Mining Graphs and Time Series:
Patterns, Anomalies, and Fraud Detection
by
Christos Faloutsos
CMU, Nov. 14, 2019
Tutorial to delegates from Government of India
Abstract
Given a large graph, like who-calls-whom, or
who-likes-whom, what behavior is normal and what should be
surprising, possibly due to fraudulent activity? How do graphs
evolve over time? Given one or more time sequences, how can we
forecast their evolution? how to spot anomalies and discontinuities?
We focus on these two topics: pattern and anomaly detection in
static and time-evolving graphs; and analysis and forecasting in
time sequences.
Foils
- Foils (pptx) in one
zip-file (Caution: over 20MB).
-
Foils (pdf, 3-up) in another
pdf zip-file.
Also per section - each taking 1hour.
Last updated by: Christos Faloutsos, Nov. 13, 2019