# CRCEN: A Generalized Cost-sensitive Neural Network Approach for Imbalanced Classification

## TL;DR

This paper introduces CRCEN, a neural network with a novel loss function designed to improve classification performance on imbalanced datasets by effectively balancing minority and majority class predictions.

## Contribution

The paper proposes CRCEN, a new cost-sensitive neural network model with a weighted cross entropy loss and theoretical insights into its behavior for imbalanced classification.

## Key findings

- CRCEN outperforms baseline models on benchmark datasets.
- Theoretical relation between predicted probability, imbalance ratio, and weights.
- Effective handling of class imbalance in neural network training.

## Abstract

Classification on imbalanced datasets is a challenging task in real-world applications. Training conventional classification algorithms directly by minimizing classification error in this scenario can compromise model performance for minority class while optimizing performance for majority class. Traditional approaches to the imbalance problem include re-sampling and cost-sensitive methods. In this paper, we propose a neural network model with novel loss function, CRCEN, for imbalanced classification. Based on the weighted version of cross entropy loss, we provide a theoretical relation for model predicted probability, imbalance ratio and the weighting mechanism. To demonstrate the effectiveness of our proposed model, CRCEN is tested on several benchmark datasets and compared with baseline models.