How to extract meaningful information from big data has been a popular open problem. Decision tree, which has a high degree of knowledge interpretation, has been favored in many real world applications. However noisy values commonly exist in high-speed data streams, e.g. real-time online data feeds that are prone to interference. When processing big data, it is hard to implement pre-processing and sampling in full batches. To solve this trade-off, we propose a new decision tree so called incrementally optimized very fast decision tree (iOVFDT). Inheriting the use of Hoeffding bound in VFDT algorithm for node-splitting check, it contains four optional strategies of functional tree leaf, which improve the classifying accuracy. In addition, a multi-objective incremental optimization mechanism investigates a balance among accuracy, mode size and learning speed...

Project Samples

Project Activity

See All Activity >

Categories

Big Data

Follow iOVFDT

iOVFDT Web Site

Other Useful Business Software
Email and SMS Marketing Software Icon
Email and SMS Marketing Software

Boost Sales. Grow Audiences. Reduce Workloads.

Our intuitive email marketing software to help you save time and build lasting relationships with your subscribers.
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of iOVFDT!

Additional Project Details

Registered

2013-02-01