2020-07-31 –, Green Track
Proper HR management within an organisation is vital in the current day and age. Because of this task’s complexity, managers should be able to rely on good tools or models to support them, so they can gauge the short and long term impact of their decisions before making them. To this end, we developed a generalised manpower simulation engine in Julia, using SimJulia. We present this tool’s main features, highlight some of the encountered difficulties, and illustrate how it can be employed.
Many studies have shown that proper human resource management is vital to the success of any organisation. This means that managers need to balance the needs of the organisation with the needs of their employees, and are required to make well-informed planning decisions. One part of the problem covers short term planning, such as setting up employee rosters to ensure an appropriate distribution of the workload over the employees. The other part deals with long term manpower planning, and usually concerns hiring and promotion policies to meet the organisation’s goals without alienating its employees. Naturally, any of the planning decisions have to be made within a certain legal framework that the organisation cannot influence.
As such, such decisions are too important to be left to the manager’s "gut feeling". Instead, they can rely on a variety of mathematical models to provide invaluable insights to allow them to make the appropriate decisions. These models can be of various types: Markov models, optimisation models using mathematical programming, stochastic simulation models, or system dynamics models, each with their own benefits and drawbacks.
In particular, we have chosen to develop a tool, the Generic Manpower Simulation Engine (GMSE), based on stochastic simulation, as an organisation’s internal structure and policies are often too complex and varied to be able to estimate all the effects of a particular change. Instead, our tool allows the user to define the structure of the organisation and its policies, entering only the direct effect these policies have on the personnel members of that organisation. Once the system is configured, the user can then run the simulation for the period of interest, and request reports on the state of the organisation at any time point covered by the simulation. This allows the user to get a prediction of the full impact of specific proposed policy changes, among other applications.
The GMSE is developed entirely in Julia with the SimJulia library at its core, and provides all the necessary methods to fully configure a manpower simulation from within Julia for the expert user, as well as a way to configure one from MS Excel.
In addition to giving an overview of the GMSE, we will show how we use the SimJulia library, and we illustrate some of the challenges we faced, and how we decided to handle those challenges. Finally, we give a quick overview of how we can use the GMSE to optimise the organisation’s policies.
JOHAN VAN KERCKHOVEN graduated from the Vrije Universiteit Brussel (VUB) in Brussels as a Master in Mathematics (Licentiaat in de Wiskunde), with specialisation in statistics, in 2002. He worked as a university researcher, specialising in variable selection methods in predictive modelling and robust statistics, and teaching assistant at various Belgian universities (2002-2012), obtaining his PhD in Applied Economics in 2008 at the Katholieke Universiteit Leuven. From 2012-2016 he worked as market risk modeller at KBC. He joined the department MWMW of the Royal Military Academy as a researcher in 2016, specialising in (discrete event) simulation, in particular using SimJulia.