Machine learning for multi-criteria inventory classification applied to intermittent demand

Multi-criteria inventory classification groups inventory items into classes, each of which is managed by a specific re-order policy according to its priority. However, the tasks of inventory classification and control are not carried out jointly if the classification criteria and the classification approach are not robustly established from an inventory-cost perspective. Exhaustive simulations at the single item level of the inventory system would directly solve this issue by searching for the best re-order policy per item, thus achieving the subsequent optimal classification without resorting to any multi-criteria classification method. However, this would be very time-consuming in real settings, where a large number of items need to be managed simultaneously.

In this article, a reduction in simulation effort is achieved by extracting from the population of items a sample on which to perform an exhaustive search of best re-order policies per item; the lowest cost classification of in-sample items is, therefore, achieved. Then, in line with the increasing need for ICT tools in the production management of Industry 4.0 systems, supervised classifiers from the machine learning research field (i.e. support vector machines with a Gaussian kernel and deep neural networks) are trained on these in-sample items to learn to classify the out-of-sample items solely based on the values they show on the features (i.e. classification criteria). The inventory system adopted here is suitable for intermittent demands, but it may also suit non-intermittent demands, thus providing great flexibility. The experimental analysis of two large datasets showed an excellent accuracy, which suggests that machine learning classifiers could be implemented in advanced inventory classification systems.     

Control of interrelated research and development projects

The purpose of this paper is to examine a type of resource allocation problem arising in the context of research and development activities. The particular problem analyzed involves scheduling a group of projects in such a way that total cost is minimized while several precedence relations are satisfied and specific completion times are maintained. The primary difficulty results from the existence of commonalities that allow the successful completion of a particular project to be applied to several different purposes. A solution approach is developed which combines a one-pass network algorithm to deal with the precedence and time restrictions and a dynamic programming procedure to allocate the resources to each project.     

Physician anger, Part 2. More on the dance of anger.

This article is a follow-up to an interview with Charles Dwyer, PhD, which appeared in the 1999 March/April issue of The Physician Executive. He described how physician executives can change the perceptions of today's beleaguered physicians and help them cope with change. We then asked him for some hands-on strategies to deal with physician anger, fear, and resentment. After much contemplation on providing a list of "fixes" that will restore each of us to a state of greater satisfaction, Dr. Dwyer concludes that there are no generalizable solutions because there are too many variables that come into play in each organization, individual, or group. Attending to the self can provide both individual rescue from these turbulent times and the best hope for changes in the system from which patients and health care providers can benefit. If physicians are to regain their power and maintain, or even improve, their quality of life, clearly changes are called for. And these are changes that require persistent effort and uncomfortable adjustments.     

Marriages and fertility among Turkish and Moroccan women in Belgium: results from census data

The patterns of family formation and fertility behavior of Turkish and Moroccan women in Belgium are changing rapidly. The census data (1991) indicate a fertility decline. The reasons are changes in the nuptiality patterns, contraceptive behavior, and migratory flows. The changes are not identical in both communities. Young cohorts postpone their marriage, but this is most prominent among Moroccan women. On the other hand, young Turkish women have a clear preference for smaller families. The changes also differentiate according to migrant "generation" and level of education. The changes are not restricted to Belgium but are also observed in the countries of origin.     

THE UNCERTAIN FUTURE OF IDEOLOGY: Rereading Marx

Throughout its history, "ideology" (the concept and theory) served as social science's foil, an opposing standard against which it defined its own knowledge-as-truth. As social science since mid-century has undergone changes in its idea of itself and its methods of inquiry, the theory of ideology has served as register, visably recording these changes. Works by the structuralists and poststructuralists, especially Althusser and Foucault, forced upon social theorists a profound rethinking of power and its operations and moved "ideology" away from the theory of false consciousness towards a view of ideology as cultural practice. For some, ideology theory is obsolete (due to its classical roots as "false consciousness") or redundant (due to its links to "culture"). Despite the merits of these arguments, a provisional argument on behalf of ideology theory is offered.

Marxism, after drawing us to it as the moon draws the tides, after transforming all our ideas, after liquidating the categories of our bourgeois thought, abruptly left us stranded.

—Jean-Paul Sartre