E-learning practice is continuously using experimentation in order to enhance the basic information transfer model where knowledge is passed from the system/ tutors to the students. Boosting student productivity through on-line experimentation is not simple since many organizational, educational and technological issues need to be dealt with. This work describes the application of a Learning Mo...

Sales forecasting is a common topic in business. Our task is predicting a famous drug company daily sales for 1,115 stores located across Germany for six weeks in advance. Store sales are influenced by many factors. Our project aims to create a robust prediction model. Based on Gradient Boosting and Random Forest, our model performs well in this sales forecasting competition with resulting in r...

The expertise of electricity load forecasting has developed over decades. Some of the best load forecasting models use this expertise to improve the load forecasting accuracy by splitting the forecasting problem into sub-problems such as for weekend/weekday and peak/off peak. This research is designed to evaluate a method based on boosting algorithms to split the data into sub-problems for pric...

Lernmaschinen extrahieren Informationen aus einer gegebenen Menge von Trainingsbeispielen, so dass sie in der Lage sind, Eigenschaften von bisher ungesehenen Beispielen – z.B. eine Klassenzugehörigkeit – vorherzusagen. Wir betrachten den Fall, bei dem die resultierende Klassifikationsoder Regressionsregel aus einfachen Regeln – den Basishypothesen – zusammengesetzt ist. Die sogenannten Boosting...

This paper describes a new technique for solving multiclass learning problems by combining Freund and Schapire’s boosting algorithm with the main ideas of Dietterich and Bakiri’s method of error-correcting output codes (ECOC). Boosting is a general method of improving the accuracy of a given base or “weak” learning algorithm. ECOC is a robust method of solving multiclass learning problems by re...

Smooth boosting algorithms are variants of boosting methods which handle only smooth distributions on the data. They are proved to be noise-tolerant and can be used in the “boosting by filtering” scheme, which is suitable for learning over huge data. However, current smooth boosting algorithms have rooms for improvements: Among non-smooth boosting algorithms, real AdaBoost or InfoBoost, can per...

Smooth boosting algorithms are variants of boosting methods which handle only smooth distributions on the data. They are proved to be noise-tolerant and can be used in the “boosting by filtering” scheme, which is suitable for huge data. However, current smooth boosting algorithms have rooms for improvements: Among non-smooth boosting algorithms, real AdaBoost or InfoBoost, can perform more effi...

A general classification framework, called boosting chain, is proposed for learning boosting cascade. In this framework, a “chain” structure is introduced to integrate historical knowledge into successive boosting learning. Moreover, a linear optimization scheme is proposed to address the problems of redundancy in boosting learning and threshold adjusting in cascade coupling. By this means, the...

A general classification framework, called boosting chain, is proposed for learning boosting cascade. In this framework, a “chain” structure is introduced to integrate historical knowledge into successive boosting learning. Moreover, a linear optimization scheme is proposed to address the problems of redundancy in boosting learning and threshold adjusting in cascade coupling. By this means, the...

Boosting is a general method for improving the accuracy of any given learning algorithm. This short overview paper introduces the boosting algorithm AdaBoost, and explains the underlying theory of boosting, including an explanation of why boosting often does not suffer from overfitting as well as boosting’s relationship to support-vector machines. Some examples of recent applications of boostin...