Search results

Product success is contingent on forecasting when a product is needed and how it should be offered. Forecasting accuracy is contingent on the correct forecasting technique. Using supermarket data across two product categories, this chapter shows that using a bevy of forecasting methods improves forecasting accuracy. Accuracy is measured by the mean absolute percentage error. The optimal methods for one consumer goods product may be different than for another. The best model varied from sophisticated, most such as autoregressive integrated moving average (ARIMA) and Holt–Winters to a random walk model. Forecasters must be proficient in multiple statistical techniques since the best technique varies within a categories, variety, and product size.

This study aims to predict overnight stays in Italy at tourist accommodation facilities through a nonlinear, single factor, stochastic model called CIR#. The contribution of this study is twofold: in terms of forecast accuracy and in terms of parsimony (both from the perspective of the data and the complexity of the modeling), especially when a regular pattern in the time series is disrupted. This study shows that the CIR# not only performs better than the considered baseline models but also has a much lower error than other additional models or approaches reported in the literature.

Typically, tourism demand tends to follow regular trends, such as low and high seasons on a quarterly/monthly level and weekends and holidays on a daily level. The data set consists of nights spent in Italy at tourist accommodation establishments as collected on a monthly basis by Eurostat before and during the COVID-19 pandemic breaking regular patterns.

Traditional tourism demand forecasting models may face challenges when massive amounts of search intensity indices are adopted as tourism demand indicators. In addition, given the importance of accurate forecasts, many studies have proposed novel hybrid models or used various combinations of methods. Thus, although there are clear benefits in adopting more complex approaches, the risk is that of dealing with unwieldy models. To demonstrate how this approach can be fruitfully extended to tourism, the accuracy of the CIR# is tested by using standard metrics such as root mean squared errors, mean absolute errors, mean absolute percentage error or average relative mean squared error.

The CIR# model is notably simpler than other models found in literature and does not rely on black box techniques such as those used in neural network (NN) or data science-based models. The carried analysis suggests that the CIR# model outperforms other reference predictions in terms of statistical significance of the error.

The proposed model stands out for being a viable option to the Holt–Winters (HW) model, particularly when dealing with irregular data.

The proposed model has demonstrated superiority even when compared to other models in the literature, and it can be especially useful for tourism stakeholders when making decisions in the presence of disruptions in data patterns.

The novelty lies in the fact that the proposed model is a valid alternative to the HW, especially when the data are not regular. In addition, compared to many existing models in the literature, the CIR# model is notably simpler and more transparent, avoiding the “black box” nature of NN and data science-based models.

一般来说, 旅游需求往往遵循规律的趋势, 例如季度/月的淡季和旺季, 以及日常的周末和假期。该数据集包括欧盟统计局在打破常规模式的2019冠状病毒病大流行之前和期间每月收集的在意大利旅游住宿设施度过的夜晚。

本研究旨在通过一个名为cir#的非线性单因素随机模型来预测意大利游客住宿设施的过夜住宿情况。这项研究的贡献是双重的:在预测准确性方面和在简洁方面(从数据和建模复杂性的角度来看), 特别是当时间序列中的规则模式被打乱时。我们表明, cir#不仅比考虑的基线模型表现更好, 而且比文献中报告的其他模型或方法具有更低的误差。

当大量搜索强度指标被作为旅游需求指标时, 传统的旅游需求预测模型将面临挑战。此外, 鉴于准确预测的重要性, 许多研究提出了新的混合模型或使用各种方法的组合。因此, 尽管采用更复杂的方法有明显的好处, 但风险在于处理难使用的模型。为了证明这种方法能有效地扩展到旅游业, 使用RMSE、MAE、MAPE或AvgReIMSE等标准指标来测试cir#的准确性。

cir#模型明显比文献中发现的其他模型简单, 并且不依赖于黑盒技术, 例如在神经网络或基于数据科学的模型中使用的技术。所进行的分析表明, cir#模型在误差的统计显著性方面优于其他参考预测。

这个模型作为Holt-Winters模型的一个拟议模型, 特别是在处理不规则数据时。

即使与文献中的其他模型相比, 所提出的模型也显示出优越性, 并且在数据模式中断时对旅游利益相关者做出决策特别有用。

创新之处在于所提出的模型是Holt-Winters模型的有效替代方案, 特别是当数据不规律时。此外, 与文献中的许多现有模型相比, cir#模型明显更简单、更透明, 避免了神经网络和基于数据科学的模型的“黑箱”性质。

Normalmente, la demanda turística tiende a seguir tendencias regulares, como temporadas altas y bajas a nivel trimestral/mensual y fines de semana y festivos a nivel diario. El conjunto de datos consiste en las pernoctaciones en Italia en establecimientos de alojamiento turístico recogidas mensualmente por Eurostat antes y durante la pandemia de COVID-19, rompiendo los patrones regulares.

El presente estudio pretende predecir las pernoctaciones en Italia en establecimientos de alojamiento turístico mediante un modelo estocástico no lineal de un solo factor denominado CIR#. La contribución de este estudio es doble: en términos de precisión de la predicción y en términos de parsimonia (tanto desde la perspectiva de los datos como de la complejidad de la modelización), especialmente cuando un patrón regular en la serie temporal se ve interrumpido. Demostramos que el CIR# no sólo aplica mejor que los modelos de referencia considerados, sino que también tiene un error mucho menor que otros modelos o enfoques adicionales de los que se informa en la literatura.

Los modelos tradicionales de previsión de la demanda turística pueden enfrentarse a desafíos cuando se adoptan cantidades masivas de índices de intensidad de búsqueda como indicadores de la demanda turística. Además, dada la importancia de unas previsiones precisas, muchos estudios han propuesto modelos híbridos novedosos o han utilizado diversas combinaciones de métodos. Así pues, aunque la adopción de enfoques más complejos presenta ventajas evidentes, el riesgo es el de enfrentarse a modelos poco manejables. Para demostrar cómo este enfoque puede extenderse de forma fructífera al turismo, se comprueba la precisión del CIR# utilizando métricas estándar como RMSE, MAE, MAPE o AvgReIMSE.

El modelo CIR# es notablemente más sencillo que otros modelos encontrados en la literatura y no se basa en técnicas de caja negra como las utilizadas en los modelos basados en redes neuronales o en la ciencia de datos. El análisis realizado sugiere que el modelo CIR# supera a otras predicciones de referencia en términos de significación estadística del error.

El modelo propuesto destaca por ser una opción viable al modelo Holt-Winters, sobre todo cuando se trata de datos irregulares.

El modelo propuesto ha demostrado su superioridad incluso cuando se compara con otros modelos de la bibliografía, y puede ser especialmente útil para los agentes del sector turístico a la hora de tomar decisiones cuando se producen alteraciones en los patrones de datos.

La novedad radica en que el modelo propuesto es una alternativa válida al Holt-Winters especialmente cuando los datos no son regulares. Además, en comparación con muchos modelos existentes en la literatura, el modelo CIR# es notablemente más sencillo y transparente, evitando la naturaleza de “caja negra” de los modelos basados en redes neuronales y en ciencia de datos.

Virgin Atlantic Cargo is one of the largest air freight operators in the world. As part of a wider strategic development initiative, the company has identified forecasting accuracy as of strategic importance to its operational efficiency. This is because accurate forecast enables the company to have the right resources available at the right place and time. The purpose of this paper is to undertake an evaluation of current month-to-date forecasting utilized by Virgin Atlantic Cargo. The study employed demand patterns drawn from historical data on chargeable weight over a seven-year-period covering six of the company's routes.

A case study is carried out, where a comparison between forecasting models is undertaken using error accuracy measures. Data in the form of historical chargeable weight over a seven-year-period covering six of the company's most profitable routes are employed in the study. For propriety and privacy reasons, data provided by the company have been sanitized.

Preliminary analysis of the time series shows that the air cargo chargeable weight could be difficult to forecast due to demand fluctuations which appear extremely sensitive to external market and economic factors.

The study contributes to existing literature on air cargo forecasting and is therefore of interest to scholars examining the problems of overbooking. Overbooking which is employed by air cargo operators to hedge against “no-show” bookings. However, the inability of air cargo operators to accurately predict cargo capacity unlikely to be used implies that operators are unable to establish with an aspect of certainty their revenue streams. The research methodology adopted is also predominantly discursive in that it employs a synthesis of existing forecasting literature and real-life data for accuracy analysis.

The purpose of this paper is to apply GM (1, 1) and TFGM (1, 1) models on the healthcare sector, which is a new area, and to show TFGM (1, 1) forecasting accuracy on this sector.

GM (1, 1) and TFGM (1, 1) models are presented. A hospital’s nine months (monthly) demand data is used for forecasting. Models are applied to the data, and the results are evaluated with MAPE, MSE and MAD metrics. The results for GM (1, 1) and TFGM (1, 1) are compared to show the accuracy of forecasting models. The grey models are also compared with Holt–Winters method, which is a traditional forecasting approach and performs well.

The results of this study indicate that TFGM (1, 1) has better forecasting performance than GM (1, 1) and Holt–Winters. GM (1, 1) has 8.01 per cent and TFGM (1, 1) 7.64 per cent MAPE, which means excellent forecasting power. So, TFGM (1, 1) is also an applicable forecasting method for the healthcare sector.

Future studies may focus on developed grey models for health sector demand. To perform better results, parameter optimisation may be integrated to GM (1, 1) and TFGM (1, 1). The demand may be predicted not only for the total demand on hospital, but also for the demand of hospital departments.

This study contributes to relevant literature by proposing fuzzy grey forecasting, which is used to predict the health demand. Therefore, the new application area as the health sector is handled with the grey model.

Through a case study, this paper reports on a research project to develop a risk integrated methodology for forecasting the cost of electricity in a National Health Service (NHS) acute care hospital building. The paper is formed of two strands. Strand one presents a rationale for selecting an appropriate time series forecasting method and strand two looks at the implementation of probabilistic modelling of the forecasts generated in strand one. The results of the research revealed that the Holt‐Winters multiplicative forecasting method produced the most reliable forecasts. The probabilistic modelling of the forecasts revealed that after a pair‐wise comparison between data collected at the hospital used as the case study and data collected from NHS acute care trusts nationwide, the forecasts were most likely to belong to the Weibull distribution. The results could then be used as inputs into a whole life cycle cost model or as a stand‐alone forecasting technique for predicting future electricity costs for use in the NHS Trust Financial Proforma returns.

Earnings forecasts provide useful numerical information concerning the expectations of a firm's future prospects and indicate management's ability to anticipate a firm's changing internal structure and external environment. The reasons for studying the accuracy of earnings forecasts is due to the Securities and Exchange Commission's position on financial forecasts and the issuance of a Statement of Position by the AICPA. These statements are important since they, in part, have motivated researchers to the importance of forecasting financial information. Consequently, if the disclosure of earnings forecasts in financial reports is permissable, the improvement of financial forecasts should be one of the primary concerns of the AICPA, the SEC, and numerous other interested groups.

Indian railways (IR) is one of the largest railway networks in the world. As a part of its strategic development initiative, demand forecasting can be one of the indispensable activities, as it may provide basic inputs for planning and control of various activities such as coach production, planning new trains, coach augmentation and quota redistribution. The purpose of this study is to suggest an approach to demand forecasting for IR management.

A case study is carried out, wherein several models i.e. automated autoregressive integrated moving average (auto-ARIMA), trigonometric regressors (TBATS), Holt–Winters additive model, Holt–Winters multiplicative model, simple exponential smoothing and simple moving average methods have been tested. As per requirements of IR management, the adopted research methodology is predominantly discursive, and the passenger reservation patterns over a five-year period covering a most representative train service for the past five years have been employed. The relative error matrix and the Akaike information criterion have been used to compare the performance of various models. The Diebold–Mariano test was conducted to examine the accuracy of models.

The coach production strategy has been proposed on the most suitable auto-ARIMA model. Around 6,000 railway coaches per year have been produced in the past 3 years by IR. As per the coach production plan for the year 2023–2024, a tentative 6551 coaches of various types have been planned for production. The insights gained from this paper may facilitate need-based coach manufacturing and optimum utilization of the inventory.

This study contributes to the literature on rail ticket demand forecasting and adds value to the process of rolling stock management. The proposed model can be a comprehensive decision-making tool to plan for new train services and assess the rolling stock production requirement on any railway system. The analysis may help in making demand predictions for the busy season, and the management can make important decisions about the pricing of services.

Better forecasting always leads to better management and planning of the operations. The container throughput data are complex and often have multiple seasonality. This makes it difficult to forecast accurately. The purpose of this paper is to forecast container throughput using deep learning methods and benchmark its performance over other traditional time-series methods.

In this study, long short-term memory (LSTM) networks are implemented to forecast container throughput. The container throughput data of the Port of Singapore are used for empirical analysis. The forecasting performance of the LSTM model is compared with seven different time-series forecasting methods, namely, autoregressive integrated moving average (ARIMA), simple exponential smoothing, Holt–Winter’s, error-trend-seasonality, trigonometric regressors (TBATS), neural network (NN) and ARIMA + NN. The relative error matrix is used to analyze the performance of the different models with respect to bias, accuracy and uncertainty.

The results showed that LSTM outperformed all other benchmark methods. From a statistical perspective, the Diebold–Mariano test is also conducted to further substantiate better forecasting performance of LSTM over other counterpart methods.

The proposed study is a contribution to the literature on the container throughput forecasting and adds value to the supply chain theory of forecasting. Second, this study explained the architecture of the deep-learning-based LSTM method and discussed in detail the steps to implement it.

In this chapter, we argue that under- and over-reaction are both parts of the price dynamics caused by investor's naïve judgmental extrapolation. We propose to use the Holt–Winters model, a parsimonious model with two parameters, to represent investor's conservatism (anchoring) and representativeness (trending). The complexity of earning information, which is broken down into a drift, a transitory shock, and an autocorrelated permanent shock, add further volatility to the price. We explain the price dynamics caused by the interplay of the earning model and investor's naïve belief. It is further argued that empirical “underreaction” and “overreaction” differ from true under- and overreaction. The simulated results with the proposed model confirm with empirical findings on under- and overreaction.

This paper looks at the application of economic and financial series in forecasting IPD monthly rental series. The approach follows that employed in classical business cycle work that seeks to decompose series into trend, cyclical and noise components and is the first time that it has been applied to IPD monthly data. Trend extraction is obtained by means of the Hodrick‐Prescott filter. Several potential indicator series are investigated together with their lead characteristics. The short‐term forecasts of these series are compared with naïve methods and a composite indicator. The results show the naïve methods, especially the Holt‐Winters method, and certain leading indicator series produce satisfactory short‐term forecasts, but the success is both sector and time‐dependent. This suggests that it is a worthwhile endeavour in identifying potential leading indicator series. The methodology presented in this paper should be seen as complementing existing approaches that employ standard econometric procedures in modelling rental growth.