Mathias Kern

On Optimising Resource Planning in BT plc with FOS

The need to move from reactive to proactive resource planning has been highlighted by industry analysts, academia and enterprises. Proactive resource planning provides business users with a view of future jobs, which in turn will help them to plan their workforce utilisation appropriately in order to reduce costs and improve customer satisfaction. This paper presents the application of FOS, an integrated service management system, for managing the resources of BT. FOS incorporates applications for reliable workload forecasting, optimised workforce planning, as well as advance tools for visualising and communicating the outputs to end users

Neural network demand models and evolutionary optimisers for dynamic pricing

Dynamic pricing is a pricing strategy where price for the product changes according to the expected demand for it. Some work on using neural network for dynamic pricing have been previously reported, such as for forecasting the demand and modelling consumer choices. However, little work has been done in using them for optimising pricing policies. In this paper, we describe how neural networks and evolutionary algorithms can be combined together to optimise pricing policies. Particularly, we build a neural network based demand model and use evolutionary algorithms to optimise policy over build model. There are two key benefits of this approach. Use of neural network makes it flexible enough to model a range of different demand scenarios occurring within different products and services, and the use of evolutionary algorithm makes it versatile enough to solve very complex models. We also evaluate the pricing policies found by neural network based model to that found by other widely used demand models. Our results show that proposed model is more consistent, adapts well in a range of different scenarios, and in general, finds more accurate pricing policy than other three compared models.

Integrated resource planning for diverse workforces

Resource planning is an integral component of service chain management as it ensures that customer commitments are met, that a high quality of service is maintained and that operational costs are kept as low as possible. Service enterprises with varied, manifold service offerings often employ large, diverse workforces to deliver their services. Such resource planning scenarios are particularly challenging as different types of services often require individual planning approaches but, at the same time, the aim is to resource plan for the entire workforce to guarantee an optimal overall balance. In this paper, we propose an integrated approach to resource planning for diverse workforces that combines the ability to plan separately and differently for distinct service categories with the ability to maintain control of and balance the entirety of resources. Furthermore, we present FieldPlan-90 as a real life case study that realizes this integrated resource planning approach.

Strategic Resource Planning

One of the cornerstones of successful organisations has been the optimal use of their workforce. Two types of resources characterise service organisations: front and back office resources. These resources are defined by their capability (i. e., skills), location and availability. Front office resources handle incoming demand whilst the back office resources execute the services related to the demand. Planning of such resources can be carried out at one of three levels: strategic, tactical and operational; referring to long-, medium-, and short-, term planning respectively. The three levels for planning may overlap or may be distinct. Either way there is a flow of information from strategic to tactical and from tactical to operational. The loop is then closed by flow of information from operational back to strategic (see Fig. 3.1). In this context, strategic planning provides information on the overall balance of customer demand with available resource capacity. Tactical planning suggests a coarsegrain allocation of resources to tasks with no consideration given to when those tasks must be executed. And operational planning represents the allocation of specific resources to specific tasks; detailing the specific times of execution. The level of detail required for planning increases as one moves in time from strategic to operational. For strategic planning it is sufficient to analyse resource requirements based on the number of resources and their levels of productivity. On the other hand, for operational planning it is imperative that details such as starting location, preferred working location, scheduled hours, and availability for overtime are identified for accurate deployment to be realised.

An Auction-Based System for Workforce Resource Allocation

In this paper, we look at the problem of workforce redeployments where we consider the deployment of field engineers within a company organisation. Traditional methods for solving such problems have focused primarily on using centralised decision makers and optimisation algorithms which compute results in a solely centralised manner. Now, auctions have shown to have been used successfully for allocating resources in various applications and systems. Thus, in this paper, we propose a system that makes use of auctions as a mechanism for allocating the resources (field engineers) between different geographical parts of an organisation.

Tactical Resource Planning and Deployment

One of the key goals for service businesses is to find the right balance between the quality of service delivered to its customers and the incurred cost. The quality of service should be as high as possible in order to achieve high customer satisfaction and retention, and this often increases costs. Authorising overtime, for example, to guarantee timely service delivery has financial consequences. However, costs generally should be as small as possible to achieve high profitability. Clearly both objectives are contradictory and often cannot be fully satisfied at the same time due to the constraints on resource utilisation

FieldPlan: Tactical Field Force Planning in BT

In a highly competitive market, BT faces tough challenges as a service provider for telecommunication solutions. A proactive approach to the management of its resources is absolutely mandatory for its success. In this paper, an AI-based planning system for the management of parts of BT’s field force is presented. FieldPlan provides resource managers with full visibility of supply and demand, offers extensive what-if analysis capabilities and thus supports an effective decision making process.

Dynamic Pricing with Neural Network Demand Models and Evolutionary Algorithms

The use of neural networks for demand forecasting has been previously explored in dynamic pricing literatures. However, not much has been done in its use for optimising pricing policies. In this paper, we build a neural network based demand model and show how evolutionary algorithms can be used to optimise the pricing policy based on this model. There are two key benefits of this approach. Use of neural network makes it flexible enough to model range of different demand scenarios occurring within different products and services, and the use of evolutionary algorithm makes it versatile enough to solve very complex models. We also compare the pricing policies found by neural network model to that found by using other widely used demand models. Our results show that proposed model is more consistent, adapts well in a range of different scenarios, and in general, finds more accurate pricing policy than the other three compared models.

Field Service Planning as an Enabler for Field Service Optimisation

In this paper, we present a solution developed at BTs Intelligent Systems Research Centre which addresses the issue of proactive service planning with the ultimate goal of aligning supply optimally to meet the anticipated demand. The planning process generates two plans; a capacity plan and a deployment plan. The capacity plan provides all relevant details in volume in terms of the anticipated demand and the available supply whereas the deployment plan is a finer-grained refinement of the capacity plan which specifies where resources should be deployed (geographical locations) and what resources should be used for (skill assignments). These plans are generated by efficiently matching a pool of available resources to a number of jobs that need to be done using an advanced search algorithm. Our optimisation approach incorporates a number of rules and parameters in order to satisfy variable sets of goals, for example to minimise cost, to maximise quality of service, or combinations of both