Forecast accuracy of demand for registered nurses and its determinants in South Korea.

BACKGROUND: Despite the significance of demand forecasting accuracy for the registered nurse (RN) workforce, few studies have evaluated past forecasts. PURPOSE: This paper examined the ex post accuracy of past forecasting studies focusing on RN demand and explored its determinants on the accuracy of demand forecasts. METHODS: Data were collected by systematically reviewing national reports or articles on RN demand forecasts. The mean absolute percentage error (MAPE) was measured for forecasting error by comparing the forecast with the actual demand (employed RNs). Nonparametric tests, the Mann‒Whitney test, and the Kruskal‒Wallis test were used to analyze the differences in the MAPE according to the variables, which are methodological and researcher factors. RESULTS: A total of 105 forecast horizons and 196 forecasts were analyzed. The average MAPE of the total forecast horizon was 34.8%. Among the methodological factors, the most common determinant affecting forecast accuracy was the RN productivity assumption. The longer the length of the forecast horizon was, the greater the MAPE was. The longer the length of the data period was, the greater the MAPE was. Moreover, there was no significant difference among the researchers' factors. CONCLUSIONS: To improve demand forecast accuracy, future studies need to accurately measure RN workload and productivity in a manner consistent with the real world.

Exploration on human resource management and prediction model of data-driven information security in Internet of Things.

The advent of the Internet of Things (IoT) has accelerated the pace of economic development across all sectors. However, it has also brought significant challenges to traditional human resource management, revealing an increasing number of problems and making it unable to meet the needs of contemporary enterprise management. The IoT has brought numerous conveniences to human society, but it has also led to security issues in communication networks. To ensure the security of these networks, it is necessary to integrate data-driven technologies to address this issue. In response to the current state of human resource management, this paper proposes the application of IoT technology in enterprise human resource management and combines it with radial basis function neural networks to construct a model for predicting enterprise human resource needs. The model was also experimentally analyzed. The results show that under this algorithm, the average prediction accuracy for the number of employees over five years is 90.2 %, and the average prediction accuracy for sales revenue is 93.9 %. These data indicate that the prediction accuracy of the model under this study's algorithm has significantly improved. This paper also conducted evaluation experiments on a wireless communication network security risk prediction model. The average prediction accuracy of four tests is 91.21 %, indicating that the model has high prediction accuracy. By introducing data-driven technology and IoT applications, this study provides new solutions for human resource management and communication network security, promoting technological innovation in the fields of traditional human resource management and information security management. The research not only improves the accuracy of the prediction models but also provides strong support for decision-making and risk management in related fields, demonstrating the great potential of big data and artificial intelligence technology in the future of enterprise management and security.

Electricity demand analysis and forecasting: The case of GADA special economic zone.

Ethiopia is a country in East Africa experiencing significant economic growth in recent years, with an increasing electricity demand. Ensuring sustainable and efficient energy for newly developed industries and economic zones is crucial. In this study, a 15-year electric power demand forecast for the new economic zone under construction is conducted. The electrical power demand forecast is done for the year 2025-2040 by using bottom-up forecasting approach for three different scenarios. Long-range Energy Alternatives Planning (LEAP) system software is used to analyze residential, industrial, and general business sector electric power demand. The analysis of the assessed scenario shows that the economic zone's electric power demand increases by 52.2 % from the base year 2025-2040 for the baseline scenario, due to anticipated rapid urbanization, growth in population, economic expansion, and anticipated political stability. Compared to the baseline scenario, the total power demand shows a growth of 68 % from the forecast year (2025) to 2040 for the aggressive scenario, which ensures sustainable and efficient energy options that can draw businesses from both domestic and international baselines. In contrast, the total power demand in the conservative scenario shows a growth of 30.3 % from the base year (2025) to 2040. This reduction in demand compared to the two scenarios indicates a reflection of how much electricity power demand could be if certain development conditions failed to be realized in the economy. In general, both results show a rapid increase in power demand compared to the base year. To address this increasing demand, a supply-side demand analysis can be done for reference and aggressive scenarios. The analysis result indicated that by 2040, supply-side demand from the national grid will increase by 93.5 % and 175.9 % for reference and aggressive scenarios, respectively, compared to the base year 2025 demand. Due to the huge gap between the supply and demand in the country, onsite off-grid generation can be considered to cover 25 % of the demand in the economic zone. Hence, with the support of off-grid generation, the demand from the national grid was reduced to 45 % and 107 % for reference and aggressive scenarios with the support of onsite generation. Hence, this research clearly shows that there is a serious need for large scale electricity generation and distribution planning and preparation to meet the continually increasing electric power demand in a sustainable manner to accommodate the growth and change required to develop the modern economic zones in the country.

Blood Demand Forecasting and Supply Management: An Analytical Assessment of Key Studies Utilizing Novel Computational Techniques.

Use of data-driven methodologies in enhancing blood transfusion practices is rising, leveraging big data, machine learning, and optimization techniques to improve demand forecasting and supply chain management. This review used a narrative approach to identify, evaluate, and synthesize key studies that considered novel computational techniques for blood demand forecasting and inventory management through a search of PubMed and Web of Sciences databases for studies published from January 01, 2016, to March 30, 2023. The studies were analyzed for their utilization of various techniques, and their strengths, limitations, and areas for improvement. Seven key studies were identified. The studies focused on different blood components using various computational methods, such as regression, machine learning, hybrid models, and time series models, across different locations and time periods. Key variables used for demand forecasting were largely derived from electronic health record data, including clinical related predictors such as laboratory test results and hospital census by location. Each study offered unique strengths and valuable insights into the use of data-driven methods in blood bank management. Common limitations were unknown generalizability to other healthcare settings or blood components, need for field-specific performance measures, lack of ABO compatibility consideration, and ethical challenges in resource allocation. While data-driven research in blood demand forecasting and management has progressed, limitations persist and further exploration is needed. Understanding these innovative, interdisciplinary methods and their complexities can help refine inventory strategies and address healthcare challenges more effectively, leading to more robust, accurate models to enhance blood management across diverse healthcare scenarios.

A Model Selection Approach for Time Series Forecasting: Incorporating Google Trends Data in Australian Macro Indicators.

This study examined whether the behaviour of Internet search users obtained from Google Trends contributes to the forecasting of two Australian macroeconomic indicators: monthly unemployment rate and monthly number of short-term visitors. We assessed the performance of traditional time series linear regression (SARIMA) against a widely used machine learning technique (support vector regression) and a deep learning technique (convolutional neural network) in forecasting both indicators across different data settings. Our study focused on the out-of-sample forecasting performance of the SARIMA, SVR, and CNN models and forecasting the two Australian indicators. We adopted a multi-step approach to compare the performance of the models built over different forecasting horizons and assessed the impact of incorporating Google Trends data in the modelling process. Our approach supports a data-driven framework, which reduces the number of features prior to selecting the best-performing model. The experiments showed that incorporating Internet search data in the forecasting models improved the forecasting accuracy and that the results were dependent on the forecasting horizon, as well as the technique. To the best of our knowledge, this study is the first to assess the usefulness of Google search data in the context of these two economic variables. An extensive comparison of the performance of traditional and machine learning techniques on different data settings was conducted to enable the selection of an efficient model, including the forecasting technique, horizon, and modelling features.

How climate change affects electricity consumption in Chinese cities-a differential perspective based on municipal monthly panel data.

Addressing the impacts of climate change has become a global public crisis and challenge. China is characterized by a complex and diverse topography and vast territory, which makes it worthwhile to explore the differential impacts of climate change on urban electricity consumption in different zones and economic development conditions. This study examines the differential impact of climate factors on urban electricity consumption in China based on monthly panel data for 282 prefectures from 2011 to 2019 and projects the potential demand for future urban electricity consumption under different climate change scenarios. The results show that (1) temperature changes significantly alter urban electricity consumption, with cooling degree days (CDD) and heating degree days (HDD) contributing positively to urban electricity consumption in areas with different regional and economic development statuses, with elasticity coefficients of 0.1015-0.1525 and 0.0029-0.0077, respectively. (2) The temperature-electricity relationship curve shows an irregular U-shape. Each additional day of extreme weather above 30 °C and below -12 °C increases urban electricity consumption by 0.52% and 1.52% in the north and by 2.67% and 1.32% in the south. Poor cities are significantly more sensitive to extremely low temperatures than rich cities. (3) Suppose the impacts of climate degradation on urban electricity consumption are not halted. In that case, the possible Shared Socioeconomic Pathways 1-1.9 (SSP1-1.9), SSP1-2.6, and SSP2-4.5 will increase China's urban electricity consumption by 1621.96 billion kWh, 2960.87 billion kWh, and 6145.65 billion kWh, respectively, by 2090. Finally, this study makes some policy recommendations and expectations for follow-up studies.

Specifying a cascade water demand forecasting model using time-series analysis: a case of Jordan.

This study aims to develop a model for forecasting water demand for 2021-2030 to examine water availability for municipality uses in the Al-Balqa governorate of Jordan. The method was developed using a time series analysis of historical data from 1990-2010, which comprised yearly and monthly water consumption and socioeconomic factors, including population, income, and climate factors, such as average precipitation and temperatures. The analysis of historical data was conducted using the Statistical Package for the Social Sciences. The study found that the increase in population, reaching 740,790 inhabitants in 2030, the high level of social life, and the fluctuation of temperature and precipitation exceed the significant water demand, increasing to 69.88 million cubic meters in 2030 from 52.95 in 2020. The time series analysis employed historical data for 2011-2020 indicating monthly municipal water use to measure the model's validity. The results confirm the model's ability to forecast water demand. The study recommends intensifying managerial practices to avoid such difficulties that face the water sector to achieve water security at the country's level.

The impact of public health emergencies on hotel demand - Estimation from a new foresight perspective on the COVID-19.

This paper proposes a new foresight approach to estimate the impact of public health emergencies on hotel demand. The forecasting-based influence evaluation consists of four modules: decomposing hotel demand before an emergency, matching each decomposed component to a forecasting model, combining the predictions as the expected demand after the emergency, and estimating the impact by comparing actual demand against that predicted. The method is applied to analyze the impact of COVID-19 on Macao's hotel industry. The empirical results show that: 1) the new approach accurately estimates COVID-19's impact on hotel demand; 2) the seasonal and industry development components contribute significantly to the estimate of expected demand; 3) COVID-19's impact is heterogeneous across hotel services.

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.

Forecasting Future Demand of Nursing Staff for the Oldest-Old in China by 2025 Based on Markov Model.

BACKGROUND: An aging population and an increase in the proportion of disabled elderly have brought an unprecedented global challenge, especially in China. Aside lack of professional long-term care facilities, the shortage of human resource for old-age care is also a major threat. Therefore, this study tries to forecast the demand scale of nursing staff for the oldest-old in 2025 in China servicing as a reference for the development plan of human resource for elderly nursing. METHODS: Based on CLHLS (Chinese Longitudinal Healthy Longevity Survey) 2011 and 2014, Logit model was used to construct the transition probability matrix of the elderly's health status (health/mild/moderate/severe disability and death). By using the data of the elderly population aged 65 or over in the 2010 national population census, we projected the number of Chinese oldest-old population in different health status by 2025 through Markov model and projected the scale of the demand of nursing staff combined with the human population ratio method. RESULTS: The forecast shows that the Chinese oldest-old population is about 52.6 million, among which 46.9 million are healthy, 3.7 million are mild, 0.8 million are moderate, and 1.2 million are severely disabled in 2025. Concurrently, the demand scale of nursing staff will be 5.6 million according to the low standard and 11.5 million according to the high standard. Thus, human resource supply of long-term care is worrying. CONCLUSION: In 2025, the population size of the Chinese oldest-old will be further expanded, and the demand of care will increase accordingly, leading to a vast gap in the nursing staff. Therefore, it is urgent to build a professional nursing staff with excellent comprehensive quality and reasonable quantity, to ensure the sustainable development of China's elderly care service industry.

Implementing a material planning and control method for special nutrition in a Brazilian public hospital.

This study aims to (i) propose a demand forecast model for special nutrition materials in the context of health services, and (ii) comparatively evaluate three inventory management and control systems (periodic review, continuous review and mixed) for special nutrition materials. For that, we carried out a case study in a Brazilian public teaching hospital where data and information collection were conducted over a span of 22 months (from January 2018 and were consolidated until October 2019). A six-step approach was followed to propose the demand forecasting models and, later, evaluate the inventory control systems for special nutrition materials. Results indicate that if the organization implements the proposed inventory management method, there could be savings of up to 33% in the stock values managed by the healthcare organization. This research shows the planning and control of special nutrition materials in an integrated manner. Demand forecasting methods have been combined with inventory management to promote systemic improvements to healthcare organization.

Projecting the effect of easing societal restrictions on non-COVID-19 emergency demand in the UK: Statistical inference using public mobility data.

While it is well established that societal restrictions have been effective in reducing COVID-19 emergency demand, evidence also suggests an impact upon emergency demand not directly related to COVID-19 infection. Hospital planning may benefit from a greater understanding of this association and the ability to reliably forecast future levels of non-COVID-19 demand. Activity data for Accident and Emergency (A&E) attendances and emergency admissions were sourced for all hospitals within the Bristol, North Somerset and South Gloucestershire healthcare system. These were regressed upon publicly available mobility data obtained from Google's Community Mobility Reports for the local area. Seasonal trends were controlled for using time series decomposition. The models were used to predict non-COVID-19 emergency demand under the UK Government's plan to sequentially lift all restrictions by 21 June 2021, in addition to three alternative hypothetical relaxation strategies. Rates of public mobility within the local area were shown to account for 77% and 65% of the variance in non-COVID-19 related A&E attendances and emergency admissions respectively. Modelling supports an increase in emergency demand in line with the level and timing of societal restrictions, with significant increases to be expected upon the ending of all legal limits. This study finds that non-COVID-19 emergency demand associates with the level of societal restrictions, with rates of public mobility representing a key determinant. Through predictive modelling, healthcare systems can improve their demand forecasting in effectively managing hospital capacity.

Forecasting Demand for the Typhoid Conjugate Vaccine in Low- and Middle-income Countries.

BACKGROUND: The World Health Organization (WHO) released a position paper in March 2018 calling for integration of a novel typhoid conjugate vaccine (TCV) into routine immunization along with catch-up campaigns for children up to age 15. Gavi, the Vaccine Alliance, has committed funding to help resource-constrained countries introduce this vaccine. In this article, the Typhoid Vaccine Acceleration Consortium forecasts demand if WHO recommendations are followed. METHODS: We built a model of global TCV introductions between 2020 and 2040 to estimate the demand of the vaccine for 133 countries. We estimated each country's year of introduction by examining its estimated incidence of typhoid fever, its history of introducing new vaccines, and any knowledge we have of its engagement with typhoid prevention, including intention to apply for Gavi funding. Our model predicted use in routine infant vaccination as well as campaigns targeting varying proportions of the unvaccinated population up to 15 years of age. RESULTS: Between 2020 and 2025, demand will predominantly come from African countries, many receiving Gavi support. After that, Asian countries generate most demand until 2030, when campaigns are estimated to end. Demand will then track the birth cohort of participating countries, suggesting an annual routine demand between 90 and 100 million doses. Peak demand is likely to occur between 2023 and 2026, approaching 300 million annual doses if campaign implementation is high. CONCLUSIONS: In our analysis, target population for catch-up campaigns is the main driver of uncertainty. At peak demand, there is some risk of exceeding presently estimated peak production capacity. Therefore, it will be important to carefully coordinate introductions, especially when accompanied by campaigns targeting large proportions of the eligible population.