0.25
0.5
0.75
1.25
1.5
1.75
2
Temporal Causal Modeling with Graphical Granger Methods
Published on Aug 22, 20079751 Views
The need for mining causality, beyond mere statistical correlations, for real world problems has been recognized widely. Many of these applications naturally involve temporal data, which raises the ch
Related categories
Chapter list
Temporal Causal Modeling with Graphical Granger Methods00:03
Talk Outline00:19
A Motivating Example: Key Performance Indicator Data (KPI) in Corporate Index Management [S&P] 00:48
KPI Case Study: Temporal Causal Modeling for Identifying Levers of Corporate Performance01:37
Granger Causality02:52
Variable Space Expansion & Feature Space Mapping05:21
Graphical Granger Methods07:04
Exhaustive Granger vs. Lasso Granger08:33
Baseline Methods: SIN and VAR08:41
Empirical Evaluation of Competing Methods08:42
Experiment 1A: Performance vs. Factors10:38
Experiment 1’s Efficiency 11:53
Experiment 1B: Performance vs. Factors12:54
Experiment 1C: Performance vs. Factors13:11
Experiment 2: Learned Graphs15:35
Experiment 3: Real World Data Output Graphs on the Corporate KPI Data16:09
Thank You16:49