An organization must manage its resource consumption and material flows in order to satisfy the demand of its products as efficiently as possible. Managing of the aforementioned requires a balance between the organizations resources (such as the capability of distribution and production) and the market demand. According to Gardner (1990), an estimation of future demand is a necessity for maintaining the balance. An instrument that is used frequently to estimate future demand is demand forecasting. The demand forecasting practice has been thoroughly studied and a plethora of academic contributions exist on the topic. However, a best practice demand forecasting method does not exist for every kind of product. The purpose of this paper is to identify which time series forecasting method that will result in the lowest error rate on fast moving consumer goods. The methods are based on sales data of 18 articles from the company Coca-Cola Enterprises Sverige AB which predominantly sells soft drinks. The majority of the theoretical framework is time series models presented by the authors Stig-Arne Mattsson, Patrik Jonsson and Steven Nahmias. The paper identifies Exponential smoothing with individual input variables as the forecasting method with the lowest error rate. The method gave the lowest possible error rate on over 55 percent of the articles. In addition, the combined error rate of the articles using Exponential smoothing with individual input variables gave the lowest overall error.

nÃo hà / A Lubnor à uma refinaria de pequeno porte da Petrobras instalada dentro da cidade de Fortaleza-CE, que processa petrÃleos do tipo naftÃnico, pouco disponÃveis na natureza. A refinaria dispÃe hoje de trÃs opÃÃes desses Ãleos para processamento e produz basicamente asfaltos e lubrificantes naftÃnicos, sendo a Ãnica produtora nacional destes Ãltimos. O planejamento de processamento de matÃria-prima e produÃÃo dessa unidade industrial à realizado de forma centralizada pela sede da organizaÃÃo, que busca os melhores resultados para o todo, mesmo que isso penalize uma unidade especÃfica. Este trabalho temcomo objetivos planejar as operaÃÃes logÃsticas em uma refinaria de petrÃleo para maximizar seus resultados e mostrar que sincronizando a demanda por produtos acabados e a chegada de matÃria-prima, a refinaria pode aumentar a capacidade de processamento reduzindo os estoques em processo. Para esse fim, foi adotada a estratÃgia de pesquisa bibliogrÃfica e exploratÃria aplicada a um estudo de caso. Os referenciais teÃricos estÃo suportados na previsÃo de demanda, gestÃo de estoques e nos sistemas de apoio à decisÃo. Os resultados apontam que entre seis configuraÃÃes possÃveis de processamento pela refinaria, duas apresentam melhor rentabilidade, duas apresentam um resultado um pouco inferior e as duas outras sÃo inviÃveis. A demonstraÃÃo de que à possÃvel aumentar a produÃÃo com a reduÃÃo dos estoques em processo à realizada atravÃs de uma planilha do Microsoft Excel, que tem como variÃvel a carga da unidade. Aumentando-se a carga em 50% e 100%, os estoques em processo caem a nÃveis inferiores aos existentes hoje na refinaria. Ao final deste trabalho sÃo apontadas recomendaÃÃes para a soluÃÃo de problemas especÃficos que reduzem a rentabilidade da refinaria e o nÃvel de serviÃo desejado / Lubnor is a small tonnage Petrobrasâ refinery located in Fortaleza, CearÃ, Brazil. It refines naphtenic crude oils, which are not easy to find in nature. There are three kinds of Brazilian naphtenics oils currently available to be processed in Lubnor. The refinery produces basically asphalts and naphtenic lubricants, and it is the only Brazilian producer of these kinds of lubricants. The kinds of petroleum to process and the production planning of the refinery are made by the headquarters of the organization, which looks for the best results for the whole Company, although it means losses for one of the refineries. This work has the following objectives: to plan the logistic operations of a petroleum refinery in order to maximize its profits and to show that the refinery can improve its processing capacity reducing its in process inventory by synchronizing or balancing the output of final products and the input of crude oils. To reach these objectives, it was adopted the strategy of a literature research applicable to a case study. The theoretical references concern demand forecasting, inventory management and decision support systems. The results show that among the six possible configurations of oil refining, two are profitable, other two have a little gain and the last two are unfeasible. The demonstration that it is possible to increase the production reducing the in process inventory is made by using a Microsoft Excel spreadsheet with one variable: the diary flow of crude oil in the distillation unit. Increasing the flow in 50% and 100%, the in process inventory decreases to a lower level when compared with the current inventory at the refinery. At the end of this work, there are recommendations to solve specific problems which are reducing the refinery profitability and the service level

L'objectif principal de cette recherche est d'analyser les effets de l'agrégation sur la prévision de la demande. Cet effet est examiné par l'analyse mathématique et l’étude de simulation. L'analyse est complétée en examinant les résultats sur un ensemble de données réelles. Dans la première partie de cette étude, l'impact de l'agrégation temporelle sur la prévision de la demande a été évalué. En suite, Dans la deuxième partie de cette recherche, l'efficacité des approches BU(Bottom-Up) et TD (Top-Down) est analytiquement évaluée pour prévoir la demande au niveau agrégé et désagrégé. Nous supposons que la série désagrégée suit soit un processus moyenne mobile intégrée d’ordre un, ARIMA (0,1,1), soit un processus autoregressif moyenne mobile d’ordre un, ARIMA (1,0,1) avec leur cas spéciales. / Demand forecasting performance is subject to the uncertainty underlying the time series an organisation is dealing with. There are many approaches that may be used to reduce demand uncertainty and consequently improve the forecasting (and inventory control) performance. An intuitively appealing such approach that is known to be effective is demand aggregation. One approach is to aggregate demand in lower-frequency ‘time buckets’. Such an approach is often referred to, in the academic literature, as temporal aggregation. Another approach discussed in the literature is that associated with cross-sectional aggregation, which involves aggregating different time series to obtain higher level forecasts.This research discusses whether it is appropriate to use the original (not aggregated) data to generate a forecast or one should rather aggregate data first and then generate a forecast. This Ph.D. thesis reveals the conditions under which each approach leads to a superior performance as judged based on forecast accuracy. Throughout this work, it is assumed that the underlying structure of the demand time series follows an AutoRegressive Integrated Moving Average (ARIMA) process.In the first part of our1 research, the effect of temporal aggregation on demand forecasting is analysed. It is assumed that the non-aggregate demand follows an autoregressive moving average process of order one, ARMA(1,1). Additionally, the associated special cases of a first-order autoregressive process, AR(1) and a moving average process of order one, MA(1) are also considered, and a Single Exponential Smoothing (SES) procedure is used to forecast demand. These demand processes are often encountered in practice and SES is one of the standard estimators used in industry. Theoretical Mean Squared Error expressions are derived for the aggregate and the non-aggregate demand in order to contrast the relevant forecasting performances. The theoretical analysis is validated by an extensive numerical investigation and experimentation with an empirical dataset. The results indicate that performance improvements achieved through the aggregation approach are a function of the aggregation level, the smoothing constant value used for SES and the process parameters.In the second part of our research, the effect of cross-sectional aggregation on demand forecasting is evaluated. More specifically, the relative effectiveness of top-down (TD) and bottom-up (BU) approaches are compared for forecasting the aggregate and sub-aggregate demands. It is assumed that that the sub-aggregate demand follows either a ARMA(1,1) or a non-stationary Integrated Moving Average process of order one, IMA(1,1) and a SES procedure is used to extrapolate future requirements. Such demand processes are often encountered in practice and, as discussed above, SES is one of the standard estimators used in industry (in addition to being the optimal estimator for an IMA(1) process). Theoretical Mean Squared Errors are derived for the BU and TD approach in order to contrast the relevant forecasting performances. The theoretical analysis is supported by an extensive numerical investigation at both the aggregate and sub-aggregate levels in addition to empirically validating our findings on a real dataset from a European superstore. The results show that the superiority of each approach is a function of the series autocorrelation, the cross-correlation between series and the comparison level.Finally, for both parts of the research, valuable insights are offered to practitioners and an agenda for further research in this area is provided.

The thesis „The Inventory Management of Trading Company” deals with the issue of material flow and inventory management. In the introductory part of the thesis, the theoretical basis of supply logistics in a logistics chain, the issue of inventory, its storage and in particular its management have been defined. In the second part, inventory management in a logistics center of a company has been analyzed. In the last part, the solutions for improving inventory management of a company, mainly in terms of reduction of the amount, have been proposed.

This dissertation aimed to improve travel time estimation for the purpose of transportation planning by developing a travel time estimation method that incorporates the effects of signal timing plans, which were difficult to consider in planning models. For this purpose, an analytical model has been developed. The model parameters were calibrated based on data from CORSIM microscopic simulation, with signal timing plans optimized using the TRANSYT-7F software. Independent variables in the model are link length, free-flow speed, and traffic volumes from the competing turning movements. The developed model has three advantages compared to traditional link-based or node-based models. First, the model considers the influence of signal timing plans for a variety of traffic volume combinations without requiring signal timing information as input. Second, the model describes the non-uniform spatial distribution of delay along a link, this being able to estimate the impacts of queues at different upstream locations of an intersection and attribute delays to a subject link and upstream link. Third, the model shows promise of improving the accuracy of travel time prediction. The mean absolute percentage error (MAPE) of the model is 13% for a set of field data from Minnesota Department of Transportation (MDOT); this is close to the MAPE of uniform delay in the HCM 2000 method (11%). The HCM is the industrial accepted analytical model in the existing literature, but it requires signal timing information as input for calculating delays. The developed model also outperforms the HCM 2000 method for a set of Miami-Dade County data that represent congested traffic conditions, with a MAPE of 29%, compared to 31% of the HCM 2000 method. The advantages of the proposed model make it feasible for application to a large network without the burden of signal timing input, while improving the accuracy of travel time estimation. An assignment model with the developed travel time estimation method has been implemented in a South Florida planning model, which improved assignment results.

Route planning forms an important aspect of airline operations for them to sustain the effects of deregulation and fierce competition. The Indian economic liberalization in 1991 has seen diminishing monopoly of Air India and dynamic demand splits amongst the service providers. Our research focuses on developing an aggregate route traffic demand forecasting (RTDF) model specifically for international carriers operating from India. The model is an econometric model that combines concepts of the traditional Gravity model of Physics and the Micro-economic theoretic model that links demand to price. In other words, the RTDF model is a fusion of the behavioral and gravity models. While developing the model, Becker’s approach of utility maximization has been made use of, thereby combining time and other inputs required to produce travel. The model is developed for the existing international routes from India with 2005 aggregative data provided by International Civil Aviation Organization (ICAO), which spanned 15 countries in Europe, Asia, Canada, and North America. The model has been validated and tested for its predictive power on a few intentionally left out routes from the original sample. The model explains about 70% of the variance, which is well above the acceptable zone for cross-sectional data. The model is then estimated for 2007 data on a few randomly selected high demand routes; the prediction error ranging from a minimum of 3.5% to a maximum of 13%, a range well within the acceptable error limits. We derive a sector-cost-model (SCM) by applying the concept of break-even analysis on the RTDF model. The SCM provides cost estimates on a particular route at various levels of airfare. The SCM helps us gain further insights into the business nature prevailing in the airline sector. On the viability of operations, we propose the sector-operation-fare (SOF) to be charged on a respective route, given the load factor, if the airline wishes to continue operations. For arriving at the SOF, we follow a demand oriented framework that comprises of two demand curves: the airline curve and the traffic curve. The numerical analyses provide room for policy formulations that help airlines in refining, redefining, and revitalizing the decision-making process in their operations. Airlines can use this model to forecast demand for a newly contemplated route and obtain a fair idea of the price they can charge the customer. In other words, airlines can estimate the economic viability of operations on a respective route.

This diploma thesis deals with a demand forecasting in electronic shop focused on electronics Alza.cz. The aim of the thesis is to evaluate several forecasting methods for different groups of products and to determine which of them provides the most accurate forecasts. The theoretical part is focused on electronic business, logistics cost, demand forecast, demand forecasting methods and forecast accuracy measuring methods. In practical part, selected methods are applied on data of past demand to calculate the forecasts. Afterwards the forecast accuracy is measured. At the end the thesis provides evaluation of forecast accuracy of the methods.

This thesis deals with the prediction demand forecasting in a company, focusing especially on quantitative methods of prediction. The theoretical part presents the predictions of demand, its place and importance in a company. Secondly, it presents various methods of qualitative and quantitative demand forecasting and the methods for measuring prediction accuracy. The practical part applies several methods on a real data of the company. These are the methods of moving averages, exponential smoothing, Holt and Holt-Winters method and the simple linear regression. The accuracy of each method are compared with each other and most accurate method is then used to predict demand for the year 2015.

Cette thèse porte sur la prévision de la demande des expéditeurs et des offres de capacité des transporteurs pour la planification opérationnelle des systèmes `Many-to-One-to-Many' (M1M). Un tel système agit comme un décideur intermédiaire entre les expéditeurs et les transporteurs en coordonnant le transport des marchandises des expéditeurs aux destinataires en utilisant les capacités offertes par les transporteurs. Le décideur prend ses décisions dans un horizon de planification opérationnelle, en optimisant ces décisions en tenant compte de l'incertitude sur les périodes futures. Pour accompagner les décisions du décideur, il est essentiel de prédire les nouvelles demandes des expéditeurs et les nouvelles capacités des transporteurs. Cela conduit à des problèmes de prévision de séries chronologiques à plusieurs variables et à plusieurs étapes. L'objectif de ce travail est d'analyser l'impact des erreurs de prévision sur la qualité de la solution pour un problème de planification opérationnelle M1M donné. Cette thèse présente d'abord la structure du système M1M, la planification opérationnelle et les tâches de prévision associées. Nous décrivons la caractérisation des demandes des expéditeurs et des offres des transporteurs ainsi que comment la prévision peut soutenir les décisions en définissant les informations nécessaires pour le décideur sur l'horizon opérationnel. Nous couvrons ensuite l’optimisation de l’affectation charge-transporteur en introduisant un modèle d'optimisation déterministe et les prévisions utilisées en entrée. En l'absence de données réelles, nous générons un ensemble de données synthétiques qui est ensuite utilisé pour estimer les modèles de prévision. L'objectif est de définir quelques modèles de prévision qui présentent des erreurs afin que nous puissions évaluer leur impact sur la qualité de la solution pour le problème de planification opérationnelle. Dans ce contexte, nous comparons plusieurs modèles ARIMA pour prédire les futures demandes et offres. Nous constatons que les modèles avec des erreurs de prévision relativement faibles peuvent conduire à des améliorations significatives de la qualité de la solution. Enfin, nous exposons quelques pistes de recherches futures. / This thesis is about forecasting new shipper-demand requests and carrier-capacity offers for operational planning of Many-to-One-to-Many (M1M) systems. Such a system acts as an intermediary decision-maker between shippers and carriers, coordinating the transportation of goods from shippers to consignees (shipment recipients) using capacity offered from carriers. The decision-maker makes the decisions within an operational planning horizon, optimizing these decisions accounting for uncertainty over future time periods. To support the decisions, forecasting new shipper-demands and carrier capacities is essential. This leads to multi-variate multi-step time series forecasting problems. The objective of this work is to analyze the impact of forecast errors on the solution quality for a given M1M operational planning optimisation method. This thesis first presents the M1M system structure, operational planning, and related forecasting tasks. It explains the characterization of the shipper requests and carrier offers. We describe how forecasting can support the decisions by defining the needed information for the decision-maker over the operational horizon. We then cover the optimization of load-to-carrier assignments introducing a deterministic formulation and the forecasts used as input. In the absence of real data, we generate a synthetic data set that is then used for estimating forecasting models. The aim is to define a few forecasting models that exhibit some errors so that we can assess their impact on the solution quality for the operational planning problem. In this context, we compare several ARIMA models to predict future requests and offers. We find that the models with relatively low forecast errors can lead to significant improvements in solution quality. Finally, we outline a few directions for future research.

Energy demand forecasting has been more vital in recent years with countries setting goals to become climate neutral by 2050. Indeed, energy demand forecasting allows the understanding of drivers of the energy demand in all sectors of the economy. It also allows the planning of transformation of the future energy system. This study focuses on forecasting energy demand in Europe using a multi-country bottom-up modelling approach. The work explores ways of collecting large quantity of data to feed an energy model and method of completion for missing data series. It also aims at studying attributes that make a model user friendly and easy to use for the modelling of several countries. A model and a database are developed to answer these questions. A case application is conducted on the specific topic of the phase out of internal combustion engines in the EU to validate model dynamics and practical use. It is found that an energy demand forecasting model is easier and more time efficient to use with an included historical database. The case study shows that multi-country modelling can be relevant for policy assessment. Finally, improvements and future developments are proposed for the present work. / Prognoser för energiefterfrågan har blivit allt viktigare under de senaste åren i och med att länder har satt upp mål om att bli klimatneutrala senast 2050. Prognoser för energiefterfrågan gör det möjligt att förstå drivkrafterna bakom energiefterfrågan inom alla ekonomiska sektorer. Det gör det också möjligt att planera omvandlingen av det framtida energisystemet. Denna studie fokuserar på prognoser för energiefterfrågan i Europa med hjälp av en bottom-up-modelleringsmetod för flera länder. I arbetet undersöks olika sätt att samla in stora mängder data för att mata en energimodell och metoder för att komplettera saknade dataserier. Det syftar också till att studera attribut som gör en modell användar vänlig och lätt att använda för modellering av flera länder. En modell och en databas utvecklas för att besvara dessa frågor. För att validera modellens dynamik och praktiska användning genomförs en fallstudie om utfasningen av förbränningsmotorer i EU. Det visar sig att en modell för prognostisering av energiefterfrågan är enklare och mer tidseffektiv att använda med en inkluderad historisk databas. Fallstudien visar att modeller för flera länder kan vara relevanta för policybedömning. Slutligen föreslås förbättringar och framtida utveckling för det aktuella arbetet.