Data prediction analysis with data mining techniques. Behaviour of different techniques

      Аннотация: Nowadays it is of great importance for companies to make predictions, as well as to measure how they have behaved over time, in order to be able to plan the course of their business, reduce losses and increase profits. In order to generate an estimate of sales, different data mining techniques were analyzed. Among the techniques that were selected are time series, and within it, moving averages, exponential smoothing and trend adjusted exponential smoothing; linear regression and random trees were also selected. Prediction models were created with each one of the techniques, applying the corresponding equations and the information extracted from the database, in order to generate sales predictions with greater precision, to later compare the different results and measure the percentage of error.

Ключевые слова: Forecasting, Data Mining, Business model, Sales Forecasting