Demand forecasting can be classified as a business process performed as a part of supply chain management. Although a complex term, it can be defined as a process that looks at available data with the aim of forming a forecast for future demand. Demand forecasting can be divided into two basic approaches, namely quantitative and qualitative demand forecasting methods. Qualitative methods gather the views and opinions of people who possess certain knowledge about the observed subject. They are conducted mainly through questionnaires and interviews, on the basis of which an attempt is made to form a common opinion of the examined mass. Quantitative methods apply mathematical methods in forming forecasts. They are applied when there is a sufficient level of historical data on the basis of which the mathematical models can be calculated. The best known method of quantitative demand prediction is time series analysis. The method implies the existence of historical data that unfolded in a certain order. There are three basic methods of time series analysis, namely simple exponential smoothing, Holt model or trend-corrected exponential smoothing, and Winters model or Trend and seasonality corrected exponential smoothing. Time series analysis models include smoothing constants in their calculations, which represent the speed of adjustment of the model to the latest knowledge about certain changes in demand. Since the demand consists of three observable factors, level, trend and seasonality, the inclusion of these variables in the forecast calculations yields more relevant results. When calculating demand forecasts for Apple Inc. whose demand has a pronounced seasonality and a slight growth trend, all three before mentioned methods of time series analysis were applied, as well as the static method, which obtains its calculations through deseasonalization of demand. The methods were calculated with the data obtained from the above mentioned company, as well as the appropriate error measurement methods in order to better describe the application of such approaches while forecasting future demand.