BBahati Brenda Kizito·Aug 1599% Accuracy Is Not Always Good: What Fraud Detection Taught Me About MLMy fraud detection model hit 99% accuracy and still failed. Here’s what imbalanced data, precision, recall, F1-score, confusion matrices, and SMOTE taught me the hard way.8 min read·godfident-data.hashnode.dev
Iismail zamareh·May 6A Practical Guide to Tackling Class Imbalance in Tabular DatasetsComparative analysis of different categories of solutions for imbalanced tabular datasets — educational tutorial / beginner-friendly explainer with clear steps9 min read·athar-automation.hashnode.dev
KK Ahamed·Sep 30, 2023Addressing Imbalanced Datasets in Machine Learning: Leveraging SMOTE-NC for Enhanced Classification PerformanceAn imbalanced dataset in the context of machine learning is a dataset where the distribution of classes (categories) is not approximately equal. In other words, one class significantly outnumbers the other class or classes. This imbalance can create ...3 min read·datailm.hashnode.dev
EEdward Tian·Apr 1, 2018Handling Class ImbalanceWhat is class imbalance? When we’re dealing with a classification task, we have a model that tries to classify a record into some sort of category. Sometimes it’s whether or not a tumor is cancerous, or whether or not an application for a loan is acc...5 min read·dsblog.hashnode.dev
