This PhD thesis focuses on using time series models for counts in modelling and forecasting a special type of count series called intermittent series. An intermittent series is a series of non-negative integer values with some zero values. Such series occur in many areas including inventory control of spare parts. Various methods have been developed for intermittent demand forecasting with Croston’s method being the most widely used. Some studies focus on finding a model underlying Croston’s method. With none of these studies being successful in demonstrating an underlying model for which Croston’s method is optimal, the focus should now shift towards stationary models for intermittent demand forecasting. This thesis explores the application of a class of models for count data called the Integer Autoregressive Moving Average (INARMA) models. INARMA models have had applications in different areas such as medical science and economics, but this is the first attempt to use such a model-based method to forecast intermittent demand. In this PhD research, we first fill some gaps in the INARMA literature by finding the unconditional variance and the autocorrelation function of the general INARMA(p,q) model. The conditional expected value of the aggregated process over lead time is also obtained to be used as a lead time forecast. The accuracy of h-step-ahead and lead time INARMA forecasts are then compared to those obtained by benchmark methods of Croston, Syntetos-Boylan Approximation (SBA) and Shale-Boylan-Johnston (SBJ). The results of the simulation suggest that in the presence of a high autocorrelation in data, INARMA yields much more accurate one-step ahead forecasts than benchmark methods. The degree of improvement increases for longer data histories. It has been shown that instead of identification of the autoregressive and moving average order of the INARMA model, the most general model among the possible models can be used for forecasting. This is especially useful for short history and high autocorrelation in data. The findings of the thesis have been tested on two real data sets: (i) Royal Air Force (RAF) demand history of 16,000 SKUs and (ii) 3,000 series of intermittent demand from the automotive industry. The results show that for sparse data with long history, there is a substantial improvement in using INARMA over the benchmarks in terms of Mean Square Error (MSE) and Mean Absolute Scaled Error (MASE) for the one-step ahead forecasts. However, for series with short history the improvement is narrower. The improvement is greater for h-step ahead forecasts. The results also confirm the superiority of INARMA over the benchmark methods for lead time forecasts.

The aim of this thesis is to briefly introduce the reader to the problem of development of the electricity consumption, to show the possibilities of its prediction, and provide an example of electricity consumption analysis, which may serve as a basis for long-term forecast. The first part of this work is devoted to brief overview of the development of consumption of electrical energy in the Czech Republic and factors associated with that development. The main events of Czech electrification history are outlined, as well as factors influencing the magnitude of the demand for electricity in the recent times. There are described the possibilities of the influence of foreign exchange and price of the electricity, net losses, GDP, the consumption of gas, the number of inhabitants, or the structure of the economy. This work further describes the development of the consumption of electric energy abroad and comparison of the electricity consumption in the Czech Republic to its neighboring countries, in which there are apparently influence by variety of factors that affect the consumption development trend. For more complex overview, the electricity consumption of most of European states is being noted, and near the end of the chapter the development in poorest countries and in quickly growing economies is shown. The fourth chapter mentions methods for short and middle-term prediction of consumption of electricity. There also is more consistent description of possibilities useful for long-term prediction, for which the use of the results of statistics analysis is possible. The description of observed data that are used to find the dependences of different factors is made in the following part. Further the approach of the statistics analysis used in this thesis is shown, and the key terms are explained. The dates concerning the consumption of Czech Republic are analyzed, followed by the states with similar trend of the consumption and finally other European states. Sixth chapter examines the possible uses of the outcomes of statistical analyses for long-term prediction of electricity consumption. The conclusion sums up the knowledge acquired during the research concerning problem of electricity consumption and my own analysis of data.

O objetivo desta pesquisa é validar a hipótese de que o minerador de dados pode ser utilizado como uma ferramenta para previsão dos padrões de viagens, inclusive sob mudança comportamental dos indivíduos. Para o desenvolvimento deste trabalho foi adotada uma postura científica indutiva, utilizando como dados as informações contidas nas duas pesquisas origem-destino realizadas em 1987 e 1997 pelo METRÔ-SP na região metropolitana de São Paulo (RMSP). Os dados da primeira pesquisa e as mudanças comportamentais dos indivíduos observadas no período de 1987 a 1997 forneceram as condições para elaboração do cenário futuro a ser usado para projeção da demanda por transporte para 1997. Aplicando a Árvore de Decisão e Classificação, uma das técnicas de mineração de dados disponível no software S-PLUS 6.1, foram obtidas as distribuições das probabilidades das distribuições dos padrões de viagens encadeadas relacionadas a cada grupo homogêneo de viajantes urbanos. Estas probabilidades foram aplicadas aos indivíduos da amostra de 1997, estimando o número de viajantes urbanos por padrão de viagem encadeada em cada uma das 361 zonas de tráfego da RMSP. Os valores estimados pelo modelo foram comparados com os dados observados em 1997 pelo teste estatístico não-paramétrico de Kolmogorov-Smirnov (K-S). Ao final, concluiu-se que a hipótese proposta foi confirmada em 92,2% das zonas de tráfego analisadas / The main aim of this work is to submit to a validation test the hypothesis that data mining technique can be used as a tool for forecasting the trip-chaining patterns including individual behavioral changes. For the project development, an inductive scientific method point of view was adopted, using as a data resource the information contained in two origin-destination surveys carried out by METRÔ-SP in the São Paulo metropolitan area (SPMA) in 1987 and 1997. The first survey data and the individual behavioral changes observed in the period from 1987 to 1997 provided the information to build a future scenario to predict the 1997’s travel demand. Applying the Classification and Regression Tree which is a data mining technique available in S-PLUS 6.1 software package, it were obtained the probabilities distribution of the trip-chaining patterns and set the contextual socioeconomics characteristics of the urban travelers. These probabilities were applied to the 1997 individuals belonging to the sample collected in 1997 to estimate the number of urban travelers by trip-chaining patterns for each of the 361 traffic zones of SMPA. The estimated results from the model were compared with the real values of 1997 data set using the Kolmogorov-Smirnov (K-S) non-parametric statistic test. The main conclusion is that the hypothesis was confirmed in 92.2% of the SPMA traffic zones

[pt] Segundo o INEP/MEC, nos últimos 20 anos, o número de matrículas da educação superior de graduação no Brasil cresceu mais de duas vezes, com uma taxa de crescimento anual verificada a partir de 2001 em torno de 5,7 por cento ao ano. Ainda segundo esta instituição, em 2008 houve o ingresso de 1.505.819 novos estudantes nos cursos presenciais, ao mesmo tempo em que 1.479.318 vagas não foram ocupadas, sendo que 54,6 por cento do total de vagas ofertadas pelo setor privado. Tendo em conta que São Paulo é o maior estado do Brasil, é muito importante que o Ministério da Educação tome conhecimento de como se dará a dinâmica da oferta de educação superior nos próximos 20 anos para que suas ações (políticas públicas, sobretudo) possam ser realizadas com êxito. O objetivo deste trabalho é aplicar modelagem estatística para estimar a oferta do ensino superior do Estado de São Paulo no período de 2015 a 2035, considerando dados da INEP de educação superior. A motivação para este trabalho é melhorar o planejamento da oferta de curso superior e fazer a replicação do modelo preditivo para outros estados do Brasil. A metodologia usada é modelagem estatística (modelos de regressão linear) e séries temporais (Holt). Como resultado, têm-se as áreas e/os cursos onde o governo federal deve investir no futuro aprimorando seu planejamento. / [en] According to INEP/MEC, in the last 20 years, the number of undergraduate higher education enrollments in Brazil has grown more than twice, with an annual growth rate of 5,7 percent per year since 2001. According to this institution, in 2008 there were 1.505.819 new students enrolled in presential courses, while 1.479.318 vacancies were not filled, with 54.6 percent of the total number of vacancies offered by the private sector. Given that São Paulo is the largest state in Brazil, it is very important that the Ministry of Education becomes aware of the dynamics of the offer of higher education in the next 20 years so that its actions (mainly public policies) can be successfully executed. The objective of this study is to apply statistical modeling to estimate the offer of higher education in the State of São Paulo in the period from 2015 to 2035, considering data from INEP about higher education. The motivation for this work is to improve the planning of the offer of higher education and to replicate the predictive model for other Brazilian states. The methodology used concerns statistical modeling (linear regression models) and time series (Holt). As a result, it is obtained the areas and/or courses where the federal government should invest in the future, improving its planning. / [es] Según el INEP/MEC, en los últimos 20 años, el número de matrículas de educación superior en Brasil creció más de dos veces, con una tasa de crecimiento anual verificada a partir de 2001 en torno al 5,7 por ciento por año. Según esta institución, en 2008 hubo un ingreso de 1.505.819 nuevos estudiantes en los cursos presenciales, al mismo tiempo que 1.479.318 vacantes no fueron ocupadas, siendo el 54,6 por ciento del total de vacantes ofrecidas por el sector privado. Dado que São Paulo es el mayor estado de Brasil, es muy importante que el Ministerio de Educación tome conocimiento de cómo se dará la dinámica de la oferta de educación superior en los próximos 20 años para que sus acciones (políticas públicas, sobre todo) puedan realizarse con éxito. El objetivo de este trabajo es aplicar modelos estadísticos para estimar la oferta de educación superior del Estado de São Paulo en el período de 2015 a 2035, considerando datos de INEP de educación superior. La motivación para este trabajo es mejorar la planificación de la oferta de curso superior y hacer replicación del modelo predictivo para otros estados de Brasil. La metodología utilizada es modelos estadístico (modelos de regresión lineal) y series tiempo (Holt). Como resultado, se tienen las áreas y/o cursos donde el gobierno federal debe invertir en el futuro mejorando su planificación.

O objetivo desta pesquisa é validar a hipótese de que o minerador de dados pode ser utilizado como uma ferramenta para previsão dos padrões de viagens, inclusive sob mudança comportamental dos indivíduos. Para o desenvolvimento deste trabalho foi adotada uma postura científica indutiva, utilizando como dados as informações contidas nas duas pesquisas origem-destino realizadas em 1987 e 1997 pelo METRÔ-SP na região metropolitana de São Paulo (RMSP). Os dados da primeira pesquisa e as mudanças comportamentais dos indivíduos observadas no período de 1987 a 1997 forneceram as condições para elaboração do cenário futuro a ser usado para projeção da demanda por transporte para 1997. Aplicando a Árvore de Decisão e Classificação, uma das técnicas de mineração de dados disponível no software S-PLUS 6.1, foram obtidas as distribuições das probabilidades das distribuições dos padrões de viagens encadeadas relacionadas a cada grupo homogêneo de viajantes urbanos. Estas probabilidades foram aplicadas aos indivíduos da amostra de 1997, estimando o número de viajantes urbanos por padrão de viagem encadeada em cada uma das 361 zonas de tráfego da RMSP. Os valores estimados pelo modelo foram comparados com os dados observados em 1997 pelo teste estatístico não-paramétrico de Kolmogorov-Smirnov (K-S). Ao final, concluiu-se que a hipótese proposta foi confirmada em 92,2% das zonas de tráfego analisadas / The main aim of this work is to submit to a validation test the hypothesis that data mining technique can be used as a tool for forecasting the trip-chaining patterns including individual behavioral changes. For the project development, an inductive scientific method point of view was adopted, using as a data resource the information contained in two origin-destination surveys carried out by METRÔ-SP in the São Paulo metropolitan area (SPMA) in 1987 and 1997. The first survey data and the individual behavioral changes observed in the period from 1987 to 1997 provided the information to build a future scenario to predict the 1997’s travel demand. Applying the Classification and Regression Tree which is a data mining technique available in S-PLUS 6.1 software package, it were obtained the probabilities distribution of the trip-chaining patterns and set the contextual socioeconomics characteristics of the urban travelers. These probabilities were applied to the 1997 individuals belonging to the sample collected in 1997 to estimate the number of urban travelers by trip-chaining patterns for each of the 361 traffic zones of SMPA. The estimated results from the model were compared with the real values of 1997 data set using the Kolmogorov-Smirnov (K-S) non-parametric statistic test. The main conclusion is that the hypothesis was confirmed in 92.2% of the SPMA traffic zones

Due to the increasingly uncertain environments that global supply chains operate within, both due to component shortages and other types of challenges, the possibility of managing demand variability and balancing it with supply capabilities is getting more challenging. The primary way to deal with these fluctuations in demand is by building flexibility in the supply chain to meet the variations that occur and keep the customers satisfied. However, when flexibility is not enough, and the supply chain becomes increasingly strained due to geopolitical factors and customers demanding higher customizations, more efforts are required to manage the variability. This study investigates the possibility that instead of relying solely on flexibility, try to deal with the variations that arise in demand. This relates both to internal processes that increase variation but also to the variations that are caused by actual changes in demand. The study partly examines what drives internal variation and how one should work to minimize it. Moreover, concerning the external variation, demand shaping theory is applied. This is to understand how external variation can be handled by trying to steer the demand. As the theory in previous studies has primarily been applied in B2C contexts, the applicability of the theory in a B2B context is also examined. Furthermore, the study also investigates how demand and supply should be integrated to utilize the concepts in the best way possible when managing demand variability. The study has been conducted through a case study at Ericsson, where people who work within sales and supply have participated and contributed with their knowledge. The results show the importance of integration between different functions to succeed in managing demand variations and having a more significant impact on what customers buy. This means both clear communication, internally and externally, and the importance of having a unified vision and incentives that drive the company towards the same goal. In addition, the results also show that although the academic literature is mainly aimed at B2C companies, it is possible to apply the concept to B2B companies as well. / Till följd av den alltmer osäkra omvärld som globala leveranskedjor arbetar inom, med både komponentbrist och andra typer av utmaningar, blir det allt svårare att hantera den varierande efterfrågan och balansera den mot den kapacitet som företag besitter. Det primära sättet att hantera dessa fluktuationer i efterfrågan är genom att bygga in flexibilitet för att kunna bemöta de variationer som uppstår och för att behålla kunder nöjda. När flexibiliteten inte räcker till och leveranskedjan blir alltmer ansträngd, på grund av geopolitiska faktorer och kunder som kräver alltmer kundanpassade produkter, behöver man arbeta än mer med att försöka hantera variationen som uppstår. Syftet med denna studie är därför att undersöka möjligheten att, i stället för att enbart förlita sig på flexibilitet, försöka hantera de variationer som uppstår i efterfrågan. Detta relaterar både till interna processer som driver variationen men också de variationer som orsakas av faktiska förändringar i efterfrågan. Studien undersöker vad det är som driver intern variation och hur man bör arbeta för att minimera denna. I relation till den externa variationen, används bland annat demand shaping teori för att förstå hur denna typ av variation kan hanteras genom att försöka ha mer inflytande över vad kunderna väljer att köpa. Då teorin i tidigare studier enbart applicerats i B2C sammanhang, undersöks även om teorin är applicerbar i en B2B kontext. Studien undersöker också hur funktioner inom försäljning och supply bör integreras för att möjliggöra detta. Studien har genomförts som en fallstudie på Ericsson där personer som arbetar inom försäljning och supply deltagit och bidragit med sin kunskap. Resultaten visar på vikten av integration mellan olika funktioner för att lyckas hantera demand variationer och på att ha större inverkan på det kunderna köper. Detta innebär tydlig kommunikation både internt och externt, samt värdet av att ha gemensamma mål och incitament som driver företaget mot samma vision. Resultaten visar dessutom på att det finns förutsättningar för att applicera det undersökta konceptet på B2B företag trots att den akademiska litteraturen främst riktat in sig mot B2C företag.