VVashni Roy·3d agoWhy 0.5 Isn't Always the Right Classification ThresholdI changed the threshold of the same churn model from 0.3 to 0.7. The model stayed the same, but its predictions changed quite a lot.3 min read·vashniroy.hashnode.dev
SSiddhesh Sawant·2d agoLogistic Regression from First Principles: Log-Odds, Likelihood and the Decision ThresholdLogistic regression derived step by step: sigmoid and log-odds, log loss and its gradient, gradient descent and Newton's method, and the decision threshold.53 min read·siddheshsawant.hashnode.dev
DDylan Hogg·Sep 25Static embeddings: a practical guide to model2vecSentence-transformer embeddings work well, but they are slow on a CPU. For a few thousand texts, the speed doesn't matter. When you embed millions of texts, or need embeddings within a tight latency b8 min read·infocruncher.hashnode.dev
MMunukutla Sri Shanmukha Aditya·Sep 4Why Accuracy Can Be Misleading in Failure Detection SystemsWhy accuracy can mislead in failure detection systems, and why precision and recall matter when working with imbalanced data.4 min read·shanmukha-aditya.hashnode.dev1A
TTharun·Aug 31From Lines to Decisions: Why Regression Fails at ClassificationLearn why linear regression fails at classification, how predictions can go below 0 or above 1, and why sigmoid is needed for probabilities.9 min read·tharunpandya.hashnode.dev1
AAkash·Aug 5Building Production-Ready ML Models: From Data to DeploymentMaster ML workflows with real-world projects. Learn preprocessing, training, evaluation, and deployment using Python & scikit-learn.12 min read·akashbuilds.hashnode.dev
NNethmi Amasha·Aug 3Why Are Both Chi-Square Test and ANOVA (F-Test) Used for Classification?Explore the differences between Chi-Square and ANOVA (F-Test) for feature selection in classification using simple examples.4 min read·curiousdeveloperbyamasha.hashnode.dev
AAkshay Yadav·Aug 1Predictive Maintenance for Industrial MachinesProblem Statement A manufacturing plant wants to predict machine failure before it happens using live sensor readings (air/process temperature, rotational speed, torque, and tool wear), so that mainte9 min read·projectsoncs.hashnode.dev
AAman Jain·Jul 16Building a GPT Model from Scratch (Part 5): Fine-Tuning GPT-2 for Text ClassificationHow I adapted a pretrained GPT-2 model to classify SMS messages as spam or not spam.10 min read·curious-pm.hashnode.dev
RRishikant·Jun 28Mastering Logistic Regression: Probability, Decision Boundaries, and Advanced RegularizationMoving beyond basic classification: A deep dive into Cross-Entropy MLE, Elastic Net, and L-BFGS optimization.7 min read·rishiii2.hashnode.dev
