Blog
Posts & updates
Writing from MyMarketEstimates. Posts live on Substack — click any post below to read it there (opens in a new tab).
20 most recent posts
Where the Models Break
Jun 8, 2026 · nfos
The previous posts in this series covered how win probability models work across six sports - the Markov chains behind baseball and tennis, the Poisson framework for soccer and hockey, the random walk in basketball, and…
Where Sportsbooks and Prediction Markets Fall Short for Sports Trading
Jun 3, 2026 · nfos
Both models host trading today, but the structural gaps come from opposite directions. The architecture that closes them is starting to come into view.
Dynamic Tournament Win Probability: The Integration Layer
May 27, 2026 · nfos
The previous two posts described tournament-level win probability for Grand Slams and the World Cup as separate problems.
Thinking Through Win Probability at the Grand Slams
May 22, 2026 · nfos
The tennis win probability model described earlier in this series operates at the match level.
Win Probability at the World Cup
May 17, 2026 · nfos
The 2026 FIFA World Cup kicks off June 11 in North America.
Soccer and Hockey: The Poisson Sports
May 17, 2026 · nfos
Soccer and hockey share a structural property that separates them from basketball and football: goals are rare.
BioValue: building a drug valuation tool from scratch
May 12, 2026 · nfos
check it out live: BioValue
The Perception Problem
May 10, 2026 · nfos
A mutual friend recently introduced me to a wealth advisor.
Baseball and Tennis: The Discrete State Sports
May 10, 2026 · nfos
Baseball and tennis share a structural property that separates them from every other major sport: the game state at any moment is fully described by a finite, enumerable set of discrete variables.
From API Call to Bedrock in Five Files
May 10, 2026 · nfos
The previous post explained the rationale for moving from direct Anthropic API (Application Programming Interface) calls to AWS (Amazon Web Services) Bedrock.
From Claude to Bedrock
May 6, 2026 · nfos
Most people who use Claude interact with it in one of two ways: the website at claude.ai, or Claude Code in the terminal.
Basketball: The Random Walk
May 6, 2026 · nfos
Basketball produces more scoring events per game than any other major sport.
The Process Caught Up to the Code. The Tools Haven't.
Apr 30, 2026 · nfos
The previous post argued that AI flipped the bottleneck in software development.
The Training Problem Nobody Talks About
Apr 30, 2026 · nfos
Every company that scales past a handful of people hits the same wall.
The Math Behind Win Probability
Apr 30, 2026 · nfos
The previous post mapped the landscape - which sports use which approaches and why.
Measure Once, Cut Twice
Apr 24, 2026 · nfos
The bottleneck in software development moved. The process hasn't caught up.
From the Sportsbook to the Order Book
Apr 21, 2026 · nfos
From bookmakers to prediction markets: the two-century evolution that explains why Wall Street tools don't work on sports.
Updating the encrypted live site with one Cowork prompt
Apr 19, 2026 · nfos
follow on from last post
The State of Win Probability in Sports
Apr 19, 2026 · nfos
Win probability is one of the most widely displayed and least understood numbers in sports.
Choosing an Agent Framework is an Engineering Decision
Apr 16, 2026 · nfos
We recently went through the agent framework decision at SportChartz.