Search

Retail forecasting is a diverse and dynamic research area encompassing a variety of different topics. The advent of online channels, the increasing complexity of product ranges, and the shortening lifespan of many items are as examples of some of the new challenges that maintain the importance of improving forecasting in this domain. This thesis aims to address questions in retail forecasting that are closely linked with relevant problems faced in the industry. As such, the problems have been identified through a combination of reviewing the academic literature, discussion, and engagement with practitioners. This thesis starts by considering the situation where demand series are influenced by multiple seasonal and calendar effects. This is a challenge which is widespread due to high frequency sampling and decision making in retailing. We develop a new model to accommodate flexibility in modelling complex seasonal patterns, which also aids with mitigating the effect of short demand histories on forecasting performance. The new model is embedded in an innovations state-space formulation and it is demonstrated empirically using wholesale food data to provide competitive forecasting accuracy to established benchmarks. Next, the dual problems of SKU-level model parameter estimation and forecasting are considered. For retailers experiencing frequent promotional activities, this is a principal issue. The parameter estimates provide insights about the elasticity of different factors on demand for the SKU, and therefore inform marketing planning. Accurate forecasts, for both promotional and baseline periods, support other functions such as replenishment and inventory management. First, a geometric parameter inheritance procedure is proposed, which uses aggregate information within a product hierarchy to improve parameter estimates under certain assumptions. At brand level, it is typically easier to better estimate elasticity effects, making this strategy preferable. Second, a debiasing approximation is derived for the forecasting procedure, which is demonstrated to reduce bias, whilst remaining competitive in terms of forecast accuracy, as shown in a simulation study. The debiasing approximation is then evaluated with an inventory simulation study, which examines the conditions under which improvements in inventory performance can be gained. The conclusions give useful insights for inventory managers, and demonstrate that bias is a significant factor in inventory performance.

Validation in language testing is an ongoing process in which information is collected through investigations into the design, implementation, products and impacts of an assessment (Sireci, 2007). This includes the cognitive processes elicited from candidates by a test (Weir, 2005). This study investigated the English Speaking Board’s ESOL International examinations at levels B2 and C1 of the CEFR. The study considered the role of discourse competence in successful performances through examination of cognitive phases employed by candidates and metadiscourse markers and whether the use fit with models such as the CEFR and Field (2004) and so contributed to the validation argument. The study had two strands. The process strand of the study was largely qualitative and focussed on the cognitive processes which candidates used to compose their texts. Verbal reports were carried out with a total of twelve participants, six at each level. The product strand of the study analysed the use of metadiscourse markers in the scripts of sixty candidates in order to identify developing features of discourse competence at levels B2 and C1. The process strand of the study identified that there were statistically significant differences in the cognitive phases employed by the participants in the study. The investigation also identified a number of differences in what B2 and C1 learners attended to while carrying out the different phases. The product strand of the study found no statistically significant differences in the use of metadiscourse markers used by candidates at the two levels, but observed differences in the way particular metadiscourse markers were employed. These differences indicate the direction for a possible larger-scale study. Unlike previous studies into metadiscourse (Burneikaite, 2008; Plakans, 2009; Bax, Nataksuhara & Waller, forthcoming) the study controlled for task, text type and rhetorical pattern and nationality. The study suggested that discourse competence contributed to higher-level performances in writing and that the examinations under investigation elicited a wide range of cognitive phases from C1 candidates. The study also suggested that many of the CEFR’s statements about the development of discourse competence at the higher levels are correct.