Discussing the article: "Building a Neural Loss-Pattern Auditor in MQL5"

[MetaQuotes]

Check out the new article: Building a Neural Loss-Pattern Auditor in MQL5.

Aggregate metrics like win rate or profit factor miss sequence-dependent behavior, such as sizing up right after a loss. This MQL5 script trains a small native neural network on closed-deal history to estimate loss probability from behavioral and market-context features. It reports accuracy uplift over a baseline, probability calibration, and permutation feature importance, then combines them into a configurable A-F grade with concise, plain-language recommendations.

Consider two trades on the same symbol, opened at a similar volatility level and around the same time of day. The only difference is context: one follows a string of breakeven trades, and the other follows a loss and is sized 2.5 times larger than the trader's typical volume. A profit factor or win-rate summary treats both trades as two anonymous rows in the same ledger. Neither statistic can see that the second trade belongs to a pattern, a larger size specifically following a loss, because that pattern lives in the relationship between trades, not in any single trade's own outcome.

A single threshold rule, for example flagging any trade above 1.5 times the average size, would catch oversized trades in general. It cannot tell whether being oversized after a loss is riskier than being oversized after a win, or whether the effect only shows up when combined with something else, such as trading late in the session. Testing combinations of conditions by hand does not scale far past two or three features. This is exactly the kind of weak, multi-feature interaction problem a small neural network is suited for, and a fixed rule is not. The hidden layer can learn a combination of inputs, such as "recent loss and oversized," that no single input predicts well on its own.

Author: Cristian David Castillo Arrieta