Forecast quality improvement with Action Research: A success story at PharmaCo

There is a gap in the forecasting research surrounding the theory of integrating and improving forecasting in practice. The number of academically affiliated consultancies and knowledge transfer projects that there are around, due to a need for improvements in forecast quality, would suggest that many interventions and actions are taking place. However, the problems that surround practitioner understanding, learning and usage are rarely documented. This article takes the first step toward trying to rectify this situation by using the specific case study of a fully engaged company. A successful action research intervention in the Production Planning and Control work unit improved the use and understanding of the forecast function, contributing to substantial savings, enhanced communication and improved working practices.     

Stock market volatility forecasting: Do we need high-frequency data?

The general consensus in the volatility forecasting literature is that high-frequency volatility models outperform low-frequency volatility models. However, such a conclusion is reached when low-frequency volatility models are estimated from daily returns. Instead, we study this question considering daily, low-frequency volatility estimators based on open, high, low, and close daily prices. Our data sample consists of 18 stock market indices. We find that high-frequency volatility models tend to outperform low-frequency volatility models only for short-term forecasts. As the forecast horizon increases (up to one month), the difference in forecast accuracy becomes statistically indistinguishable for most market indices. To evaluate the practical implications of our results, we study a simple asset allocation problem. The results reveal that asset allocation based on high-frequency volatility model forecasts does not outperform asset allocation based on low-frequency volatility model forecasts.     

Influential factors on Chinese airlines’ profitability and forecasting methods

We establish profit models to predict the performance of airlines in the short term using the quarterly profit data collected on the three largest airlines in China together with additional recent historical data on external influencing factors. In particular, we propose the application of the LASSO estimation method to this problem and we compare its performance with a suite of other more modern state-of-the-art approaches including ridge regression, support vector regression, tree regression and neural networks. It is shown that LASSO generally outperforms the other approaches in this study. We concluded a number of findings on the oil price and other influential factors on Chinese airline profitability.     

颠覆性技术识别与预测方法研究进展

为了把握颠覆性技术识别与预测方法研究进展，首先对颠覆性的内涵、特征和运行机制进行论述；然后，通过对已有文献进行系统梳理，将识别与预测方法分为5类，分别展开详述；最后，对各类方法进行比较分析。研究发现，已有颠覆性技术识别与预测方法仍处于发展的初期阶段，所有识别研究方法均围绕颠覆性技术的外部影响或内在特征中的某一方面展开，并未将二者有机结合起来。未来，应综合把握颠覆性技术内外部特征，构建全面、系统的识别与预测框架。     

A note on “Bed allocation techniques based on census data”

Capacity planning and resource allocation are crucial to the cost-effective delivery of health care services. In this paper, we present an analytic approach based on a modified version of the Holt-Winters multiplicative seasonality forecasting model to determine the frequency distribution associated with a hospital care unit's census. This paper is a follow-up to the census frequency distribution simulation model described in Lapierre et al. (Socio Econ. Plan. Sci. 33 (1999) 25). We demonstrate that our model can provide census frequency distributions equivalent to the simulation model of Lapierre et al. [1], but without the computational effort common to simulation models.     

A note on forecasting international tourism demand in Spain

This paper considers the extent to which price and income proxy variables help in forecasting tourist demand in Spain. Contrary to some recent studies, we found that the inputs' contribution in terms of fitting and forecasting is nil when compared with alternative univariate models. Whether these findings are the results of the restrictions embedded in building the proxy inputs or in a poor specification of the dynamics of these models remains to be seen. We also contend that when dealing with medium, long-term forecasting comparisons, the use of the traditional aggregate accuracy measures like RMSE and MAPE help very little in discriminating among competing models. In these situations, predicted annual growth rates may be a better alternative.     

Forecasting category sales and market share for wireless telephone subscribers: a combined approach

The ability to forecast market share remains a challenge for many managers especially in dynamic markets, such as the telecommunications sector. In order to accommodate the unique dynamic characteristics of the telecommunications market, we use a multi-component model, called MSHARE. Our method involves a two-phase process. The first phase consists of three components: a projection method, a ring down survey methodology and a purchase intentions survey. The predictions from these components are combined to forecast category sales for the wireless subscribers market. In the second phase, market shares for the various brands are generated using the forecast of the number of subscribers that are obtained in Phase 1 and the share predictions from the ring down methodology. The proposed methodology produces the minimum Relative Absolute Error for each market as compared to the forecasts from each individual component in the first phase. The value of the proposed model is illustrated by its application to a real world scenario. The managerial implications of the proposed model are also discussed.     

Multiple generation product life cycle predictions using a novel two-stage fuzzy piecewise regression analysis method

Product life cycle (PLC) prediction plays a crucial role in strategic planning and policy definition for high-technology products. Forecast methodologies which can predict PLCs accurately can help to achieve successful strategic decision-making, forecasting, and foresight activities in high-technology firms, research institutes, governments, and universities. Over the past few decades, even though analytic framework strategies have been proposed for production, marketing, R&D (research and development), and finance, aiming at each stage of PLCs, forecast methodologies with which to predict PLCs are few. The purpose of this research is to develop a novel forecast methodology to allow for predictions of product life time (PLT) and the annual shipment of products during the entire PLC of multiple generation products. A novel two-stage fuzzy piecewise regression analysis method is proposed in this paper. In the first stage, the product life-time of the specific generation to be analyzed will be predicted by the fuzzy piecewise regression line that is derived based upon the product life-time of earlier generations. In the second stage of the forecast methodology, the annual shipment of products of the specified generation will be predicted by deriving annual fuzzy regression lines for each generation, based upon the historical data on the earlier generations' products. An empirical study predicting the life-time and the annual shipment of the 16 Mb (Mega bit) DRAM (Dynamic Random Access Memory) PLC is illustrated to validate the analytical process. The results demonstrate that two-stage fuzzy piecewise regression analysis can predict multiple generation PLT and PLC precisely, thereby serving as a foundation for future strategic planning, policy definitions and foresights.     

Forecasting economic time series with unconditional time-varying variance

The classical forecasting theory of stationary time series exploits the second-order structure (variance, autocovariance, and spectral density) of an observed process in order to construct some prediction intervals. However, some economic time series show a time-varying unconditional second-order structure. This article focuses on a simple and meaningful model allowing this nonstationary behaviour. We show that this model satisfactorily explains the nonstationary behaviour of several economic data sets, among which are the U.S. stock returns and exchange rates. The question of how to forecast these processes is addressed and evaluated on the data sets.     

Minnesota-type adaptive hierarchical priors for large Bayesian VARs

Large Bayesian VARs with stochastic volatility are increasingly used in empirical macroeconomics. The key to making these highly parameterized VARs useful is the use of shrinkage priors. We develop a family of priors that captures the best features of two prominent classes of shrinkage priors: adaptive hierarchical priors and Minnesota priors. Like adaptive hierarchical priors, these new priors ensure that only ‘small’ coefficients are strongly shrunk to zero, while ‘large’ coefficients remain intact. At the same time, these new priors can also incorporate many useful features of the Minnesota priors such as cross-variable shrinkage and shrinking coefficients on higher lags more aggressively. We introduce a fast posterior sampler to estimate BVARs with this family of priors—for a BVAR with 25 variables and 4 lags, obtaining 10,000 posterior draws takes about 3 min on a standard desktop computer. In a forecasting exercise, we show that these new priors outperform both adaptive hierarchical priors and Minnesota priors.