Cluster-based Forecasting for Laboratory samples Research paper Business Analytics

Forecasting a future event is important for companies for a better planning in their daily operations, also it helps every company to understand their customers better. Companies use forecast methods to predict the future events on a daily, weekly, and monthly basis. Forecasting requires data from the past and present to predict the future. This report addresses the methods that are used to forecast the number of samples to be received in 2017 for IDEXX Laboratories in the United Kingdom. The data used for this research paper contains the number of samples received from the veterinary practitioners at IDEXX Laboratories from January 2010 until December 2016. Because of the challenges in the data, customers are first clustered using three distance measures. The forecast is done on the clustered data using the Holt Winters model and the ARIMA model. The best forecasting model is then chosen with the lowest Root Mean Squared Error [RMSE].