Didier Soopramanien

The value of competitive information in forecasting FMCG retail product sales and the variable selection problem

Sales forecasting at the UPC level is important for retailers to manage inventory. In this paper, we propose more effective methods to forecast retail UPC sales by incorporating competitive information including prices and promotions. The impact of these competitive marketing activities on the sales of the focal product has been extensively documented. However, competitive information has been surprisingly overlooked by previous studies in forecasting UPC sales, probably because of the problem of too many competitive explanatory variables. That is, each FMCG product category typically contains a large number of UPCs and is consequently associated with a large number of competitive explanatory variables. Under such a circumstance, time series models can easily become over-fitted and thus generate poor forecasting results.

Consumer decision making, E-commerce and perceived risks

This article studies how adoption and usage behaviour of the Internet and online shopping, respectively influence the preference to use electronic commerce to purchase different types of products. We empirically model the preference for electronic commerce when consumers have to buy different types of products and thus face different types of risks (Cox and Rich, 1964). Unlike previous research, we find that consumers who have previously shopped online, display stronger preferences to buy products on the Internet irrespective of the perceived level of product-specific risks of online shopping. This article provides an interesting and novel insight into how both adoption and usage of electronic commerce impact on the attitude and risk perception of buying less predictable (more risky) products on the Internet.

A new look at gender effects in participation and occupation choice

The growth in female labour participation and occupational attainment represents the most dramatic feature of labour markets in the second half of the twentieth century. This has been due in part to developments in social attitudes and the consequent changes in the prices attached to womens characteristics, and in part to changes in those characteristics themselves. This paper analyses these issues by constructing models of participation and occupational choice for the years 1970 and 1990, and then by evaluating which participation and occupation regimes would have been selected by respondents with the characteristics of women observed in 1970 had they faced the coefficients which obtained in 1990. It is established that changing prices accounts for a substantial part of the improvement in womens fortunes in the labour market. To provide a basis of comparison, the model is also estimated for men. Choices concerning occupational and labour market participation are modelled using both the standard multinomial

Simulation of Career Development in the European Commission

The European Commission (the Commission) employs more than 22,000 officials who provide administrative services to the European Union. In 2003, the Commission introduced a performance appraisal and promotion system based on points that the officials earn each year. In 2006, the Commission realized that the system needed to be revised. To support the review process, the Commission invited tenders for a project to develop simulation models that it could use to project the future performance of the existing system. A team from Lancaster University won the bid and subsequently worked closely with Commission officials to develop a new system. In 2009, the stakeholders in the Commissions performance appraisal and promotion system agreed to implement the improved system. The simulation model is unusual in the field of manpower planning because it models the consequences of appraisal-system rules. It uses novel, accurate, and efficient sampling techniques that are based on regression models of the underlying relationships in the data. The model was a crucial part of renegotiating the appraisal and promotion system and implementing a new system.

Behavioural modelling of career progression in the European Commission

Though manpower planning models have been part of OR for many years, and simulation has always been acknowledged as a potential approach, there are few reported applications of its use. In this case-based study we report on a micro-simulation model that exploits the structure of the European Commission’s appraisal and promotion rules, and includes regression-based sampling schemes which allow for non-Normal error terms to represent behavioural factors that led to the need for a new system. With a suitably parsimonious formulation the 20,000 person model runs very effectively, and the transparency associated with simulation proves an important factor in the successful use of the model as the basis for designing a promotion box system that was implemented across the Commission in 2009. The simulation modelling incorporates many Markov-type elements, and we reflect on important lessons learned from this combined use of micro-simulation and Markov-based approaches to manpower modelling.

Risk in Credit Granting and Lending Decisions: Credit Scoring

The discipline of credit scoring is concerned with the development and application of predictive models of the likelihood that credit obligations will be met. The likelihood that credit obligations will be met represents the risk attached to granting credit. In this paper, the authors present an overview of the context of credit scoring and how it fits in the wider research area of risk analysis and prediction. The interested reader who wishes to pursue further research in this area will develop a pedagogical appreciation of this growing area of research in predictive risk analysis. Keywords: credit scoring; risk of default; modeling and prediction