Exploring the financial consequences of the servitization of manufacturing

Commentators suggest that to survive in developed economies manufacturing firms have to move up the value chain, innovating and creating ever more sophisticated products and services, so they do not have to compete on the basis of cost. While this strategy is proving increasingly popular with policy makers and academics there is limited empirical evidence to explore the extent to which it is being adopted in practice. And if so, what the impact of this servitization of manufacturing might be. This paper seeks to fill a gap in the literature by presenting empirical evidence on the range and extent of servitization. Data are drawn from the OSIRIS database on 10,028 firms incorporated in 25 different countries. The paper presents an analysis of these data which suggests that: [i] manufacturing firms in developed economies are adopting a range of servitization strategies-12 separate approaches to servitization are identified; [ii] these 12 categories can be used to extend the traditional three options for servitization-product oriented Product-Service Systems, use oriented Product-Service Systems and result oriented Product-Service Systems, by adding two new categories "integration oriented Product-Service Systems" and "service oriented Product-Service Systems"; [iii] while the manufacturing firms that have servitized are larger than traditional manufacturing firms in terms of sales revenues, at the aggregate level they also generate lower profits as a % of sales; [iv] these findings are moderated by firm size (measured in terms of numbers of employees). In smaller firms servitization appears to pay off while in larger firms it proves more problematic; and [v] there are some hidden risks associated with servitization-the sample contains a greater proportion of bankrupt servitized firms than would be expected. © Springer Science + Business Media, LLC 2009.

Random function priors for exchangeable arrays with applications to graphs and relational data

A fundamental problem in the analysis of structured relational data like graphs, networks, databases, and matrices is to extract a summary of the common structure underlying relations between individual entities. Relational data are typically encoded in the form of arrays; invariance to the ordering of rows and columns corresponds to exchangeable arrays. Results in probability theory due to Aldous, Hoover and Kallenberg show that exchangeable arrays can be represented in terms of a random measurable function which constitutes the natural model parameter in a Bayesian model. We obtain a flexible yet simple Bayesian nonparametric model by placing a Gaussian process prior on the parameter function. Efficient inference utilises elliptical slice sampling combined with a random sparse approximation to the Gaussian process. We demonstrate applications of the model to network data and clarify its relation to models in the literature, several of which emerge as special cases.

Dynamic Covariance Models for Multivariate Financial Time Series

The accurate prediction of time-changing covariances is an important problem in the modeling of multivariate financial data. However, some of the most popular models suffer from a) overfitting problems and multiple local optima, b) failure to capture shifts in market conditions and c) large computational costs. To address these problems we introduce a novel dynamic model for time-changing covariances. Over-fitting and local optima are avoided by following a Bayesian approach instead of computing point estimates. Changes in market conditions are captured by assuming a diffusion process in parameter values, and finally computationally efficient and scalable inference is performed using particle filters. Experiments with financial data show excellent performance of the proposed method with respect to current standard models.