Skip to content
Montex Alpha Rail System
$497

Analytics Labs — Advanced EV Lab

Where expectancy gets interrogated, not just calculated.

Beyond the headline number

EV exists at many layers.

Normal EV, Trend Partial EV, Trend No-Partial EV, Overflow EV, Trend Blend, Normal+Trend, All-Blended, weekly, monthly, rolling, structural. A blended number can hide branch weakness — the lab decomposes it so the operator sees where edge actually comes from, and how stable it is across windows.

  • Rolling EV versus static EV separates persistent edge from favorable-sequence artifacts.
  • Outlier robustness: does monthly EV survive removing the one +8R trade? If not, median behavior is the truth.
  • Sensitivity maps show which probability assumptions the blended EV is fragile to.

Beyond the headline number

EV exists at many layers.

Normal EV, Trend Partial EV, Trend No-Partial EV, Overflow EV, Trend Blend, Normal+Trend, All-Blended, weekly, monthly, rolling, structural. A blended number can hide branch weakness — the lab decomposes it so the operator sees where edge actually comes from, and how stable it is across windows.

01Rolling EV versus static EV separates persistent edge from favorable-sequence artifacts.
02Outlier robustness: does monthly EV survive removing the one +8R trade? If not, median behavior is the truth.
03Sensitivity maps show which probability assumptions the blended EV is fragile to.

The core idea

How MARS uses this

The Weekly Scorecard converts branch hit probabilities into EV and tags each week by threshold. The rolling line is what MARS actually trusts: single-week readings are treated as noise until the rolling window confirms direction. RED weeks trigger doctrine - reduced aggression and review - rather than negotiation.

GREEN ≥ +0.25RYELLOWREDROLLING EVW1W2W3W4W5W6W7W8W9W10W11W12

How it benefits you

You learn to distinguish a bad week from a broken system. Variance stops triggering rule changes, and genuine expectancy decay gets caught while it is still one line on a chart instead of a hole in the account. The GREEN/YELLOW/RED language also makes weekly review fast and unambiguous.

Weekly EV tagged GREEN / YELLOW / RED against expectancy thresholds, with the rolling-EV line separating persistent edge from one lucky week.

R&D boundary

02

The lab is a sandbox with a door.

Weight experiments, filter ideas, and profile candidates live here — validated against evidence before deliberate promotion. Production data flows forward cleanly; the lab must never contaminate the live Scorecard until a change is tested, approved, and intentionally moved into production.

Reference

The credibility checks — is the edge statistically real?

CheckQuestion it answers
Sample maturityIs there enough closed-trade evidence to trust the EV at all?
Branch-level EV separationIs edge coming from where the model says it should?
Sensitivity tablesHow fast does EV degrade as hit rates slip?
Fee-drag stressDoes the edge survive real commission and swap load?
Blend robustnessDoes the weighted profile stay positive when weights drift?

Reference

CLEAN: low pain, high opportunitySURVIVORS: works, but absorbs painQUIET: low pain, low reachBLEEDERS: pain without payoffMAE (stop consumed) →MFE (opportunity) →

Every trade plotted by pain taken (MAE) versus opportunity generated (MFE). The four quadrants diagnose entry precision and exit management at a glance.

Inside this module

2 pages go deeper than this one.

01

Layers of EV

Go deeper →

02

The R&D Sandbox

Go deeper →

Connected inside MARS

This module doesn't work alone.

Connected — 01

Expected Value (metric)

Open system page →

Connected — 02

Weekly Trading Scorecard

Open system page →

Connected — 03

Monte Carlo Lab

Open system page →

Use cases

Where it earns its place

  • ▸Validating a strategy's expectancy is real before scaling risk
  • ▸Testing whether fee drag and slippage are consuming a thin edge
  • ▸Comparing standard logic against branch variants on expectancy contribution
  • ▸Stress-testing EV assumptions before they feed the Monte Carlo model

Edge cases & failure modes

Where it can mislead

  • !Small samples: six good trades prove nothing — insufficient-sample states exist for a reason.
  • !Sequence luck inflates short-window EV; rolling stability tracking is the antidote.
  • !EV boosted by overexposure isn't edge — RAER and RAPF exist to catch exactly this.

Go deeper

Operator briefs on this territory.

Deep dive — 01

Six families of EV truth: how the lab decomposes one number into causes.

One EV number, six causal families. The lab's job is telling you which family owns the problem.

Read the full brief →

Deep dive — 02

Statistical truth first: the gate battery every EV must pass.

Sample gate, lower bound, P(EV>0), outlier stripping — the honesty battery before any EV means anything.

Read the full brief →

Deep dive — 03

Rolling EV: the tab that catches decay while the average still smiles.

The cumulative average is the last to know. Rolling windows are where edge decay first becomes visible.

Read the full brief →

Take it further

Six metric families, one configuration at a time. The Foundry runs the same statistical layer as an experiment surface — change the scope, the winsorization, the confidence level, and watch which verdicts hold.

Open the AlphaRail Foundry Lab ↗

Every module ships in the complete MARS package.

One price. Eleven workbooks, three TradingView indicators, and the full manual library — $497.

Get MARS Pro — $497Explore the Platform