cleanliness and environmental sustainability. EV charging stations (EVCSs) play a pivotal role in this massive transition towards EVs, where accurate forecasting of EVCS demand is crucial for seamlessly integrating EVs into existing power grids. Most of the existing research mainly concentrates on univariate forecasting, neglecting the multiple factors influencing EVCS demand. Hence, this study offers a comparative analysis of different algorithms for univariate forecasting and multivariate forecasting, where the multivariate scheme incorporates metadata such as charging time, greenhouse gas savings, and gasoline savings. The experimental results indicate the superiority of the multivariate scheme over the univariate forecasting. For multivariate forecasting, the gated recurrent unit (GRU) has outperformed other models such as categorical boosting (Catboost), recurrent neural network (RNN), long short‐term memory (LSTM), extreme gradient boosting (XGBoost), random forest, convolutional neural network (CNN), CNN + LSTM, and LSTM + LSTM. The results of this study emphasize the significance of using the GRU model for multivariate forecasting with metadata during normal and noisy scenarios to yield more reliable and accurate predictions. This approach enhances decision‐making, policy development, and efficient grid integration in the growing EV sector.

Optimizing warehouse management system with blockchain and machine learning predictive data analytics

Blockchain technology is proving to be a disruptive technology in many areas of supply chain, manufacturing, medical, agriculture, and so on. Warehouses are an inevitable part of the supply chain. Issues like space optimization, route optimization, quick item pick-up, demand forecasting, and transaction management are of importance to address in warehouse management systems (WMS). Traditional database systems have limitations of interoperability among different entities involved in warehouses. This paper presents an innovative application of blockchain technology and machine learning (ML) to build a smart warehouse management system in Web3 (SWMW3). We developed a decentralized application (DApp) using Web3.0 principles, integrating ReactJS for the frontend, express for the backend, and blockchain through smart contracts. This integration enhances security and transparency by storing WMS operational data in the blockchain and automating payments and verifications through smart contracts. Additionally, we implemented a ML model for predicting the total time from order receipt to delivery, leveraging historical data to optimize workflow, reduce delays, and improve overall efficiency. This combination of blockchain for secure transactions and ML for predictive analytics generates a robust, efficient, and optimized management system for the warehouse.

Forecasting Strategies in Retail: Utilizing Advanced Machine Learning Methods while Safeguarding Privacy

Abstract Demand forecasting is critical to optimizing retail inventory management, pricing, and operations. This study compares several time series forecasting models on a publicly available retail dataset, including traditional stats like ARIMA and SARIMA, smoothing techniques, and new ones from Facebook, such as Prophet and Neural Prophet. We evaluate each model using metrics like Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R2. The results show that NeuralProphet and hybrid models outperform traditional models like ARIMA and SARIMA. We also look at the computational efficiency and practicality of the models and provide insights into how they can be used in real-world demand forecasting scenarios. The results show that traditional models are robust. Still, advanced models like NeuralProphet and hybrids, which combine machine learning with time series forecasting, have a lot of potential to improve forecast accuracy and operational decision-making.

Machine learning-based performance prediction for energy storage medium-deep borehole ground source heat pump systems

With the rapid development of artificial intelligence, data-driven prediction models play an important role in energy demand forecasting and performance prediction. This study established performance prediction models for medium-deep borehole ground source heat pump (MDB-GSHP) systems to predict the coefficient of performance (COP) of GSHP, utilizing back propagation neural network (BPNN), extreme learning machine (ELM), support vector machine (SVM), and particle swarm optimization-support vector machine (PSO-SVM) method that optimizes the penalty parameter (C), insensitive loss parameter (ε), and kernel parameter (γ) of SVM using PSO. Operational data were collected through field experiments, and typical parameters were selected as features to establish the feature set. The feature set was then optimized using Pearson correlation analysis and recursive feature elimination (RFE), resulting in the creation of five distinct feature sets. Error analysis and trend evaluation results indicate that the combined feature set (FS5), which incorporates the advantages of multiple feature selection methods, demonstrates the best performance. The PSO-SVM model exhibits outstanding performance under various input conditions, achieving an accuracy of over 90% within the error range. When using FS5, the PSO-SVM model achieves a mean absolute percentage error (MAPE) of 0.037, mean absolute error (MAE) of 0.103, root mean square error (RMSE) of 0.125, coefficient of multiple determinations (R2) of 0.970, and explained variance score (EVS) of 0.967, showcasing excellent predictive performance. The research results can provide a basis for the formulation of storage-related operational parameters and the optimization of system operation for energy storage in MDB-GSHP heating systems.

Demand Forecasting for Aqua Tech Technical Textiles

Demand forecasting plays a significant role in the Aquatech industry, where innovation integration with aquacultural practices drives efficiency and effectiveness. This abstract outline the importance, challenges, techniques, and implications of demand forecasting in the sector. Demand forecasting is essential for businesses to anticipate trends, optimize resource allocation, and enhance operational efficiency. By accurately predicting future demand for aquacultural products, services, and technological outcomes, companies can make informed decisions regarding production, operations, and marketing strategies. However, demand forecasting in this industry faces several challenges, including seasonal variations, data availability, technological complexity, and uncertainties. Aquaculture demand is influenced by factors such as precipitation patterns, regulatory policies, and consumer preferences, making it difficult to develop precise forecasting models. Various techniques are used for demand forecasting, including statistical methods, data analytics, and machine learning algorithms. Time series analysis, regression analysis, and hybrid forecasting approaches are commonly employed to analyze historical data and predict future demand patterns. Accurate demand forecasting has significant implications for businesses, including improved resource planning, supply chain management, and customer satisfaction. By aligning production capacities with anticipated demand and optimizing supply levels, companies can minimize costs, reduce waste, and enhance competitiveness in the market. Demand forecasting is a critical aspect of strategic planning and decision-making in the specialized industry. By utilizing advanced techniques and effectively addressing challenges, businesses can enhance their ability to anticipate trends, meet customer demands, and drive sustainable growth in an increasingly dynamic and competitive environment

Optimizing procurement efficiency: Frameworks for data-driven cost reduction and strategic vendor management

This paper explores data-driven frameworks for optimizing procurement efficiency, focusing on cost reduction strategies and strategic vendor management. Procurement is critical in enhancing operational resilience and supporting organizational objectives in an era of increasing financial pressures and complex supply chains. The study examines data analytics approaches, such as spend analysis, predictive cost modeling, and demand forecasting, which enable organizations to uncover cost-saving opportunities and streamline procurement processes. Additionally, it highlights how data-driven vendor management, through continuous evaluation, risk assessment, and performance tracking, contributes to sustainable supply chain efficiency. Key recommendations include establishing data governance frameworks, investing in advanced analytics tools, enhancing data literacy among procurement teams, and fostering transparent supplier relationships. By integrating analytics into procurement strategies, organizations can achieve long-term cost efficiency, build stronger supplier partnerships, and support sustainable growth.

The role of artificial intelligence and machine learning in optimizing U.S. healthcare supply chain management

This paper aims to review the role of Artificial Intelligence and Machine Learning in managing the healthcare supply chain in the United States. Healthcare supply chains face several challenges such as fragmentation, lack of real-time visibility, and inventory management issues. However, there are solutions with the help of AI and machine learning, including the availability of predictive analytics to improve demand forecasting, optimization algorithms for inventory and logistics, and automated quality control. Application areas demand forecasting, supplier selection, logistics optimization, quality control, and real-time tracking. The applications of AI in healthcare supply chains have the potential to improve the healthcare supply chain in terms of reduced costs, increased efficiency, optimized decision-making, and better patient outcomes. However, the implementation experience has shown several challenges such as data quality, privacy concerns, regulatory compliance, and workforce adaptation within organizations. Successful implementations in various health organizations in the US give valuable insights into how AI could be well implemented. The future presents several opportunities for supply chain optimization with the rise of blockchain and Internet of Things (IoT) integration. For healthcare supply chains to adopt AI, organizations should have specific AI plans, start with pilot projects in high-impact areas, invest in data infrastructure, and ensure strong leadership support. As AI becomes increasingly critical for competitive advantage, it has the potential to create more resilient, efficient, and patient-centric supply chains in the US healthcare system.

Global trade dynamics' impact on food pricing and supply chain resilience: A quantitative model

This study explores the influence of global trade dynamics on food pricing and supply chain resilience, focusing on the development of a quantitative model that examines the relationships between trade policies, economic indicators, and trade volumes. As fluctuations in trade policies—such as tariffs, quotas, and subsidies—directly impact food prices and market stability, this model provides a structured framework for assessing these variables’ interdependencies. By integrating data on trade flows, currency exchange rates, and commodity prices, the model quantifies the effects of protective and liberalized trade measures on both local and international food markets. This approach allows for identifying trends in pricing volatility linked to policy shifts, thereby offering insights into areas vulnerable to trade disruptions and external economic shocks. The resilience of the food supply chain is measured by evaluating metrics such as delivery times, supplier diversity, and inventory levels across regions affected by trade policy changes. The findings emphasize that trade barriers can result in price spikes, delays, and supply shortages, while open trade policies generally support market flexibility and pricing stability. Additionally, the model incorporates economic indicators such as Gross Domestic Product (GDP), inflation, and unemployment rates, which correlate with food demand and purchasing power, thereby further influencing price and supply chain stability. Future research could leverage this model to develop adaptive strategies that strengthen supply chain resilience under various global trade conditions. Suggested adaptations include diversifying suppliers, increasing inventory buffers, and enhancing predictive analytics for better demand forecasting. By integrating these adaptive measures, stakeholders can mitigate adverse effects on food accessibility and affordability in both developed and emerging economies. This research contributes to the literature on food security, highlighting the need for resilient trade policies and supply chain strategies in an increasingly interconnected global economy.

Revolutionizing library systems with advanced automation: A blueprint for efficiency in academic resource management

The advent of advanced automation technologies has the potential to revolutionize library systems, particularly within academic institutions, where effective resource management is essential. This paper outlines a comprehensive blueprint for integrating automation into library operations to enhance efficiency, accessibility, and user engagement. Key technologies discussed include Radio Frequency Identification (RFID), Artificial Intelligence (AI), and Machine Learning (ML), which streamline processes such as cataloging, circulation, and inventory management. The implementation of RFID facilitates self-service checkouts and real-time inventory tracking, significantly reducing the time spent on manual tasks, thereby allowing library staff to concentrate on enhancing user experiences and curating resources strategically. Furthermore, AI-driven chatbots provide personalized recommendations, improving user satisfaction and ensuring that patrons receive tailored support. This blueprint emphasizes the role of automated digital repositories and intelligent content indexing systems, which accelerate cataloging and ensure timely access to scholarly materials. By automating information retrieval processes, libraries can reduce wait times and improve the overall accessibility of resources. Data analytics are also pivotal, enabling libraries to monitor usage patterns, optimize resource allocation, and forecast future demands, ensuring alignment with academic priorities. Moreover, the paper addresses challenges related to automation implementation, including financial constraints, data privacy concerns, and staff training requirements, proposing solutions such as gradual implementation and interdepartmental collaboration. Ultimately, the transition to advanced automation not only enhances operational efficiency but also boosts academic productivity by making resources more accessible and user-centered. This strategic move toward a digital-first library environment signifies a profound transformation in academic libraries, promoting an agile approach to resource management. As institutions increasingly adopt these technologies, they position themselves at the forefront of educational innovation, effectively integrating academic resources into the digital learning landscape.

Privacy-preserving federated data access and federated learning: Improved data sharing and AI model development in transfusion medicine.

Health data comprise data from different aspects of healthcare including administrative, digital health, and research-oriented data. Together, health data contribute to and inform healthcare operations, patient care, and research. Integrating artificial intelligence (AI) into healthcare requires understanding these data infrastructures and addressing challenges such as data availability, privacy, and governance. Federated learning (FL), a decentralized AI training approach, addresses these challenges by allowing models to learn from diverse datasets without data leaving its source, thus ensuring privacy and security are maintained. This report introduces FL and discusses its potential in transfusion medicine and blood supply chain management. FL can offer significant benefits in transfusion medicine by enhancing predictive analytics, personalized medicine, and operational efficiency. Predictive models trained on diverse datasets by FL can improve accuracy in forecasting blood transfusion demands. Personalized treatment plans can be refined by aggregating patient data from multiple institutions using FL, reducing adverse reactions and improving outcomes. Operational efficiency can also be achieved through precise demand forecasting and optimized logistics. Despite its advantages, FL faces challenges such as data standardization, governance, and bias. Harmonizing diverse data sources and ensuring fair, unbiased models require advanced analytical solutions. Robust IT infrastructure and specialized expertise are needed for successful FL implementation. FL represents a transformative approach to AI development in healthcare, particularly in transfusion medicine. By leveraging diverse datasets while maintaining data privacy, FL has the potential to enhance predictions, support personalized treatments, and optimize resource management, ultimately improving patient care and healthcare efficiency.

Short-term water demand prediction using stacking regression–based machine learning

ABSTRACT Forecasting of water demand and equitable allocation of local water resources are used to reduce and eliminate water shortages and waste. The key emphasis of this research article is to estimate water demand using the prediction model for the Peroorkada urban water distribution network. The characteristics, such as head, pressure, and base demand, related to the water demand were the features of the prediction model. The prediction model has been developed using python. The water distribution network consists of 99 nodes. The demand graph for a time interval of 6 h has been plotted and predicted for all the nodes, and 24-h interval demand has been plotted for vulnerable nodes, which were determined by the sensor placement toolkit. This study included 13 machine learning algorithms, including three hybrid/stacked regression techniques. The least absolute shrinkage and selection operator-based stacking regressor model performs the best at demand prediction. Single prediction models were outperformed by stacking regressor models.