Abstract   Purpose - The purpose with this thesis is to investigate how to increase sales forecast accuracy.   Methodology – To fulfil the purpose a case study was conducted. To collect data from the case study the authors performed interviews and gathered documents. The empirical data was then analysed and compared with the theoretical framework.   Result – The result shows that inaccuracies in forecasts are not necessarily because of the forecasting technique but can be a result from an unorganized forecasting process and having an inefficient information flow. The result further shows that it is not only important to review the information flow within the company but in the supply chain as whole to improve a forecast’s accuracy. The result also shows that time series can generate more accurate sales forecasts compared to only using qualitative techniques. It is, however, necessary to use a qualitative technique when creating time series. Time series only take time and sales history into account when forecasting, expertise regarding consumer behaviour, promotion activity, and so on, is therefore needed. It is also crucial to use qualitative techniques when selecting time series technique to achieve higher sales forecast accuracy. Personal expertise and experience are needed to identify if there is enough sales history, how much the sales are fluctuating, and if there will be any seasonality in the forecast. If companies gain knowledge about the benefits from each technique the combination can improve the forecasting process and increase the accuracy of the sales forecast.   Conclusions – This thesis, with support from a case study, shows how time series and qualitative techniques can be combined to achieve higher accuracy. Companies that want to achieve higher accuracy need to know how the different techniques work and what is needed to take into account when creating a sales forecast. It is also important to have knowledge about the benefits of a well-designed forecasting process, and to do that, improving the information flow both within the company and the supply chain is a necessity.      Research limitations – Because there are several different techniques to apply when creating a sales forecast, the authors could have involved more techniques in the investigation. The thesis work could also have used multiple case study objects to increase the external validity of the thesis.

En effektiv materialhantering har en viktig del i hur konkurrenskraftig en organisation är och att utveckla sina arbetssätt inom detta område är en kontinuerlig utmaning. I en organisation utgör lagerhållning av varor en av de mest väsentliga logistikkostnaderna. Ett sätt att reducera dessa kostnader är genom prognostisering.  Det finns därmed ett incitament för organisationer att allokera resurser på detta område för att bedriva sin verksamhet mer kostnadseffektivt och vara fortsatt konkurrenskraftiga. Statliga myndigheter är inget undantag gällande kostnadsreduceringar, speciellt eftersom de hushåller med resurser som tillhandahålls av regeringen. Studiens syfte har varit att undersöka vilka kvantitativa prognosmetoder som kan användas och hur de ska väljas för att uppnå en förbättrad lagerstyrning. Studien genomfördes som en fallstudie på Trafikverket. Genom att studera en organisation och använda verklig data, bidrar studien med en ökad förståelse för hur prognostiseringsprocessen är utformad samt hur prognostisering kan tillämpas utifrån efterfrågan på ett brett sortiment av artiklar. Totalt har prognoser upprättats för 245 artiklar som finns i det nuvarande sortimentet. Fem olika prognosmetoder användes för att upprätta prognoser som sedan utvärderades med två prognosmått. För att sedan välja den bästa prognosmetoden för varje artikel på ett objektivt sätt användes Data Envelopment Analysis (DEA). Studien visar vilka steg som ingår i prognostiseringsprocessen samt vilka aktiviteter som bör genomföras i varje steg. Studiens användning av DEA-analys för att bestämma den mest lämpliga prognosmetoden för ett sortiment av artiklar visar nya användningsområden för metoden. Studiens resultat och analys visade att de prognosmetoder som organisationen använder inte genererar det bästa resultatet. Prognosfelet minskade för sortimentet när den prognosmetod som DEA-analysen föreslog användes. Studiens slutsatser visade att organisationen inte analyserat varför de prognosmetoder som används är lämpliga samtidigt som de inte följer upp och utvärderar resultatet. Vidare gavs rekommendationer till fallstudieföretaget gällande vilka prognosmetoder och utvärderingsmått de kan använda sig av. / For organizations, an efficient management of material is a source for cost reductions and is an important aspect to continuously develop in order to stay competitive. Keeping stock is one of the significant costs related to logistics and one method that can contribute to a reduction in future stock levels is demand forecasting. There is therefore an incentive for organizations to allocate resources to this area of subject, to operate more efficiently and maintain or increase competitiveness. The public sector is not an exception in regard to working with cost reductions and a strict budget, especially since they use funds allocated by the government. The purpose of this thesis is to investigate which quantitative forecasting methods that can be used and how the methods should be chosen. The goal is to provide more accurate forecasts that contributes to a reduction of total material handled. The thesis was performed as a case study at Trafikverket (the Swedish transport administration). Through study and analysis of a real organization who provided real-world data to work with, the thesis contributes with an understanding of how the forecasting process is outlined and how it can be practiced when managing a large set of products. Five different forecasting methods were used in this thesis together with two measurements of accuracy. In total, forecasts were developed for 245 different products by using real data on past demand. Data Envelopment Analysis (DEA) was used to choose the most and least appropriate forecasting methods for each product. The thesis demonstrates which steps and activities are necessary in the forecasting process and the usage of DEA to decide which method is the most and least suitable for a large set of products shows a new usage for the method. The result and analysis of the thesis showed that the forecasting methods used by the case company are not the most suitable ones. The forecast error was reduced for the total set of products when using the methods that the DEA suggested. The conclusions of the thesis revealed that the case company did not perform any analysis on why the current forecasting methods were used and adding to this, no evaluation of the forecast error was performed. Further, recommendations were provided to the case company regarding which forecasting methods and accuracy measures should be employed.

Made available in DSpace on 2016-06-02T19:51:51Z (GMT). No. of bitstreams: 1 3779.pdf: 1426121 bytes, checksum: a6f8e39bedf841fb3a719a8979689441 (MD5) Previous issue date: 2011-07-06 / Nowadays, even small-sized enterprises are investing in integrated management systems, called ERP (Enterprise Resource Planning), as a way to solve planning problems and to better control their cash flow. However, these enterprises end up neglecting one of the main inputs to improve the PPC (Production Planning and Control): the demand forecast. Thus, planning and cash flow problems persist, and no matter how flexible the enterprise is, it cannot follow the demand due to limited resources. Another factor is related to the responsibility of elaborating the sales forecast, which a single area or department is in charge of and reflects all the development of the enterprise, in case values are not reliable. This work fits context, once its main goal is to present a process which combines various methods or forecasting techniques, integrating areas or departments as a whole, and sharing the responsibilities to obtain a consensual preview accepted by all. This process aims to align the revenue goals defined by the board and make possible actions with advance, in case it is seen that the objectives cannot be achieved in revenue terms, promoting coordinated actions between the commercial and productive areas, searching for a common outcome in financial terms. The proposed method also aims to improve the way of communication among areas, integrating the information and trying to suggest an evaluation and analysis process of the performed forecasts, apart from proposing an incentive to the commercial area to search for accuracy in the forecasts. The final outcome of demand forecast process will be a master production scheduling. A theoretical-empirical analysis is presented, and the research, based on literature, identifies, from the production system evolution, the production planning and control the demand forecast process, its forecasting techniques and the evaluation of errors. Next, demand forecasting processes is presented, as a way to improve the demand forecast identified in the case study and demonstrate the expected outcomes after the implementation of this demand forecast model. / Atualmente, mesmo as empresas de pequeno porte estão investindo em sistemas de gestão integrados, chamados de ERP (Enterprise Resources Planning), como uma forma de resolver problemas de planejamento e controlar melhor seu fluxo de caixa. Porém, essas empresas acabam negligenciando um dos principais insumos para melhorar o PCP (Planejamento e Controle da Produção): a previsão de demanda. Assim, persistem os problemas de planejamento e de fluxo de caixa, e por mais flexível que seja a empresa, ela não consegue acompanhar a demanda em função de recursos limitados. Outro fator está relacionado à responsabilidade de elaborar a previsão de vendas, que fica a cargo de uma única área ou departamento e reflete todo o desempenho da empresa, caso os valores não sejam confiáveis. Este trabalho se insere neste contexto, uma vez que tem como objetivo principal apresentar um processo que combine vários métodos ou técnicas de previsão, integrando as áreas ou departamentos como um todo, e dividindo as responsabilidades pela obtenção de uma previsão de consenso aceita por todos. Este processo busca alinhar as metas de faturamento definidas pela diretoria e tornar possíveis ações com antecedência, caso se perceba que os objetos podem não ser alcançados em termos de faturamento, promovendo ações coordenadas entre a área comercial e produtiva, em busca de um resultado comum em termos financeiros. O método proposto também almeja melhorar a forma de comunicação entre as áreas, integrando as informações e procura sugerir um processo de avaliação e análise das previsões realizadas, além de propor um incentivo à área comercial para que busque uma acuracidade das previsões. O resultado final do processo de previsão de demanda será um programa mestre de produção. Uma análise teórico empírica é apresentada, e a pesquisa, com base na literatura, identifica, desde a evolução dos sistemas de produção, o planejamento e controle da produção, o processo de previsão de demanda, suas técnicas de previsão e a avaliação dos erros. Em seguida, apresenta-se uma proposta de método de previsão de demanda, como forma de melhorar a previsão de demanda identificada no estudo de caso e demonstra os resultados esperados após a implantação deste modelo de previsão de demanda.

Det blir alltmer vanligt med kundanpassade produkter. Dagens sätt att tillverka på kan ses som ett resultat av att företag skiftat från massproduktion till att sätta kunden i centrum. Vi har gått in i den fjärde paradigmen av den industriella revolutionen, ”Mass-personifierad produktion” (MPP) eller ”Industri 4.0” som det även kallas. Kundanpassade produkter tar allt längre tid att göra, och för att få ut produkten snabbt krävs det att produkterna finns i lager vilket ger ett behov till prognostisering, och pålitliga processer.  I detta arbete har en fallstudie genomförts på ett industriföretag, Industri AB med syfte att undersöka och skapa förståelse för prognosprocessen på ett kundorderstyrt industriföretag. I detta arbete kartläggs även Industri AB:s prognosprocess.  Arbetet grundar sig en litteraturstudie av vetenskapliga artiklar och böcker, samt intervjuer på Industri AB. I arbetet har abduktion använts som vetenskapligt angreppsätt vilket betyder att det skett en växling mellan litteratur och empiriskt insamlat material. Genom att använda abduktion kunde de studerade faktorerna väljas utifrån de faktorer som, enligt litteraturen och Industri AB, har störst påverkan på prognosprocessen.  Efter att detta arbete genomförts går det att konstatera att det finns flera faktorer som påverkar prognosprocessen på kundorderstyrda industriföretag. Detta arbete tar upp sju påverkande faktorer och dessa är produktens utformning, osäkerhet, kommunikation och samarbete, bonussystem för säljare, den mänskliga faktorn, tillgängliga data och dess kvalitet, samt systematisk uppföljning. Faktorerna påverkar prognosprocessen på olika sätt, och denna studie ger även konkreta generella lösningsförslag samt förslag till hur Industri AB kan utveckla sin prognosprocess. / Customized products are becoming increasingly more common. Today's way of manufacturing can be seen as a result of companies shifting from mass production to putting the customer in the center. We have entered the fourth paradigm of the Industrial Revolution, "Mass-Personalized Production" or "Industry 4.0" as it is also called. Customized products take more and more time to produce, and in order to quickly get the product out, it is required that the products are in stock, which provides a need for forecasting and reliable processes. In this work, a case study has been carried out at an industrial company, Industri AB with the aim of investigating and create an understanding of the forecasting process at a customer order-driven industrial company. In this work, the forecasting process at Industri AB is also mapped. The work is based on a literature study of scientific articles and books, as well as interviews at Industri AB. In this work, abduction has been used as a scientific approach, which means that there has been an alternation between literature and empirically collected material. By using abduction, the studied factors could be selected based on the factors that, according to the literature and Industri AB, have the greatest impact on the forecasting process. After this work has been carried out, it can be concluded that there are several factors that affect the forecasting process at customer-order-driven industrial companies. This work addresses seven influencing factors and these are product design, uncertainty, communication and cooperation, bonus systems for salespeople, the human factor, the available data and its quality and systematic follow-up. The factors affect the forecasting process in different ways, and this study also provides concrete general solutions and suggestions for how Industri AB can improve their forecasting process.

<p>In a world that is moving faster and faster, a company’s ability to align to market changes is becoming a major competitive factor. Forecasting enables companies to predict what lies ahead, e.g. trend shifts or market turns, and makes it possible to plan for it. But looking into the future is never an easy task.</p><p>“Prediction is very difficult, especially if it’s about the future.” (Niels Bohr, 1885-1962)</p><p>However, progress in the field of forecasting has shown that it is possible for companies to improve on forecasting practices. This master thesis looks at the sales forecasting practices in MNCs primarily operating in emerging and developing countries. We examine the whole process of sales forecasting, also known as forecasting management, in order to develop a comprehensive model for forecasting in this type of companies. The research is based on a single case study, which is then later generalized into broader conclusions.</p><p>The conclusion of this master thesis is that forecasting is a four-step exercise. The four stages we have identified are: Knowledge creation, knowledge transformation, knowledge use and feedback. In the course of these four stages a company’s sales forecast is developed, changed and used. By understanding how each stage works and what to focus on, companies will be able to improve their forecasting practices.</p>

In a world that is moving faster and faster, a company’s ability to align to market changes is becoming a major competitive factor. Forecasting enables companies to predict what lies ahead, e.g. trend shifts or market turns, and makes it possible to plan for it. But looking into the future is never an easy task. “Prediction is very difficult, especially if it’s about the future.” (Niels Bohr, 1885-1962) However, progress in the field of forecasting has shown that it is possible for companies to improve on forecasting practices. This master thesis looks at the sales forecasting practices in MNCs primarily operating in emerging and developing countries. We examine the whole process of sales forecasting, also known as forecasting management, in order to develop a comprehensive model for forecasting in this type of companies. The research is based on a single case study, which is then later generalized into broader conclusions. The conclusion of this master thesis is that forecasting is a four-step exercise. The four stages we have identified are: Knowledge creation, knowledge transformation, knowledge use and feedback. In the course of these four stages a company’s sales forecast is developed, changed and used. By understanding how each stage works and what to focus on, companies will be able to improve their forecasting practices.