Toward Scalable Learning with Non-uniform Distributions: E ects and a Multi-classi er Approach

نویسندگان

  • Philip K. Chan
  • Salvatore J. Stolfo
چکیده

Many factors innuence the performance of a learned classiier. In this paper we study diier-ent methods of measuring performance based on a uniied set of cost models and the eeects of training class distribution with respect to these models. Observations from these eeects help us devise a distributed multi-classiier meta-learning approach to learn in domains with skewed class distributions, non-uniform cost per error, and large amounts of data. One such domain is credit card fraud detection and our empirical results indicate that, up to a certain degree of skewed distribution , our approach can signiicantly reduce loss due to illegitimate transactions.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Learning with Non - uniform Class and CostDistributions : E ects and a Multi - classi erApproachPHILIP

Many factors innuence a learning process and the performance of a learned classiier. In this paper we investigate the performance eeects of class distribution in the training set. We also study diierent methods of measuring performance based on cost models and the performance eeects of training class distribution with respect to the diierent cost models. Observations from these eeects help us d...

متن کامل

Toward Scalable Learning with Non-Uniform Class and Cost Distributions: A Case Study in Credit Card Fraud Detection

Very large databases with skewed class distributions and non-unlform cost per error are not uncommon in real-world data mining tasks. We devised a multi-classifier meta-learning approach to address these three issues. Our empirical results from a credit card fraud detection task indicate that the approach can significantly reduce loss due to illegitimate transactions.

متن کامل

Can Multiagents Learn in Organization? Analyzing Organizational-Learning Oriented Classi er System

Organizational-learning oriented Classi er System (OCS) is an extension of Learning Classi er Systems (LCSs) to multiagent environments with introducing the concepts of organizational learning (OL) in organization and management science. Unlike the conventional multiagent systems in the literature, which utilize speci c and elaborate techniques, OCS integrates four mechanisms from multi-strateg...

متن کامل

A Practical View of Suboptimal Bayesian Classification with Radial Gaussian Kernels

For pattern classi cation in a multi dimensional space the minimum misclassi cation rate is obtained by using the Bayes criterion Kernel estimators or probabilistic neural networks provide a good way to evaluate the probability densities of each class of data and are an interesting parallel implementation of the Bayesian classi er However their training procedure leads to a very high number of ...

متن کامل

Constructive Neural Network Learning Algorithms for Multi-category Pattern Classiication

Constructive learning algorithms o er an approach for incremental construction of potentially near-minimal neural network architectures for pattern classi cation tasks. Such algorithms help overcome the need for ad-hoc and often inappropriate choice of network topology in the use of algorithms that search for a suitable weight setting in an otherwise a-priori xed network architecture. Several s...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1999