Decision Science Lab
Interactive experiments that build intuition for the algorithms powering ChainAlign.
Build intuition through play. Manipulate the models and see how they respond.
Correlation vs. Causation
Why connected things aren't always related
Just because two things happen together doesn't mean one causes the other. Ice cream sales and drowning deaths both rise in summer—but ice cream doesn't cause drowning. Heat causes both. In business, this mistake is expensive. You might invest millions "fixing" something that was never the real problem. There are 6 ways two things can be connected: • One causes the other (Direct Causation) • The reverse—you've got it backwards (Reverse Causation) • Something else causes both (Confounding) • Pure coincidence (Spurious Correlation) • Each causes the other in a loop (Bidirectional) • The pattern changes depending on context (Simpson's Paradox)
Bottom Line
Identifying the true relationship determines whether your intervention will work or waste resources.
In Your World
Before your next initiative, ask: "Are we fixing the cause, or just something that happens alongside it?"
Further Reading
Pearl, J. (2000). Causality: Models, Reasoning, and Inference. Cambridge University Press.
Book: Pearl, J. & Mackenzie, D. (2018). The Book of Why. Basic Books.
→ Do-calculus, causal graphs
Try It Yourself
Interact with the controls below to see how it works
Direct Causation
A truly causes B. Intervening on A will change B.
Example: Increasing production capacity → Higher output
These algorithms work together to produce decisions with explicit uncertainty quantification and transparent reasoning.
See ChainAlign in Action →