Time Molecules bridges Business Intelligence (BI), process mining, and systems thinking to help practitioners see beyond static dashboards into the flows of events that actually drive outcomes. It introduces a scalable framework for building and analyzing Markov models—simple, interpretable probabilistic representations of event transitions—across all domains of enterprise data. The book’s goal is to overcome process blindness by modeling the dynamic cycles that define business and life: sales, production, hiring, and other iterative systems that evolve through time and interact with one another.
The framework treats every case as a cycle of events and uses Markov models (Time Molecules) to capture how those events progress and influence each other. Like OLAP cubes, these models can be sliced, diced, and cached for comparison, but instead of aggregating static measures, they summarize transitions—the probabilities of what happens next and how long it takes.
By combining BI’s dimensional rigor with process-aware modeling, Time Molecules equips analysts, engineers, and decision-makers to anticipate change, simulate future outcomes, and cultivate the systems intuition needed in an AI-driven world. It argues that while modern AI (LLMs, RNNs, Transformers) models sequences of words, Markov models remain the clearest, most scalable, and interpretable way to model sequences of events, providing a human-intuitive foundation for intelligence grounded in time.
Soft Coded Logic 