Data Mining for Imbalanced Datasets: An Overview

By Nitesh V. Chawla. The Data Mining and Knowledge Discovery Handbook, 2005

1,510 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/ecfdfcd1ef21449a01701122745a7be5ba135e7f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches (2012, background): “Anyway, neither uniform distributions nor skewed distributions have to imply additional difficulties to the classifier learning task by themselves [1]–[3].”
SMOTE for Regression (2013, neutral): “[1– 4]).”
A Systematic Review on Imbalanced Data Challenges in Machine Learning (2019, methodology): “In Chawla et al. (2002), Chawla proposed Synthetic Minority Over-Sampling technique (SMOTE).”
Toward Multimodal Cyberbullying Detection (2017, methodology): “Hence, besides the traditional accuracy mesure, we also consider the Receiver Operating Characteristic (ROC) metric that is often used for evaluating the performance of such classifiers [9, 31].”
Classification with class imbalance problem: A review (2015, background): “Choosing accuracy as the performing criterion in class imbalance classification may gives inaccurate and misleading information about a classifier performance [13][14][15][16][17][18][19].”
A systematic study of the class imbalance problem in convolutional neural networks (2017, background): “However, it has some significant and long acknowledged limitations, particularly in the context of imbalanced datasets [19].”
Dual autoencoders features for imbalance classification problem (2016, methodology): “The AUC, the F1-score, and the G-Mean are used to evaluate the performances of these methods [8,37,38].”
Classification of ingestive-related cow behaviours using RumiWatch halter and neck-mounted accelerometers (2019, neutral): “The precision (Pr), the sensitivity (Se), and the specificity (Sp) are defined as (Chawla, 2005): 𝑃𝑟 = 𝑇𝑃 𝑇𝑃+𝐹𝑃 (4) 𝑆𝑒 = 𝑇𝑃 𝑇𝑃+𝐹𝑁 (5) 𝑆𝑝 = 𝑇𝑁 𝑇𝑁+𝐹𝑃 (6) Here, TP (true positive) is the number of instances where the behaviour was correctly classified by the algorithm using…”
Local neighbourhood extension of SMOTE for mining imbalanced data (2011, methodology): “2In the paper introducing original version of SMOTE [3] it was expressed in percentage, e.”
Learned lessons in credit card fraud detection from a practitioner perspective (2014, background): “A well accepted measure for unbalanced dataset is AUC (area under the ROC curve) (Chawla, 2005).”
Comparing Random Forest with Logistic Regression for Predicting Class-Imbalanced Civil War Onset Data (2016, background): “Department of Computer Science and Engineering, Arizona State University, Tempe, AZ e-mail: jingrui.he@asu.edu”
Effective detection of sophisticated online banking fraud on extremely imbalanced data (2012, methodology): “As the online banking transaction data is extremely imbalanced, sampling is necessary before applying any data mining models [16].”