Online Local Boosting: improving performance in online decision trees
This addresses the need for efficient data stream mining algorithms for handling continuous data, though it appears incremental as it builds on existing online decision tree methods.
The paper tackles the problem of high processing and memory costs in data stream mining algorithms by introducing Online Local Boosting (OLBoost), which improves predictive performance without significantly increasing costs, as shown in experiments where it enhanced online decision tree algorithms and enabled smaller trees to perform as well as larger ones.
As more data are produced each day, and faster, data stream mining is growing in importance, making clear the need for algorithms able to fast process these data. Data stream mining algorithms are meant to be solutions to extract knowledge online, specially tailored from continuous data problem. Many of the current algorithms for data stream mining have high processing and memory costs. Often, the higher the predictive performance, the higher these costs. To increase predictive performance without largely increasing memory and time costs, this paper introduces a novel algorithm, named Online Local Boosting (OLBoost), which can be combined into online decision tree algorithms to improve their predictive performance without modifying the structure of the induced decision trees. For such, OLBoost applies a boosting to small separate regions of the instances space. Experimental results presented in this paper show that by using OLBoost the online learning decision tree algorithms can significantly improve their predictive performance. Additionally, it can make smaller trees perform as good or better than larger trees.