Title: Sensitivity analysis using discrete event simulation on the selling times of a fraction of a stock
Authors: Elizaveta Logosha - Universite de technologie de Troyes (France) [presenting]
Frederic Bertrand - IRMA/Universite de technologie de Troyes (France)
Myriam Maumy - IRMA/Universite of Technology of Troyes (France)
Abstract: Process simulation is a technique used in various branches of industry. When speaking about the commercial process, less attention is paid to machine capacity or resource utilization, and more to the generation of customers, their transit times between the process steps such as discovery, proposal, purchase, and the prediction of the required number of sales. The construction of a theoretic model allows representing these sales and the state of the stock in real time through the simulation of discrete events. It is necessary to determine the impact of different simulation parameters and process characteristics on the quantities required, such as the percentage of depleting stock. An example of a stock is the number of flats in a future building. The sales process, studied by means of a process mining technique, is simulated according to these parameters in order to obtain as a result a number of different scenarios and to determine the confidence interval for the sale date of the specified percentage of the product. The study of the accuracy of the date found is completed by sensitivity analysis and determination of Sobol indices.