Demand Forecasting Research Articles

Application-Driven Learning: A Closed-Loop Prediction and Optimization Approach Applied to Dynamic Reserves and Demand Forecasting

Application-Driven Learning: Closing the Loop Between the Application and the Estimation of Forecast Models This paper introduces a closed-loop framework called application-driven learning, where the best forecast model is tailored to the application cost structure. Our methodology employs two-stage optimization schemes to derive multivariate point forecasts. The estimation problem is conceived as a bilevel model, and we propose two solution methodologies: an exact one using KKT conditions and a scalable decomposition heuristic. This approach offers a scientifically grounded alternative to ad hoc demand biasing approaches and reserve requirement rules currently adopted by power system operators worldwide. Testing with real data and large-scale systems demonstrates that our methodology consistently outperforms traditional open-loop methods, providing significant potential benefits for energy system operations.

Towards Entrepreneurial Campus Sustainability: Integrating Artificial Intelligence for Resource Allocation in Business Management

This research delves into the utilization of artificial intelligence (AI) within the framework of campus resource allocation, with a primary focus on enhancing business management practices and fostering entrepreneurial sustainability within educational institutions. Through an innovative amalgamation of AI technology and SmartPLS methodology, the study constructs a comprehensive analytical framework aimed at tackling the multifaceted challenges inherent in resource allocation within campus environments. The findings underscore the transformative potential of AI integration in optimizing resource utilization, identifying efficiency gains, and nurturing entrepreneurial endeavors. This paper distinguishes itself from existing studies by presenting a novel approach that emphasizes the unique contributions of AI-driven solutions in both methodological innovation and practical application. By harnessing SmartPLS alongside AI, the research facilitates more accurate resource demand forecasting and enables adaptive decision-making processes, thereby contributing to the Sustainable Development Goals (SDGs), particularly in promoting quality education and sustainable management practices. The study also provides a detailed technical implementation of AI algorithms, offering valuable insights into their development and application within campus settings. The broader implications for the educational sector are explored, considering the scalability and adaptability of the proposed solutions in various educational contexts. Furthermore, the research contributes to theoretical advancements by pioneering the integration of AI and SmartPLS in campus management research, offering a fresh perspective on economic, environmental, and social impact assessments of AI-driven solutions.

Electric Vehicle Charging Load Demand Forecasting in Different Functional Areas of Cities with Weighted Measurement Fusion UKF Algorithm

The forecasting of charging demand for electric vehicles (EVs) plays a vital role in maintaining grid stability and optimizing energy distribution. Therefore, an innovative method for the prediction of EV charging load demand is proposed in this study to address the downside of the existing techniques in capturing the spatial–temporal heterogeneity of electric vehicle (EV) charging loads and predicting the charging demand of electric vehicles. Additionally, an innovative method of electric vehicle charging load demand forecasting is proposed, which is based on the weighted measurement fusion unscented Kalman filter (UKF) algorithm, to improve the accuracy and efficiency of forecasting. First, the data collected from OpenStreetMap and Amap are used to analyze the distribution of urban point-of-interest (POI), to accurately classify the functional areas of the city, and to determine the distribution of the urban road network, laying a foundation for modeling. Second, the travel chain theory was applied to thoroughly analyze the travel characteristics of EV users. The Improved Floyd (IFloyd) algorithm is used to determine the optimal route. Also, a Monte Carlo simulation is performed to estimate the charging load for electric vehicle users in a specific region. Then, a weighted measurement fusion UKF (WMF–UKF) state estimator is introduced to enhance the accuracy of prediction, which effectively integrates multi-source data and enables a more detailed prediction of the spatial–temporal distribution of load demand. Finally, the proposed method is validated comparatively against traffic survey data and the existing methods by conducting a simulation experiment in an urban area. The results show that the method proposed in this paper is applicable to predict the peak hours more accurately compared to the reference method, with the accuracy of first peak prediction improved by 53.53% and that of second peak prediction improved by 23.23%. The results not only demonstrate the high performance of the WMF–UKF prediction model in forecasting peak periods but also underscore its potential in supporting grid operations and management, which provides a new solution to improving the accuracy of EV load demand forecasting.

Medium and long-term energy demand forecasts by sectors in China under the goal of “carbon peaking & carbon neutrality”: Based on the LEAP-China model

Energy is a critical material foundation for sustainable economic and social development and national security, and it is of great significance to explore China's medium and long-term energy demand to realize the “dual-carbon” goal. Based on the current state of economic and social development and energy consumption, the LEAP-CHINA model is constructed to create baseline scenario, structural adjustment scenario, technology abatement scenario, and comprehensive scenario to forecast China's total energy demand, end-use industry subsectors, end-use energy subvarieties, processing and conversion sectors from 2022 to 2060. The results show: (1) China's total energy demand showed a “rapid increase before 2039, a slow increase between 2039 and 2049, and a gentle decrease after peaking in 2049". (2) The contribution rate of energy conservation and emission reduction was comprehensive scenario > technology abatement scenario > industrial adjustment scenario > baseline scenario > energy adjustment scenario. (3) Industry was the largest energy demand industry, and the rest of the industries' energy demand share was decreasing. (4) There is a definite trend towards power system decarbonization and energy system electrification, with non-fossil energy power generation anticipated to increase to 78%–82 % in 2060. Finally, it proposes countermeasures for China's energy development in the medium and long-term.

Hotel demand forecasting with multi-scale spatiotemporal features

Accurate demand forecasting is critical to hotel revenue management and related decision-making. Considering the heterogeneity and dynamics of spatial effects across different time scales, this study introduces a novel model which can deeply extract these features to improve the forecasting performance of hotel demand. Specifically, the model constructs input variables with different periodicities and then integrates a Transformer neural network and long short-term memory to extract multi-scale and dynamic spatiotemporal features to generate accurate forecasts. The effectiveness of the model is verified through an empirical case in Xiamen, China. Results suggest our model significantly outperforms benchmarks in terms of accuracy and robustness. The findings extend the application of spatial-temporal modeling in hotel demand forecasting. Hotel managers can use our forecasts to optimize operations, improve revenues, and control risks. The extracted spatiotemporal features can also help managers examine cooperation and competition relationships with neighbor hotels.

Research on Innovation Strategy of Supply Chain Management of Agricultural Enterprises Under the Background of Big Data

With the rapid development and widespread application of Big Data technology, the supply chain management of agricultural products enterprises is facing unprecedented reform and challenges. This study takes the perspective of Big Data technology and collects relevant information on the application of supply chain management in 100 agricultural product enterprises through a survey questionnaire. The study found that the use of Big Data can effectively improve the accuracy of demand forecasting, inventory management efficiency, optimize logistics costs, improve supplier management efficiency, enhance the overall level of supply chain management of enterprises, and propose innovative strategies for supply chain management of agricultural products enterprises based on this. Big Data technology brings a new solution for agricultural products enterprises to enhance their supply chain management level, making the supply chain smarter and more efficient.

OPTIMIZING RETAIL DEMAND FORECASTING: A PERFORMANCE EVALUATION OF MACHINE LEARNING MODELS INCLUDING LSTM AND GRADIENT BOOSTING

Effective demand forecasting is vital for inventory management in retail. This study evaluates five machine learning models—Linear Regression (LR), Decision Tree Regressor (DTR), Random Forest Regressor (RFR), Gradient Boosting (GB), and Long Short-Term Memory (LSTM)—for predicting retail demand. Utilizing a dataset with transactional sales, promotions, calendar events, and external factors like weather and economic indicators, we applied rigorous preprocessing and feature engineering. Performance was assessed using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R²). Results show that LSTM outperforms other models with an MAE of 9.53, RMSE of 14.67, and R² of 0.90, excelling in capturing temporal dependencies and complex demand patterns. Gradient Boosting and Random Forest also performed well, while Linear Regression and Decision Tree Regressor showed limitations. This study highlights the effectiveness of advanced models, particularly LSTM, for enhancing demand forecasting accuracy and offers valuable insights for optimizing retail inventory and operations.

Minitab 20 and Python based-the forecasting of demand and optimal inventory of liquid aluminum sulfate supplies

In a company, inventory management is crucial due to the significant impact on various aspects of the business. Similarly, the Indonesian water supply company (PDAM) requires effective inventory management to ensure the supply of liquid aluminum sulfate chemicals. The probabilistic statistical inventory control (SIC) model is commonly used for inventory management. However, previous research on chemical inventory models in PDAMs often relied on simple linear regression to forecast demand data, which fails to capture the inherent volatility in demand. Therefore, this research aimed to predict demand data using the seasonal autoregressive integrated moving average (SARIMA) method and determine the optimal policy for supplying liquid aluminum sulfate chemicals. The results showed that the best demand forecasting model was SARIMA (2,1,2) (1,1,0)12 with a mean absolute percentage error (MAPE) value of 8.19%. The finding of the optimal inventory policy showed a safety stock value of 11,922.35 kg, a reorder point value of 49,511.20 kg, and an order quantity of 21,526.59 kg, leading to a total cost of IDR 11,132,034,145.45. The sensitivity test also showed that variations in lead time, price, μ, and σ parameters directly influence changes in total cost, reorder point, and safety stock. These calculations were conducted using Minitab and Python software.

Sectoral electricity micro-spatial load forecasting based on partitional clustering technique

<p>Load demand forecasting is crucial in energy supply planning due to economic progress and territorial expansion, where land utilization transforms dynamically. An accurate sectoral load prediction can preclude the loss of beneficial opportunities arising from excessive load demand or excessive investment at a low-growth juncture. However, the particular area in this sectoral approach is still relatively large, rendering it incapable of precisely projecting load at minor points (micro-spatial). This study has proposed a micro-spatial load prediction strategy that categorizes identified areas into smaller grids or districts. This procedure includes clustering similar sites together for improved accuracy. K-Means is one of the partitional clustering approaches, a clustering algorithm utilizing object-based centroid-based partitioning approaches. The algorithm determines a cluster's centroid or centre as the average point for the cluster. This technique is advantageous as it can process extensive data efficiently and is appropriate for circular data. This technique can divide the data into multiple partitions, ensuring that each object belongs to precisely one cluster. Subsequently, mathematical modelling is used to predict the load of each cluster, which can then be utilized to more accurately evaluate the positions and sizes of prospective substations, transmission, and distribution facilities.</p>

Balancing Cost and Economic Efficiency: Consider the multi-purpose optimization of green energy market's function in Green energy interactive infrastructure

The increasing reliance on electric micro-mobility vehicles (EMVs) in the delivery industry necessitates efficient battery-swapping infrastructure. This study presents a framework that predicts battery-swapping needs for EMVs using a simulation model that considers the entire travel chain of activities. We propose a multi-objective optimization model to strategically determine battery-swapping station locations, balancing construction and transit costs. Utilizing the Non-dominated Sorting Genetic Algorithm II (NSGA-II), we identified 35 non-dominated solutions within the Pareto front. For Nanjing City, our model indicated that the construction of an optimal network could be achieved with costs ranging from 2.85 to 4.94 million Yuan, corresponding to battery-swapping trip costs between 9700 and 197,000 Yuan. The simulation predicted a daily battery-swapping demand of 675 instances, with peak hours at 11:00 a.m. (301 swaps) and 5:00 p.m. (198 swaps). Sensitivity analysis showed that reducing the charging period from 3 h to 1 h could decrease construction costs by 1.55 million Yuan on average, while maintaining a consistent battery-swapping travel cost of around 23,000 Yuan. Additionally, a 5 % increase in battery-swapping penetration rate led to an average increase of 480,000 Yuan in construction costs and 847 Yuan in travel costs. This study integrates demand forecasting and infrastructure optimization, providing actionable insights for planning and managing battery-swapping stations.

Modeling the Impact of Holidays and Events on Retail Demand Forecasting in Online Marketing Campaigns using Intervention Analysis

Modeling the Impact of Holidays and Events on Retail Demand Forecasting in Online Marketing Campaigns using Intervention Analysis

Guiding supervisors in artificial intelligence-enabled forecasting: Understanding the impacts of salience and detail on decision-making

In many real-world situations, multiple humans are involved in decision-making when interacting with machine recommendations. We investigated a setting where an artificial intelligence system creates demand forecasts that a human planner can either accept or revise, and a supervisor then makes the final decision about which forecast to select. We designed and conducted two experimental studies to understand decision-making by a supervisor. First, we provided the improvement probabilities of adjustments at an aggregated level and found evidence for overoptimism bias and mean anchoring. Second, we provided decomposed guidance based on two adjustment attributes, direction and magnitude, to investigate the role of salience based on the distance between the improvement probabilities and level of detail in guidance effectiveness. We found no significant difference in using less and more salient guidance provided that the detail level was fixed. However, revealing more details when the guidance was more salient increased the use of guidance.

Evaluating the Effectiveness of Time Series Transformers for Demand Forecasting in Retail

This study investigates the effectiveness of Transformer-based models for retail demand forecasting. We evaluated vanilla Transformer, Informer, Autoformer, PatchTST, and temporal fusion Transformer (TFT) against traditional baselines like AutoARIMA and AutoETS. Model performance was assessed using mean absolute scaled error (MASE) and weighted quantile loss (WQL). The M5 competition dataset, comprising 30,490 time series from 10 stores, served as the evaluation benchmark. The results demonstrate that Transformer-based models significantly outperform traditional baselines, with Transformer, Informer, and TFT leading the performance metrics. These models achieved MASE improvements of 26% to 29% and WQL reductions of up to 34% compared to the seasonal Naïve method, particularly excelling in short-term forecasts. While Autoformer and PatchTST also surpassed traditional methods, their performance was slightly lower, indicating the potential for further tuning. Additionally, this study highlights a trade-off between model complexity and computational efficiency, with Transformer models, though computationally intensive, offering superior forecasting accuracy compared to the significantly slower traditional models like AutoARIMA. These findings underscore the potential of Transformer-based approaches for enhancing retail demand forecasting, provided the computational demands are managed effectively.

Applications of Machine Learning in Textile Industry

It is a question to all of us that what is machine learning and its importance for business sectors. Smart textile when using AI and computer vision try to act on knitting machines and to reduce production rate of defective types with real-time defects along with irregularities to identify with the objective to bring defective production at zero level. When ML and SC technique, artificial neural network, genetic algorithm, and fuzzy logic have preponderance over all others like Bibliographic analysis revealed a drastic rise in number of studies since 2015. It is proposed that demand forecasting is quite volatile and sensitive to several factors. Data mining studies with classification and clustering techniques, ML algorithms were implemented in textile industry. In a study it was found that machine productivity is having negative effect on quality which was confirmed by the management and confirmed a huge important in quality processing in industrial sectors. Demand forecasting by ML driven techniques has proved minimization of forecasting errors by 50%. ML is being used by Adidas to forecast demand in products since 2016. Ridge Regression estimated the correlation between predictor and observation variables.

Construction of Ensemble Learning Model for Home Appliance Demand Forecasting

Given the increasing competition among household appliance enterprises, accurately predicting household appliance demand is crucial for enterprise supply chain management and marketing. This paper proposes a combined model integrating deep learning and ensemble learning—LSTM-RF-XGBoost—to assist enterprises in identifying customer demand, thereby addressing the complexity and uncertainty of the household appliance market demand. In this study, Long Short-Term Memory Network (LSTM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) models are established separately. Then, the three individual algorithms are used as the base models in the first layer, with the multiple linear regression (MLR) algorithm serving as the meta-model in the second layer, merging the demand prediction model based on the hybrid model into the overall demand prediction model. This study demonstrates that the accuracy and stability of demand prediction using the LSTM–RF–XGBoost model significantly outperform traditional single models, highlighting the significant advantages of using a combined model. This research offers practical and innovative solutions for enterprises seeking rational resource allocation through demand prediction.

A Spatial-Temporal Aggregated Graph Neural Network for Docked Bike-sharing Demand Forecasting

Predicting the number of rented and returned bikes at each station is crucial for operators to proactively manage shared bike relocation. Although existing research has proposed spatial-temporal prediction models that significantly advance traffic prediction, these models often neglect the unique characteristics of shared bike systems (BSS). Spatially, the entire Bike Sharing System (BSS) experiences peak activity during morning and evening rush hours, whereas, during other periods, activity is localized to local stations, with some recording no rides, highlighting the need to distinguish between global and local spatial information across different times. Temporally, the historical riding records for each station exhibit non-stationary patterns, necessitating the analysis of both global trends and local fluctuations. Existing Graph Neural Network (GNN) approaches to predicting shared bike demand primarily capture static spatial-temporal data and fail to account for the dynamic nature of bike flows. Moreover, these studies focus on global spatial-temporal information without considering local nuances, making it challenging to capture spatiotemporal dynamics in fluctuating BSS. To address these challenges, we introduce the Spatial-Temporal Aggregated Graph Neural Network (STAGNN). Our model first constructs a dynamic adjacent matrix to describe the evolving connections between stations, followed by local and global information layers to capture spatial-temporal information from large-scale shared bike networks accurately. Our methodology has been validated through experiments on four real-world datasets, comparing it against benchmark models to demonstrate superior prediction accuracy. Additionally, we conduct extended experiments on four datasets during the morning and evening rush hours, and the results also affirm the efficacy of the STAGNN in enhancing prediction performance.

AI integration in supply chain and operations management: Enhancing efficiency and resilience

Artificial intelligence (AI) has become a transformative force in supply chain and operations management, offering significant enhancements in efficiency and resilience. This paper examines the integration of AI technologies such as machine learning, predictive analytics, and real-time data processing in demand forecasting, inventory management, logistics, and risk mitigation. By analyzing diverse data sources, AI improves demand forecasting accuracy, reduces inventory costs, optimizes logistics routes, and enhances supply chain visibility. Case studies and data-driven insights demonstrate how AI-driven systems enable companies to adapt to market dynamics, prevent disruptions, and achieve substantial cost savings. The findings suggest that embracing AI is essential for businesses aiming to optimize their supply chain operations and build robust, resilient frameworks capable of withstanding future challenges.

Analysis and forecast of crop water demand in irrigation districts across the eastern part of the Ebro river basin (Catalonia, Spain): estimation of evapotranspiration through copernicus-based inputs

AbstractThe agricultural sector is currently facing the uncertainty that accompanies climate change in terms of the availability of water resources, as well as the need to balance the water demand for agricultural irrigation with other uses in river basins. In Spain, irrigation districts (IDs) play a very important role in the management of water resources. The efficiency of ID water management involves finding an equilibrium between supply and demand. It is in relation to the latter where the uncertainty is greatest, because until now no tools have been available to characterize water demands with sufficient precision throughout irrigation campaigns. ID managers need precise information and the development of tools to support decision making in planning and water management. Therefore, this study aims to identify, compare and analyse the differences between the demands, allocations and consumptions of water for irrigation in different IDs of the eastern part of the Ebro basin during six consecutive growing seasons. In addition, projections of water demands up to 2100 are conducted using a dataset of six global climate models under different climate scenarios. Novel advances in remote sensing for evapotranspiration approaches using Copernicus-based inputs were used in this study. Large variabilities in water demands among IDs and in the adjustments between demands and allocations were observed, suggesting there is still much room for the improvement of water management. All climate projections have a very clear pattern indicating an upward trend in water demands until the end of the century.

Leveraging variational autoencoders and recurrent neural networks for demand forecasting in supply chain management: A case study

Accurate demand forecasting is key for companies to optimize inventory management and satisfy customer demand efficiently. This paper aims to Investigate on the application of generative AI models in demand forecasting. Two models were used: Long Short-Term Memory (LSTM) networks and Variational Autoencoder (VAE), and results were compared to select the optimal model in terms of performance and forecasting accuracy. The difference of actual and predicted demand values also ascertain LSTM’s ability to identify latent features and basic trends in the data. Further, some of the research works were focused on computational efficiency and scalability of the proposed methods for providing the guidelines to the companies for the implementation of the complicated techniques in demand forecasting. Based on these results, LSTM networks have a promising application in enhancing the demand forecasting and consequently helpful for the decision-making process regarding inventory control and other resource allocation.

Modernising Supply Chain Analytics with Demand Forecasting Engine

In todays’ dynamic market landscape accurate demand forecasting plays a role, in optimizing supply chain operations reducing inventory expenses and improving customer satisfaction. The article is a case study of one of the leading automotive spare parts manufacturers with thousands of products. The main aim of the study is to forecast the demand of the factory on bi-weekly basis and monthly basis, compare the performance metrics with different forecast approaches and suggest suitable model.