Theoretical Analysis of an XGBoost Framework for Product Cannibalization

This paper is an extension of our work where we presented a three-stage XGBoost algorithm for forecasting sales under product cannibalization scenario. Previously we developed the model based on our intuition and provided empirical evidence on its performance. In this study we would briefly go over the algorithm and then provide mathematical reasoning behind its working.

An XGBoost-Based Forecasting Framework for Product Cannibalization

Two major challenges in demand forecasting are product cannibalization and long term forecasting. Product cannibalization is a phenomenon in which high demand of some products leads to reduction in sales of other products. Long term forecasting involves forecasting the sales over longer time frame that is critical for strategic business purposes. Also, conventional methods, for instance, recurrent neural networks may be ineffective where train data size is small as in the case in this study. This work presents XGBoost-based three-stage framework that addresses product cannibalization and associated long term error propagation problems. The performance of the proposed three-stage XGBoost-based framework is compared to and is found superior than that of regular XGBoost algorithm.

Supervised Machine Learning for Signals Having RRC Shaped Pulses

Classification performances of the supervised machine learning techniques such as support vector machines, neural networks and logistic regression are compared for modulation recognition purposes. The simple and robust features are used to distinguish continuous-phase FSK from QAM-PSK signals. Signals having root-raised-cosine shaped pulses are simulated in extreme noisy conditions having joint impurities of block fading, lack of symbol and sampling synchronization, carrier offset, and additive white Gaussian noise. The features are based on sample mean and sample variance of the imaginary part of the product of two consecutive complex signal values.