Back

I'm building a conditional probability platform for intraday trading decisions based on session structure. The specific problem I'm trying to solve is:

Given a known invalidation level that typically gets breached within a known time bucket, what is the maximum distance price can realistically travel against my position before that bucket closes at 90% confidence based on current session volatility?

For the volatility input I was thinking of using the Markov regime switching model Roman shared in his channel as a live volatility determinator, I'm aware its uses 5-second bars by default that's why I'm planning to change the bar duration to match however many candles were printed before my entry signal fires using probability-weighted σ instead of hard state.
Any thoughts on whether this is the right approach?

I really appreciate what you've built here Roman, the platform and the videos have been a big part of how I'm thinking about these problems, keep it up!