awslabs / realtime-fraud-detection-with-gnn-on-dgl
An end-to-end solution for real-time fraud detection(leveraging graph database Amazon Neptune) using Amazon SageMaker and Deep Graph Library (DGL) to construct a heterogeneous graph from tabular data and train a Graph Neural Network(GNN) model to detect fraudulent transactions in the IEEE-CIS dataset.
Summary
       |
|||
| Main Code: 6,133 LOC (63 files) = TS (54%) + PY (21%) + TSX (16%) + SCSS (6%) + GRAPHQL (<1%) + HTML (<1%) + JS (<1%) Secondary code: Test: 3,182 LOC (8); Generated: 0 LOC (0); Build & Deploy: 74 LOC (2); Other: 2,961 LOC (30); |
|||
| Duplication: 4% | |||
| File Size: 0% long (>1000 LOC), 47% short (<= 200 LOC) | |||
| Unit Size: 40% long (>100 LOC), 28% short (<= 10 LOC) | |||
| Conditional Complexity: 0% complex (McCabe index > 50), 80% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (10 components) | ||
|
|
10 months old
|
||
|
|
0% of code updated more than 50 times Also see temporal dependencies for files frequently changed in same commits. |
||
| Goals: Keep the system simple and easy to change (4) | |||
|
Features of interest:
TODOs
2 files |
|||
Latest commit date: 2022-01-29
|
12
commits
(30 days)
4
contributors
(30 days) |
|