Probabilistic Graphical Models
Probabilistic graphical models for real decisions.
Bayesian networks, Markov networks, causal models, and the inference that runs on them. Worked examples across healthcare, retail, sports, policy, and drug discovery, every one shipping a model you can open and query in Darkstar.
-
Latest
Causality APIs 42: Loyalty Offers And Customer Lifetime Value
A synthetic loyalty-offer model separates redemption from true customer value when identity resolution, prior loyalty, margin, personalization, churn, and reward liability interact.
Latest articles
-
Causality APIs 07: The Campaign Knocked On The Wrong Doors
Campaigns love to say the doors they knocked decided the race. The problem is that campaigns do not knock doors at random, and the people who answer are…
-
LeadScope 05: The Average Lied
A mean effect can hide who should and should not receive an edit. That fail-closed boundary is part of the product, not a footnote.
-
Causality APIs 06: The Sepsis Alert Saved Lives. Or Did It?
A hospital switches on a sepsis alert and mortality moves. That does not mean the alert caused the change. The hard part is separating who gets flagged from…
-
LeadScope 04: The Frontier Already Knew
A recommendation gets stronger when it shows up as a populated region of chemistry, not a lone theoretical win. That happened in one of our lorazepam-centered internal workflows.
-
LeadScope 03: The Best Lead Was a Recipe
In one of our internal lorazepam-centered workflows, the most useful result was not one magic winner. It was a coordinated direction of change that improved safety without breaking…
-
LeadScope 02: Causality Is the Differentiator
Prediction can describe where a molecule sits. Causal reasoning helps decide which lever is worth trying next, what it may improve, and when the evidence is too weak…
-
Causality APIs 05: A/B Tests Are Causal, Until You Condition on the Wrong Thing
A clean A/B test is already a causal design. The trouble starts when someone conditions on post-treatment behavior, slices the experiment the wrong way, or forgets what randomization…
-
Causality APIs 04: An HMM Is Just a Dynamic Bayesian Network
Once you unroll time, an HMM is just an ordinary Bayesian network with repeated structure. That makes temporal reasoning much less mysterious and much more programmable.
-
Causality APIs 03: The Other World Is the Product
Counterfactuals are where causal APIs stop describing populations and start answering the harder question: what would have happened for this exact case?
-
Causality APIs 02: Seeing Is Not Setting
If observing X and setting X collapse to the same operation in your tooling, confounding has already beaten you.
-
Causality APIs 01: The Aggregate Lied
A treatment can look worse in the aggregate and better in every subgroup. That is not a corner case. It is the reason your query surface needs association,…
-
LeadScope 01: The Score Is Not the Strategy
Lead optimization does not stall because teams lack scores. It stalls because scores do not answer what analog to make next under competing objectives.