A Comparison of Oversampling and Undersampling Methods for Predicting Air Quality in Metropolitan Region

Javale, Deepali; Pillai, Pooja; Patel, Purvang; Jagtap, Sushmita

doi:10.1109/icaaic53929.2022.9793084

Cited by 2 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… NeighbourhoodCleaningRule: This technique involves selecting a subset of the majorityclass observations that are nearest to the minority-class observations based on a distance metric such as Euclidean distance. The majority class observations that are farther away from the minority class observations are discarded [34]. In addition, the majority class observations that are nearest to the minority class observations are removed if they are not…”

Section: Figure 6: Unbalanced Target Variable Classesmentioning

confidence: 99%

Enhancing Customer Retention through Deep Learning and Imbalanced Data Techniques

Loukili,

Messaoudi,

El Ghazi

2024

Iraqi Journal of Science

View full text Add to dashboard Cite

Accurately predicting customer churn is considered crucial by businesses in order to take proactive measures to retain their customers and avoid financial losses. In this paper, a customer churn prediction model is proposed that incorporates deep neural networks and imbalanced data techniques. The approach involves applying oversampling and undersampling methods to address class imbalances in the dataset. The model's performance is evaluated using various evaluation metrics and compared to other methods. The results demonstrate that superior performance in predicting customer churn is achieved by the proposed model compared to traditional statistical methods and deep neural networks without imbalanced data techniques. Important implications for businesses seeking to reduce customer churn and improve customer retention are provided by our findings. By using the suggested model, customers can be retained, and financial losses can be avoided proactively.

show abstract

Section: Figure 6: Unbalanced Target Variable Classesmentioning

confidence: 99%