Buyer–Supplier Relationships: A Case Study of a Japanese and Western Alliance

With the increasing liberalisation of markets, new opportunities are emerging for smaller firms with unique products and services to establish strategic supply relationships with larger component buyers, sometimes across normal cultural divides. For many Western SMEs, developing a long-term relationship with a Japanese buyer has been critical for success in the market. However this involves the challenge of adapting to Japanese style buyer–supplier relations, especially in the monitoring area. This article reports the observations made in a field study of such a culturally sensitive relationship between a Japanese buyer and a Western supplier, especially in areas such as differing perceptions of product features and quality, business procedures, and rewards. Difficulties and solutions that arose in the relationship are logged, and the advantages of training at all staff levels, the potentially critical role of ‘link-pin’ and the value of formalised linking processes are examined as ways of achieving congruence between the expectations of the two sides.     

Gradient boosting for distributional regression: faster tuning and improved variable selection via noncyclical updates

We present a new algorithm for boosting generalized additive models for location, scale and shape (GAMLSS) that allows to incorporate stability selection, an increasingly popular way to obtain stable sets of covariates while controlling the per-family error rate. The model is fitted repeatedly to subsampled data, and variables with high selection frequencies are extracted. To apply stability selection to boosted GAMLSS, we develop a new “noncyclical” fitting algorithm that incorporates an additional selection step of the best-fitting distribution parameter in each iteration. This new algorithm has the additional advantage that optimizing the tuning parameters of boosting is reduced from a multi-dimensional to a one-dimensional problem with vastly decreased complexity. The performance of the novel algorithm is evaluated in an extensive simulation study. We apply this new algorithm to a study to estimate abundance of common eider in Massachusetts, USA, featuring excess zeros, overdispersion, nonlinearity and spatiotemporal structures. Eider abundance is estimated via boosted GAMLSS, allowing both mean and overdispersion to be regressed on covariates. Stability selection is used to obtain a sparse set of stable predictors.