Inventory systems that use continuous review policy are under risk during lead time, when stock-out can occur. Therefore, system must have enough on-hand units to prevent such situations. Generally, in inventory control literature it can be found that lead time demand follows normal distribution and all other conclusions are derived from this assumption. However, in real life this does not have to be true, so it is of crucial importance to get better estimates of stochastic demand parameters over lead time. The objective of this research is to estimate the optimal (s, Q) continuous review inventory policy parameters that reduce risk of stock-out during lead time and to enhance robustness of such estimated parameters. This is done using approach we propose for demand modeling. Performances and adequacy of the proposed approach for lead time demand modeling, with various demand patterns, and its application in (s, Q) continuous inventory models are obtained by simulation and show very good results.

In this paper analytical expression for determining the optimal parameter value of the Same Slope Seasonality model was developed. Then performance of the Same Slope Seasonality model was compared to the performance of Holt-Winters exponential model, performing tests on M2-Competition time series. To determine the parameters of Holt-Winters exponential model, nonlinear mathematical programming was used. Performed tests proved that Same Slope Seasonality model is more successful than Holt-Winters exponential model. Tests revealed that Same Slope Seasonality model gives unreliable forecasts when time series has specific charac teristics, giving us valuable information for model improvement.

It is common and also predominant in the inventory control literature that demand follows normal distribution, and according to central limit theorem, demand per period will also follow normal distribution. However, in many real life situations, demand does not necessary follow normal distribution, and therefore, use of expressions used to calculate demand parameters per period are not suitable. This research suggests that available demand data are grouped into periods of desired length by overlapping. Demand data obtained by this approach provide valuable information for risk study. Suggested approach is evaluated using periodic review inventory model where all unsatisfied demand is backordered, and the same inventory control model is used to control inventories of slow and fast moving items. © 2015 The Authors. Published by Elsevier Ltd. Peer-review under responsibility of DAAAM International Vienna.

The aim of this paper is to analyze highway empirical traffic flow patterns including regression analysis at the highway tollgate station Josanica at the north exit of the capital of Bosnia and Herzegovina Sarajevo. The traffic flow analysis in this paper includes determination of arrival and service time pattern distributions and development of traffic flow time series regression forecasting models of the traffic flow. Data for this research are retrieved from the highway software system. Research shows that it is possible to build reliable regression forecasting models to predict number of vehicles per month, per week and per day in certain week as well as per defined time periods during a day. Time needed to pay at the toll station (service time) is measured by observation. This study presents arrival pattern distribution and service time distribution. Results obtained by this research will be used for the simulation of waiting line models and improvement of the existing system as well as for the highway service facilities demand forecasting.

The aim of this paper is to analyze highway empirical traffic flow patterns including regression analysis at the highway tollgate station Josanica at the north exit of the capital of Bosnia and Herzegovina Sarajevo. The traffic flow analysis in this paper includes determination of arrival and service time pattern distributions and development of traffic flow time series regression forecasting models of the traffic flow. Data for this research are retrieved from the highway software system. Research shows that it is possible to build reliable regression forecasting models to predict number of vehicles per month, per week and per day in certain week as well as per defined time periods during a day. Time needed to pay at the toll station (service time) is measured by observation. This study presents arrival pattern distribution and service time distribution. Results obtained by this research will be used for the simulation of waiting line models and improvement of the existing system as well as for the highway service facilities demand forecasting.