Excursion Groups Flow Forecasting Based on Modified Random Forest
MAGAZINE №4 (99) August 2020
AUTHORS ASLAKHANOV A.R., PAVLOVA E.V.
CATEGORY Information technologies in logistics and SCM Logistics service management Optimization and mathematical modelling Simulation modelling
ABSTRACT
In recent years, both in Russia and worldwide, there has been an annual increase in the number of museum visitors with the most popular exhibitions being visited by millions of people. In 2020, in the context of quarantine measures caused by the COVID-19 pandemic, the issue of managing museum visitors flows has become especially acute. If earlier museums throughput was limited by the maximum duration of possible evacuation from a museum building, exhibition space and the number of employees working with the visitors, in 2020, due to the observance of sanitary and epidemiological rules, the throughput of museums was further reduced. This determines the relevance of analytical solutions for museums as in order to manage visitor flows and adapt services to the high demand, it is necessary to have an effective forecasting model that takes into account the determinism of demand by a number of factors. The purpose of this paper is to develop a forecasting model for the number of excursion groups in specification museum-day-hour. A modification of random forest with the inclusion of more than 450 independent variables in the model is proposed as a forecasting method. The modification of the model relies on changing the mechanism for combining forecasts of trees in the forest in such a way that the weight of the tree in the model is inversely proportional to the measurement error of this tree. The proposed model is tested on the basis of data on more than 20,000 excursion groups of the State Russian Museum for the period 2018-2020. The proposed model showed high accuracy (36.6% WAPE and 0.5% BIAS).
Keywords: forecasting machine learning random forest combining forecasts Python forecast museum Service service quality
Justification of Service Policy Parameters for Spare Parts Supply Using Agent-based Simulation
MAGAZINE №3 (92) June 2019
AUTHORS
GOBEDZHISHVILI K.A. - Lecturer, Department of Information Systems and Technologies in Logistics, National Research University Higher School of Economics (Moscow, Russia)
ZAKHODYAKIN G.V. - Senior Lecturer, Department of Information Systems and Technologies in Logistics, National Research University Higher School of Economics (Moscow, Russia)
CATEGORY Logistics service management Simulation modelling Inventory management
ABSTRACT
Russian mining industry experiences a rapid growth providing an attractive market for suppliers of mining equipment. However, it is a customer-dominated market. The customers set stringent requirements for the initial equipment supply, as well as for the after-sale service and spare parts supply. The manufacturers of mining equipment are thus facing the need to rigorously analyze their supply chain, to develop a reasonable customer service policy and to adjust the supply chain to meet the requirements of the service policy. To fulfill the after-sale maintenance requirements, the manufacturers must stock spare parts within the supply chain and to design inventory control policies. This paper presents an agent-based simulation approach for estimation of the supply chain key performance indicators and to explore the service – cost trade-off. The conceptual model and the description of its implementation in Anylogic 8.4 software are provided. A case-study of a global mining equipment manufacturer's branch operating in Russia is described. The model is used to estimate the inventory
control policy parameters required to meet the target customer service level, to compare make-to-order against make-to-stock supply strategies, as well as to explore the service level – cost trade-off.
Keywords:
