Amazon SageMaker Local Mode Examples

The proposed methodology assess how compression algorithms influence the clustering analysis with respect to anomaly detection of vessel trajectories.

Sliced Detection and Clustering Analysis Toolkit - a tool to quickly find and cluster salient objects in your images for accelerated labeling

Tool to access and manage 14k+ jee main pyqs with semantic clustering

The thesis presents the parallelisation of a state-of-the art clustering algorithm, FISHDBC. This objective has been achived by improving the main data structures and components of the algorithm: HNSW, MST and HDBSCAN. My contribution is based on a lock-free strategy, completely wrote in Python.

Python library designed to classify photos containing specific individuals from a collection of images.

Built an end-to-end credit card default prediction system on 30,000 clients. Used HDBSCAN for behavioral segmentation (3 clusters), Gradient Boosting per cluster with SMOTE for class imbalance, Naive Bayes as baseline, and SHAP for model explainability. Deployed via Flask.

Transform scattered communications into strategic intelligence - ML-powered weekly analysis engine