Accurate Demand Forecasting Research Articles

Spatial-Temporal Diffusion Convolutional Network: A Novel Framework for Taxi Demand Forecasting

Taxi demand forecasting plays an important role in ride-hailing services. Accurate taxi demand forecasting can assist taxi companies in pre-allocating taxis, improving vehicle utilization, reducing waiting time, and alleviating traffic congestion. It is a challenging task due to the highly non-linear and complicated spatial-temporal patterns of the taxi data. Most of the existing taxi demand forecasting methods lack the ability to capture the dynamic spatial-temporal dependencies among regions. They either fail to consider the limitations of Graph Neural Networks or do not efficiently capture the long-term temporal dependencies. In this paper, we propose a Spatial-Temporal Diffusion Convolutional Network (ST-DCN) for taxi demand forecasting. The dynamic spatial dependencies are efficiently captured through a two-phase graph diffusion convolutional network where the attention mechanism is introduced. Moreover, a novel temporal convolution module is designed to learn various ranges of temporal dependencies, including recent, daily, and weekly periods. Inside the module, convolution layers are stacked to handle very long sequences. Experimental results on two large-scale real-world taxi datasets from New York City (NYC) and Chengdu demonstrate that our method significantly outperforms seven state-of-the-art baseline methods.

Spare parts demand forecasting method of modern enterprises based on digital twin model

Accurate forecast of spare parts demand is of great significance for modern enterprises to provide accurate support and improve market competitiveness. In most studies, mathematical laws are used to forecast, without enough consideration of the actual operation of equipment and the fact that the accuracy of spare parts demand forecasting is not high, which cannot adapt to the new characteristics of complex equipment use environment and fierce market competition in modern enterprises. The digital twin model can be used to forecast the demand for spare parts more accurately and guide modern enterprises to carry out accurate support. By analyzing the current spare parts demand of modern enterprises, the paper puts forward the forecasting ideas of spare parts demand based on the digital twin model by using the digital twin model of equipment maintenance management in modern enterprises. In the digital twin model, the theoretical demand forecasting model of spare parts based on life distribution of replaceable units is introduced, and the sensitivity coefficient system of spare parts demand of replaceable units to operation and environment is constructed. The digital twin model is used to feedback train the sensitivity coefficient to obtain the reliable spare parts demand rules. Based on the theoretical demand and sensitivity coefficient of spare parts, the forecasting method of spare parts demand is given, and the spare parts demand forecasting model is established. Through case analysis, the feasibility and accuracy of the forecasting model are verified.

Multivariate monthly water demand prediction using ensemble and gradient boosting machine learning techniques

Water management planning requires reliable and accurate water demand forecasting. Water demand prediction is affected by variables, such as climate, socio-economic, and demographic data. This paper investigates urban monthly average water demand prediction, using classical, ensemble, and gradient boosting-based machine learning models, using the available monthly water demand, climatic, economic, and demographic data. Three train-test data split schemes on water demand timeseries were considered to determine the effect of data size on water demand prediction. Sensitivity analysis was employed to reduce input feature dimensionality while maintaining model accuracy. A univariate timeseries (water demand only) produced R2 scores up to 0.91, which increased to 0.94 with the addition of calendar and climatic features. Increasing the training data size from 70% to 90% improved the RMSE and MAE scores by ensemble and gradient boosting methods, with the random forest and the AdaBoost models showing improvements of up to 69%. The sensitivity analysis revealed a successful input reduction scheme from a potential 17 input attributes to seven inputs. Gradient boosting models showed robust and faster execution time, especially with the increase in training data, which is attractive for medium-term urban water demand forecasting.

A hybrid extreme learning machine model with harris hawks optimisation algorithm: an optimised model for product demand forecasting applications

Accurate and real-time product demand forecasting is the need of the hour in the world of supply chain management. Predicting future product demand from historical sales data is a highly non-linear problem, subject to various external and environmental factors. In this work, we propose an optimised forecasting model - an extreme learning machine (ELM) model coupled with the Harris Hawks optimisation (HHO) algorithm to forecast product demand in an e-commerce company. ELM is preferred over traditional neural networks mainly due to its fast computational speed, which allows efficient demand forecasting in real-time. Our ELM-HHO model performed significantly better than ARIMA models that are commonly used in industries to forecast product demand. The performance of the proposed ELM-HHO model was also compared with traditional ELM, ELM auto-tuned using Bayesian Optimisation (ELM-BO), Gated Recurrent Unit (GRU) based recurrent neural network and Long Short Term Memory (LSTM) recurrent neural network models. Different performance metrics, i.e., Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Percentage Error (MPE) were used for the comparison of the selected models. Horizon forecasting at 3 days and 7 days ahead was also performed using the proposed approach. The results revealed that the proposed approach is superior to traditional product demand forecasting models in terms of prediction accuracy and it can be applied in real-time to predict future product demand based on the previous week’s sales data. In particular, considering RMSE of forecasting, the proposed ELM-HHO model performed 62.73% better than the statistical ARIMA(7,1,0) model, 40.73% better than the neural network based GRU model, 34.05% better than the neural network based LSTM model, 27.16% better than the traditional non-optimised ELM model with 100 hidden nodes and 11.63% better than the ELM-BO model in forecasting product demand for future 3 months. The novelty of the proposed approach lies in the way the fast computational speed of ELMs has been combined with the accuracy gained by tuning hyperparameters using HHO. An increased number of hyperparameters has been optimised in our methodology compared to available models. The majority of approaches to improve the accuracy of ELM so far have only focused on tuning the weights and the biases of the hidden layer. In our hybrid model, we tune the number of hidden nodes, the number of input time lags and even the type of activation function used in the hidden layer in addition to tuning the weights and the biases. This has resulted in a significant increase in accuracy over previous methods. Our work presents an original way of performing product demand forecasting in real-time in industry with highly accurate results which are much better than pre-existing demand forecasting models.

Special issue on big data in transportation

Optimization and analysis of transportation systems have become considerably more autonomous and smarter by using connectivity and automation to overcome urbanization problems, such as an ever-growing population, increasing personal travel activities, limited budgets for infrastructure deployments and so on. With this in mind, there is an increasing need for high cooperation both strategically and operationally among different types of transportation modes, each with different objectives and policies. More than ever, Intelligent Transportation Systems (ITS) are playing a significant role in providing efficient integration and cooperation among different technologies and services, and complex and diverse multi-source ITS data have increased massively. Those valuable vast amounts of data can be handled by big data analytics in terms of providing efficient, safe and convenient ITS operations. Through big data–oriented emerging technologies, traffic becomes more intelligent, more manageable and safer. This special issue focusses on data science, data systems and transportation science and their applications to deliver effective and efficient solutions to the current challenges of handling big data in real-world ITS applications. From 19 submitted articles to this special issue, 4 articles were selected based on their reviews. Each article was reviewed by at least two reviewers and went through at least two rounds of reviews. The contributions of these articles are discussed in brief below. Claudio Teixeira, Luana Fragoso, Marta Mattoso, Diego Carvalho, Eduardo Bezerra, Jorge Soares, Glauco Amorim and Eduardo Ogasawara, ‘A horizontal partitioning-based method for frequent pattern mining in transport timetable’. A public transportation timetable is a document that provides information about public transportation service times to help passengers plan their trip. The timetable will often include the times when a service is scheduled to arrive and depart from specific places. T-mine, a unique frequent pattern mining (FPM) technique for improving knowledge discovery in timetable datasets, is presented in this study to solve the issues of lowering FPM computational cost and redundancy in association rules (AR). Authors show that the T-mine can generate a greater number of distinct, non-redundant and contextualized ARs than the traditional approach without functional dependency. Zain Ul Abideen, Heli Sun, Zhou Yang and Hamza Fahim, ‘Regional based Multi-Module Spatial-Temporal Networks Predicting City-wide Taxi Pickup/Dropoff demand from Origin to Destination’. Accurate forecasting of taxi demand is essential for drivers, riders, ride-hailing businesses and zonal directors. The goal of this work, in the future time interval between all areas estimating taxi demand, is to handle city-wide taxi demand origin–destination (OD) forecasting by Multi-Module Spatial–Temporal Networks (MMSTNs), which is a subject worth studying. Authors do a lot of tests on a real-world dataset called NYCTaxi to show how they can anticipate taxi demand around the city. They also show that their method surpasses prior strategies in terms of accuracy. Fethullah Gocer and Nazmi Sener, ‘Spherical Fuzzy Extension of AHP-ARAS Methods Integrated with Modified k-Means Clustering for Logistics Hub Location Problem’. A hub location problem (HLP) is concerned with where facilities should be located and how demand nodes should be allocated to hubs in order to route goods flow to o-d lowest cost pathways. Using a modified weighted k-means clustering algorithm and Multi-Criteria Decision-Making (MCDM) tools under a spherical fuzzy set environment, this work suggests a two-layered methodology to address the logistic HLP. An application of the network structure for postal/cargo operations in Turkey demonstrates the validity of the suggested assessment model. Iván García-Aguilar, Rafael Marcos Luque-Baena and Ezequiel López-Rubio, ‘Improved detection of small objects in road network sequences using CNN and super resolution’. The authors provide a new approach that uses deep convolutional neural networks for super-resolution to identify small-scale visual objects (educed size elements) and enhance the accuracy of class prediction. The results demonstrate that using super-resolution techniques improves the detections made on an image from video surveillance systems. The guest editors hope that the research contributions and findings in this special issue will benefit the readers in enhancing their knowledge and encouraging them to work on various aspects of Big Data in transportation. We want to express our sincere thanks to the Editor-in-Chief for and Special Issue Editor of Expert Systems for allowing us to organize this issue. The editorial office staff are excellent, and we thank them for their support. We are also thankful to all the authors who made this special issue possible and to the reviewers for their thoughtful contributions.

Forecasting Hourly Electricity Demand Under COVID-19 Restrictions

The rapid spread of the COVID-19 pandemic has severely impacted many sectors including the electricity sector. The restrictions such as lockdowns, remote-working, and -schooling significantly altered the consumers' behaviors and demand structure especially due to a large number of people working at home. Accurate demand forecasts and detailed production plans are crucial for cost-efficient generation and transmission of electricity. In this research, the restrictions and their corresponding timing are classified and mapped with the Turkish electricity demand data to analyze the impact of the restrictions on total demand using a multiple linear regression model. In addition, the model is utilized to forecast the electricity demand in pandemic conditions and to analyze how different types of restrictions impact the total electricity demand. It is found that among three levels of COVID-19 restrictions, age-specific restrictions and the complete lockdown have different effects on the electricity demand on weekends and weekdays. In general, new scheduling approaches for daily and weekly loads are required to avoid supply-demand mismatches as COVID-19 significantly changed the consumer behavior, which appears as altered daily and weekly load profiles of the country. Long-term policy implications for the energy transition and lessons learned from the COVID-19 experience are also discussed.

The derived demand for advertising expenses and implications on sustainability: a comparative study using deep learning and traditional machine learning methods.

In recent years, machine learning models based on big data have been introduced into marketing in order to transform customer data into meaningful insights and to make strategic decisions by making more accurate predictions. Although there is a large amount of literature on demand forecasting, there is a lack of research about how marketing strategies such as advertising and other promotional activities affect demand. Therefore, an accurate demand-forecasting model can make significant academic and practical contributions for business sustainability. The purpose of this article is to evaluate machine learning methods to provide accuracy in forecasting demand based on advertising expenses. The study focuses on a prediction mechanism based on several Machine Learning techniques—Support Vector Regression (SVR), Random Forest Regression (RFR) and Decision Tree Regressor (DTR) and deep learning techniques—Artificial Neural Network (ANN), Long Short Term Memory (LSTM),—to deal with demand forecasting based on advertising expenses. Deep learning is a powerful technique that can solve marketing problems based on both classification and regression algorithms. Accordingly, a television manufacturer’s real market dataset consisting of advertising expenditures, sales and demand forecasting via chosen machine learning methods was analyzed and compared in terms of the accuracy of demand forecasting. As a result, Long Short Term Memory has been found to be superior to other models in providing highly accurate prediction results for demand forecasting based on advertising expenses.

Improving Short-Term Bike Sharing Demand Forecast Through an Irregular Convolutional Neural Network

As an important task for the management of bike sharing systems, accurate forecast of travel demand could facilitate dispatch and relocation of bicycles to improve user satisfaction. In recent years, many deep learning algorithms have been introduced to improve bicycle usage forecast. A typical practice is to integrate convolutional (CNN) and recurrent neural network (RNN) to capture spatial-temporal dependency in historical travel demand. For typical CNN, the convolution operation is conducted through a kernel that moves across a "matrix-format" city to extract features over spatially adjacent urban areas. This practice assumes that areas close to each other could provide useful information that improves prediction accuracy. However, bicycle usage in neighboring areas might not always be similar, given spatial variations in built environment characteristics and travel behavior that affect cycling activities. Yet, areas that are far apart can be relatively more similar in temporal usage patterns. To utilize the hidden linkage among these distant urban areas, the study proposes an irregular convolutional Long-Short Term Memory model (IrConv+LSTM) to improve short-term bike sharing demand forecast. The model modifies traditional CNN with irregular convolutional architecture to extract dependency among "semantic neighbors". The proposed model is evaluated with a set of benchmark models in five study sites, which include one dockless bike sharing system in Singapore, and four station-based systems in Chicago, Washington, D.C., New York, and London. We find that IrConv+LSTM outperforms other benchmark models in the five cities. The model also achieves superior performance in areas with varying levels of bicycle usage and during peak periods. The findings suggest that "thinking beyond spatial neighbors" can further improve short-term travel demand prediction of urban bike sharing systems.

Evolutionary Machine Learning-Based Energy Consumption Prediction for the industry

In the digitalization of industry and the industry 4.0 environment, it is important to master the accurate forecasting of energy demand in order to guarantee the continuity of production service as well as to improve the reliability of the electrical system while promoting energy efficiency strategies in the industrial sector. This paper proposes machine learning models to predict the energy consumption demand in an industrial plant, which takes into account the at-tributes that directly the consumption. The proposed models in this work include Multiple Linear Regression (MLR), Decision Tree (DT), Recurrent Neural Networks (RNN) and Gated Recurrent United (GRU), which are compared according to their performances criteria which help to find the best forecasting models. Basing on simulation results, it is proven that the MLR approach is the best forecasting method.

Smart-Meter Big Data for Load Forecasting: An Alternative Approach to Clustering

Accurate forecasting of electricity demand is vital to the resilient management of energy systems. Recent efforts in harnessing smart-meter data to improve forecasting accuracy have primarily centered around cluster-based approaches (CBAs), where smart-meter data are grouped into a small number of clusters and separate prediction models are developed for each cluster. The cluster-based predictions are then aggregated to compute the total demand. CBAs have provided promising results compared to conventional approaches that are generally not conducive to integrating smart-meter data. However, CBAs are computationally costly and suffer from the curse of dimensionality, especially under scenarios involving smart-meter data from millions of customers. In this work, we propose an efficient reduced model approach (RMA) that leverages a novel hierarchical dimension reduction algorithm to enable the integration of fine-resolution high-dimensional smart-meter data for millions of customers in load prediction. We demonstrate the applicability of our proposed approach by using data from a utility company, based in Illinois, United States, with more than 3.7 million customers and present model performance in-terms of forecast accuracy. The proposed hierarchical dimension reduction approach enables utilizing the high-resolution data from smart-meters in a scalable manner that is not exploitable otherwise. The results shows significant improvements in forecast accuracy compared to the available approaches that either do not harness fine-resolution data or are not scalable to large-scale smart-meter big data.

ELECTRIC LOAD AND POWER FORECASTING USING ENSEMBLE GAUSSIAN PROCESS REGRESSION

We propose a new forecasting method for predicting load demand and generation scheduling. Accurate week-long forecasting of load demand and optimal power generation is critical for efficient operation of power grid systems. In this work, we use a synthetic data set describing a power grid with 700 buses and 134 generators over a 365-days period with data synthetically generated at an hourly rate. The proposed approach for week-long forecasting is based on the Gaussian process regression (GPR) method, with prior covariance matrices of the quantities of interest (QoI) computed from ensembles formed by up to twenty preceding weeks of QoI observations. Then, we use these covariances within the GPR framework to forecast the QoIs for the following week. We demonstrate that the the proposed ensemble GPR (EGPR) method is capable of accurately forecasting weekly total load demand and power generation profiles. The EGPR method is shown to outperform traditional forecasting methods including the standard GPR and autoregressive integrated moving average (ARIMA) methods.

ПРИМЕНЕНИЕ МЕТОДОВ ПРОГНОЗИРОВАНИЯ В ЗАКУПОЧНОЙ ЛОГИСТИКЕ ТОРГОВЫХ ПРЕДПРИЯТИЙ

The article authors consider the possibilities of using various methods for forecasting the volume of sales, based on logistical principles, in relation to the activities of automobile dealer enterprises. The golden rule of logistics forms the basis for the logistics process behavior and is implies the supply of products in the right quantity and quality, and on time. The task of sales forecasting is to anticipate the demand parameters to plan the future activities of the enterprise. Thus, sales forecasting underlies the logistics activities of the enterprise. The effectiveness of the implementation of almost all logistics functions directly depends on the accuracy and reliability of the consumer demand forecasts. At the same time, the specifics of the activity of the enterprise in question – a car dealer – imposes certain restrictions on the possibilities of sales forecasting. In particular, the need to take into account market trends, the availability of quotas for the manufacturer, and taking into consideration the demand for the assortment on the part of consumers lead to the need to adjust the methods used for sales forecasting. The authors of the article have reviewed the forecasting methods used in logistics and highlighted the methods that can be used by car dealers to determine the volume of sales in subsequent periods. The sequence of using forecasting methods forms an algorithm for sales volume forecasting. Approbation of the methodology and algorithm for sales volume forecasting has been carried out on the example of a particular enterprise and can be used by similar enterprises in their activities.

Daily Water Demand Prediction Driven by Multi-source Data

The best scheduling of water distribution systems may be supported by accurate and trustworthy water demand forecasts, which is a positive assurance for the development of smart cities and smart water services. This paper studies a new multivariate time-series prediction model that is based on the Convolution Neural Network (CNN) and Gate Recurrent Unit(GRU), taking into account the limitations of the prediction of multivariate time series using a single model. According to the regularity of water use during the time period, the characteristics of water users are clustered and classified to form two types of users: tidal type and irregular type. The factors that affect the daily water consumption such as user type, week, water consumption of the day of the previous three weeks, major events, etc. are used as input vectors, and the 2018-2021 resident daily water consumption time series data of a domestic water company is used as the training sample, respectively establish CNN-GRU models.CNN-GRU approach is checked using the root mean square error(RMSE),mean absolute error(MAE),and mean percentage absolute error(MAPE).The results are compared with Long-Short Term Memory (LSTM),CNN and GRU.Results show that CNN-GRU improves water demand prediction. The CNN-GRU model's RMSE dropped by around 0.648, 0.82, 0.82 when compared to the LSTM, CNN, and GRU models.the MAE decreased by about 0.418,0.47,0.462;and the MAPE decreased by about 0.722,0.649,0.712.

Pandemic-Aware Day-Ahead Demand Forecasting Using Ensemble Learning

Electricity demand forecast is necessary for power systems’ operation scheduling and management. However, power consumption is uncertain and depends on several factors. Moreover, since the onset of covid-19, the electricity consumption pattern went through significant changes across the globe, which made the forecasting demand more challenging. This is mainly due to the fact that pandemic-driven restrictions changed people’s lifestyles and work activities. This calls for new forecasting algorithms to more effectively handle these conditions. In this paper, ensemble-based machine learning models are utilized for this task. The lockdown temporal policies are added to the feature set in order to make the model capable of correcting itself in pandemic situations and enhance data quality for the forecasting task. Several ensemble-based machine learning models are examined for the short-term country-level demand prediction model. Besides, the quantile random forest regression is implemented for a probabilistic point of view. For case studies, the models are trained for predicting Germany’s country-level demand. The results indicate that ensemble models, especially boosting and bagging-boosting models, are capable of accurate country-level demand forecast. Besides, the majority of these models are robust against missing the pandemic policy data. However, utilizing the pandemic policy data as features increases the forecasting accuracy during the pandemic situation significantly. Furthermore, the probabilistic quantile regression demonstrated high accuracy for the aforementioned case study.

Demand forecast and influential factors of cold chain logistics based on a grey model.

Due to high requirements of storage, operation and delivery conditions, it is more difficult for cold chain logistics to meet the demand with supply in the course of disruption. And, accurate demand forecasting promotes supply efficiency for cold chain logistics in a changeable environment. This paper aims to find the main influential factors of cold chain demand and presents a prediction to support the resilience operation of cold chain logistics. After analyzing the internal relevance between potential factors and regional agricultural cold chain logistics demand, the grey model GM (1, N) with fractional order accumulation is established to forecast future agricultural cold chain logistics demand in Beijing, Tianjin, and Hebei. The following outcomes have been obtained. (1) The proportion of tertiary industry, per capita disposable income indices for urban households and general price index for farm products are the first three factors influencing the cold chain logistics demand for agricultural products in both Beijing and Tianjin. The GDP, fixed asset investment in transportation and storage, and the proportion of tertiary industry are three major influential factors in Hebei. (2) Agricultural cold chain demand in Beijing and Hebei will grow sustainably in 2021-2025, while the trend in Tianjin remains stable. In conclusion, regional developmental differences should be considered when planning policies for the Beijing-Tianjin-Hebei cold chain logistics system.

Transmuse: Transferable Traffic Prediction in Multi-Service Edge Networks

The Covid-19 pandemic has forced the workforce to switch to working from home, which has put significant burdens on the management of broadband networks and called for intelligent service-by-service resource optimization at the network edge. In this context, network traffic prediction is crucial for operators to provide reliable connectivity across large geographic regions. Although recent advances in neural network design have demonstrated potential to effectively tackle forecasting, in this work we reveal based on real-world measurements that network traffic across different regions differs widely. As a result, models trained on historical traffic data observed in one region can hardly serve in making accurate predictions in other areas. Training bespoke models for different regions is tempting, but that approach bears significant measurement overhead, is computationally expensive, and does not scale. Therefore, in this paper we propose TransMUSE, a novel deep learning framework that clusters similar services, groups edge-nodes into cohorts by traffic feature similarity, and employs a Transformer-based Multi-service Traffic Prediction Network (TMTPN), which can be directly transferred within a cohort without any customization. We demonstrate that TransMUSE exhibits imperceptible performance degradation in terms of mean absolute error (MAE) when forecasting traffic, compared with settings where a model is trained for each individual edge node. Moreover, our proposed TMTPN architecture outperforms the state-of-the-art, achieving up to 43.21% lower MAE in the multi-service traffic prediction task. To the best of our knowledge, this is the first work that jointly employs model transfer and multi-service traffic prediction to reduce measurement overhead, while providing fine-grained accurate demand forecasts for edge services provisioning.

A Poisson-Regression, Support Vector Machine and Grey Prediction Based Combined Forecasting Model Proposal: A Case Study in Distribution Business

Demand forecasting is a complicated task due to incomplete data and unpredictability. Accurate demand forecasting has a direct impact on the performance of a company. The goal of the study is to present a new two-stage combination model named Hybrid-2-Best, for accurate demand forecasting. The model combines three forecasting models in a single combined forecast. The Hybrid-2-Best model uses a two-stage algorithm to achieve better-performing forecasts. Case study showed that the proposed Hybrid-2-Best model performs the best forecast performance among other combination techniques and individual methods. Furthermore, GP integration in the first and second stages gives flexibility. Experimental results indicate that the proposed Hybrid-2-Best model is a promising alternative for sales demand forecasting. MAPE of the proposed model is 0,13. This is a good result and better than compared other models. Proposed model performed better than other compared models in MASE and MSE as well

Deep Learning Based Customer Preferences Analysis in Industry 4.0 Environment

Customer preferences analysis and modelling using deep learning in edge computing environment are critical to enhance customer relationship management that focus on a dynamically changing market place. Existing forecasting methods work well with often seen and linear demand patterns but become less accurate with intermittent demands in the catering industry. In this paper, we introduce a throughput deep learning model for both short-term and long-term demands forecasting aimed at allowing catering businesses to be highly efficient and avoid wastage. Moreover, detailed data collected from a business online booking system in the past three years have been used to train and verify the proposed model. Meanwhile, we carefully analyzed the seasonal conditions as well as past local or national events (event analysis) that could have had critical impact on the sales. The results are compared with the best performing forecast methods Xgboost and autoregressive moving average model (ARMA), and they suggest that the proposed method significantly improves demand forecasting accuracy (up to 80%) for dishes demand along with reduction in associated costs and labor allocation.

Leveraging customer engagement to improve the operational efficiency of social commerce start-ups

Despite the surge of literature on customer engagement (CE) in social media, few studies shed light on how to leverage CE to improve firms’ operational efficiency. This research proposes a fresh framework using social media data to improve demand forecasting accuracy, resulting in a cost-efficient inventory control strategy. Drawing upon the resource mobilization perspective in particular, this research quantifies the construct of CE from the view of input–output efficiency evaluation using the Data Envelopment Analysis (DEA) model, and then leverages CE to forecast consumer online demand and reconfigure inventory management strategy. Using a 71-week data set from a social commerce start-up in China, this research shows that this new framework dramatically increases demand forecasting accuracy and reduces operational costs in inventory management. This study contributes to the literature by demonstrating the value of social media data in improving operational efficiency, particularly regarding inventory management.

Forecasting Daily Tourism Demand for Tourist Attractions with Big Data: An Ensemble Deep Learning Method

Accurate forecasting of daily tourism demand is a meaningful and challenging task, but studies on this issue are scarce. To address this issue, multisource time series data, relating to past tourist volumes, web search information, daily weather conditions, and the dates of public holidays, are selected as the forecasting variables. To fully capture the relationship between these forecasting variables and actual tourism demand automatically, an ensemble of long short-term memory (LSTM) networks is proposed with a correlation-based predictor selection (CPS) algorithm. The effectiveness of the proposed method is verified in daily tourism demand forecasting for the Huangshan Mountain Area, benchmarked against 11 forecasting methods. This study contributes to the literature by (1) introducing the use of big data in daily tourism demand forecasting, (2) proposing an ensemble of LSTM networks for daily tourism demand forecasting, and (3) providing an effective predictor selection algorithm in ensemble learning.