Exploring Causal Inferences in Finance with Graph Neural Networks

[TKDE] The official code implementation for Financial Time Series Prediction with Multi-granularity Graph Augmented Learning.

This project predicts startup profitability using Logistic Regression and Random Forest, analysing financial (funding amount, funding rounds, revenue), market (market share), and operational (startup age, employee count) factors. It evaluates AUC, accuracy, precision, recall, and F1-score, addressing underfitting, overfitting, and feature selection

The AI class learnt in PHBS.

This project predicts startup profitability using Logistic Regression and Random Forest, analysing financial (funding amount, funding rounds, revenue), market (market share), and operational (startup age, employee count) factors. It evaluates AUC, accuracy, precision, recall, and F1-score, addressing underfitting, overfitting, and feature selection

🤖 Detect fraudulent transactions in real time with our AI system, reducing losses and providing clear explanations for compliance.

Personal, governed learning system for building AI fundamentals and applications in finance — learning in public.