Forecasting Sales Through Time Series Clustering

We study the effect of decomposing time series into multiple components like trend, seasonal and irregular and performing the clustering on those components and generating the forecast values of each componentseparately. In this project we are working on sales data. Multiple forecast experts are used to forecast each component series. Statistical method ARIMA, Holt winter and exponential smoothing are used to forecastthese components. We performed clustering for forecasting and discovered a set of best, good and bad forecasters. Selection of best, good and bad forecasters is performed on the basis of count and rank of expert id’s generated. Since we have thousands of experts, we experiment with combining method to get better forecast. Finally absolute percentage error (APE) is used for comparing forecast.