Search results

Retail sales usually exhibit strong trend and seasonal patterns. Practitioners have typically used seasonal autoregressive integrated moving average (ARIMA) models to predict retail sales exhibiting these patterns. Due to economic instability, recent retail sales time-series data show a higher degree of variability and nonlinearity, which makes the ARIMA model less accurate. This chapter demonstrates the feasibility and potential of applying empirical mode decomposition (EMD) in forecasting aggregate retail sales. The hybrid forecasting method of integrating EMD and neural network (EMD-NN) models was applied to two real data sets from two different time periods. The one-period ahead forecasts for both time periods show that EMD-NN outperforms the classical NN model and seasonal ARIMA. In addition, the findings also indicate that EMD-NN can significantly improve forecasting performance during the periods in which macroeconomic conditions are more volatile.

Machine learning methods have recently gained attention in business applications. We will explore the suitability of machine learning methods, particularly support vector regression (SVR) and radial basis function (RBF) approximation, in forecasting company sales. We compare the one-step-ahead forecast accuracy of these machine learning methods with traditional statistical forecasting techniques such as moving average (MA), exponential smoothing, and linear and quadratic trend regression on quarterly sales data of 43 Fortune 500 companies. Moreover, we implement an additive seasonal adjustment procedure on the quarterly sales data of 28 of the Fortune 500 companies whose time series exhibited seasonality, referred to as the seasonal group. Furthermore, we prove a mathematical property of this seasonal adjustment procedure that is useful in interpreting the resulting time series model. Our results show that the Gaussian form of a moving RBF model, with or without seasonal adjustment, is a promising method for forecasting company sales. In particular, the moving RBF-Gaussian model with seasonal adjustment yields generally better mean absolute percentage error (MAPE) values than the other methods on the sales data of 28 companies in the seasonal group. In addition, it is competitive with single exponential smoothing and better than the other methods on the sales data of the other 15 companies in the non-seasonal group.

This research examines the use of a number of time series model structures of a moderate allocation mutual fund, PRWCX. PRWCX was rated as the top fund in its category during the past five years. The fund invests at least 50% of its total assets that the fund manager believes that have above average potential for capital growth. The remaining assets are generally invested in convertible securities, corporate and government debt bank loans, and foreign securities. Forecasting the total NAV of such a moderate allocation mutual fund, composed of an extremely large number of investments, requires a method that produces accurate results. These models are exponentially smoothing (single, double, and Winter’s Method), trend models (linear, quadratic, and exponential) are Box-Jenkins models.

Due to the increasing size and complexity of construction projects, construction engineering and management involves the coordination of many complex and dynamic processes and relies on the analysis of uncertain, imprecise and incomplete information, including subjective and linguistically expressed information. Various modelling and computing techniques have been used by construction researchers and applied to practical construction problems in order to overcome these challenges, including fuzzy hybrid techniques. Fuzzy hybrid techniques combine the human-like reasoning capabilities of fuzzy logic with the capabilities of other techniques, such as optimization, machine learning, multi-criteria decision-making (MCDM) and simulation, to capitalise on their strengths and overcome their limitations. Based on a review of construction literature, this chapter identifies the most common types of fuzzy hybrid techniques applied to construction problems and reviews selected papers in each category of fuzzy hybrid technique to illustrate their capabilities for addressing construction challenges. Finally, this chapter discusses areas for future development of fuzzy hybrid techniques that will increase their capabilities for solving construction-related problems. The contributions of this chapter are threefold: (1) the limitations of some standard techniques for solving construction problems are discussed, as are the ways that fuzzy methods have been hybridized with these techniques in order to address their limitations; (2) a review of existing applications of fuzzy hybrid techniques in construction is provided in order to illustrate the capabilities of these techniques for solving a variety of construction problems and (3) potential improvements in each category of fuzzy hybrid technique in construction are provided, as areas for future research.

Fluctuations in the tender price index have an adverse effect on the construction sector and the economy at large. This is largely due to the positive relationship that exists between the construction industry and economic growth. The consequences of these variations include cost overruns and schedule delays, among others. An accurate forecast of the tender price index is good for controlling the uncertainty associated with its variation. In the present study, the efficacy of using an adaptive neuro-fuzzy inference system (ANFIS) for tender price forecasting is investigated. In addition, the Box–Jenkins model, which is considered a benchmark technique, was used to evaluate the performance of the ANFIS model. The results demonstrate that the ANFIS model is superior to the Box–Jenkins model in terms of the accuracy and reliability of the forecast. The ANFIS could provide an accurate and reliable forecast of the tender price index in the medium term (i.e. over a three-year period). This chapter provides evidence of the advantages of applying nonlinear modelling techniques (such as the ANFIS) to tender price index forecasting. Although the proposed ANFIS model is applied to the tender price index in this study, it can also be applied to a wider range of problems in the field of construction engineering and management.

We evaluate the performance of financial analysts versus naïve models in making long-term earnings forecasts. Long-term earnings forecasts are generally defined as third-, fourth-, and fifth-year earnings forecasts. We find that for the fourth and fifth years, analysts' forecasts are no more accurate than naïve random walk (RW) forecasts or naïve RW with economic growth forecasts. Furthermore, naïve model forecasts contain a large amount of incremental information over analysts' long-term forecasts in explaining future actual earnings. Tests based on subsamples show that the performance of analysts' long-term forecasts declines relative to naïve model forecasts for firms with high past earnings growth and low analyst coverage. Furthermore, a model that combines a naïve benchmark (last year's earnings) with the analyst long-term earnings growth forecast does not perform better than analysts' forecasts or naïve model forecasts. Our findings suggest that analysts' long-term earnings forecasts should be used with caution by researchers and practitioners. Also, when analysts' earnings forecasts are unavailable, naïve model earnings forecasts may be sufficient for measuring long-term earnings expectations.

The chapter examines a comprehensive review of cross-disciplinary literature in the domain of supply chain forecasting during research period 1991–2017, with the primary aim of exploring the growth of literature from operational to demand centric forecasting and decision making in service supply chain systems. A noted list of 15,000 articles from journals and search results are used from academic databases (viz. Science Direct, Web of Sciences). Out of various content analysis techniques (Seuring & Gold, 2012), latent sementic analysis (LSA) is used as a content analysis tool (Wei, Yang, & Lin, 2008; Kundu et al., 2015). The reason for adoption of LSA over existing bibliometric techniques is to use the combination of text analysis and mining method to formulate latent factors. LSA creates the scientific grounding to understand the trends. Using LSA, Understanding future research trends will assist researchers in the area of service supply chain forecasting. The study will be beneficial for practitioners of the strategic and operational aspects of service supply chain decision making. The chapter incorporates four sections. The first section describes the introduction to service supply chain management and research development in this domain. The second section describes usage of LSA for current study. The third section describes the finding and results. The fourth and final sections conclude the chapter with a brief discussion on research findings, its limitations, and the implications for future research. The outcomes of analysis presented in this chapter also provide opportunities for researchers/professionals to position their future service supply chain research and/or implementation strategies.

The accuracy of forecasts has a critical impact on an organization. A new, practical, and meaningful forecast performance measure, percentage forecasting error (PFE), was introduced by the authors in an earlier publication. In this chapter, we examined the accuracy of the PFE under several different scenarios and found the results to indicate that PFE offers forecasters an accurate and practical alternative to assess forecast accuracy.

In scientific works on forecasting price volatility (of which the overwhelming majority, in comparison with works on price forecasting) for energy products: crude oil, natural gas, fuel oil, the authors compared the effectiveness of forecasting models of generalized autoregressive heteroscedasticity (Generalized Autoregressive Conditional Heteroscedastic model, GARCH) with regression of support vectors for futures contracts. GARCH models are a standard tool used in the literature on volatility, and the vector machine nonlinear regression model is one of the machine learning methods that has been gaining huge popularity in recent years. The authors have shown that the accuracy of volatility forecasts for energy and aluminum prices significantly depends on the volatility proxy used. The model with correctly defined parameters can lead to fewer prediction errors than GARCH models when the square of the daily yield is used as an indicator of volatility in the evaluation. In addition, it is difficult to choose the best model among GARCH models, but forecasts based on asymmetric GARCH models are often the most accurate. The work is based on a model with a representative investor who solves the problem of optimizing utility in a two-period model. The key assumption of the model is the homogeneity of energy and aluminum investor preferences, that is, preferences do not change over time. There are also works with an attempt to solve this problem in a continuous state space. A completely new theory has been put forward that allows predicting the movement of the underlying asset without using historical data, so this topic is very relevant.