Synthetic fraud graph generator for benchmarking graph-based fraud detection models in financial services.

Tutorials for Machine Learning on Graphs

[IJCNN 2021] Unified Spatio-Temporal modeling for traffic forecasting using Graph Convolutional Network

Research Project I completed under Dr Vinti Agrawal at BITS Pilani.

Data and code for Salesforce Research paper, GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning - https://arxiv.org/abs/2012.03900 . The paper provides methods for constraint graph augmentation and optimal facility placement problems

Pure Go machine learning framework. Train, run, and serve ML models with go build. Zero CGo.

A Task-Oriented graph SAmpler for HGNN

CLEVR graph: A dataset for graph based reasoning

This repository is the result of my self-study journey and a testament to the value of learning independently. It was created to inspire others to explore AI, understand what happens under the hood, and leave behind something that continues to teach long after I am gone.

Compare LLM text embeddings with structure-aware Graph AI (GNN link prediction) on any dataset with nodes, text, and edges.

Graph-native AML investigation: 14 topology features, LightGBM scoring (ROC-AUC 0.87), path-level explanations, live case explorer.

Avaliação de integridade e risco de fornecedores públicos. Cruza dados de sanções, processos e idoneidade com ML e análise de grafo.

Production-grade fraud detection pipeline with entity-level behavioral feature engineering, velocity anomaly detection, graph-based risk signals, and real-time scoring API. Built with XGBoost, PyTorch, FastAPI, and Docker.

Machine learning on graphs

Graph-RAG for Customer Journey Intelligence using NetworkX + LLM. Path-aware retrieval outperforming vector RAG on temporal queries, cohort comparison with real statistics, 5 pre-built analytics queries, and fully dockerized FastAPI/Streamlit architecture deployed on HuggingFace Spaces.

Graph-based anomaly detection for Medicare Part B billing fraud using public CMS data.

Graph ML platform for fraud ring detection using node2vec embeddings and community detection on transaction networks

word2vec, sentence2vec, machine reading comprehension, dialog system, text classification, pretrained language model (i.e., XLNet, BERT, ELMo, GPT), sequence labeling, information retrieval, information extraction (i.e., entity, relation and event extraction), knowledge graph, text generation, network embedding

A deep learning architecture combining spectral graph neural networks with curriculum learning for HOMO-LUMO gap prediction on PCQM4Mv2. Features a dual-view architecture with Chebyshev polynomial-based spectral convolutions and complexity-driven training schedules.