| Abstract [eng] |
This study explores sources of uncertainty when calculating the prediction of profit for an online advertising technology company in the short term, i.e. until the end of the current month. The first stage describes the company's business model, available products, and profit calculations, and identifies potential factors that affect profit changes. The following is an overview of existing studies to assess existing financial forecasting methods, as well as the use of data uncertainty. The descriptive analysis of the data is based on the actual data of the company concerned. Digital datasets are applied to these datasets to discover the most appropriate forecasting method and to assess the impact of data uncertainty on the result. The following digital learning methods were used for data sets: time series, linear regression. After applying mathematical methods for checking the uncertainty of data, evaluate their influence on the result and accuracy of the final forecast. |
