Account and Behavioral Analysis Using AI with MetaTrader
Adapt the symbols, periods, position sizes, risk limits, and any criteria to your approach or preferences. Carefully study every prompt before using it and review any proposed action before executing it.
You are solely responsible for AI-generated content, AI-assisted actions, trading decisions, trading results, and any resulting losses.
Profitable and costly behaviors:
Analyze my trading history from the last six months. Identify the three behaviors that made or lost the most money, support each finding with statistics, and exclude small samples.
Entry mistakes:
Review losing trades from the last three months for early entries, price chasing, counter-trend trades, and poor stops. Compare each pattern with winning trades, then turn the strongest findings into five rules.
Exit efficiency:
Compare winning and losing trades from the last three months by MAE, MFE, holding time, entry timing, and exit efficiency. Identify exit improvements that do not rely on hindsight-only logic.
Reliance on exceptional trades:
For this month's trades, recalculate results without the best 1%, 5%, and 10% of trades. State whether the remaining results support a credible edge.
Performance after wins and losses:
Analyze trades from the last three months after wins, losses, and drawdowns. Compare lot size, frequency, stop distance, holding time, and rule-breaking behavior.
Best trading times:
Using my last six months of trades, identify the best and worst trading hours and days. Separate reliable patterns from small samples.
Transaction-cost impact:
Review this month's trades to determine whether spread, commission, swap, slippage, or trading frequency erase profits in any strategy subset.
Similar trades, different outcomes:
Compare this week's trades with similar H1 market conditions but different outcomes. Assess entry timing, direction, stop distance, volatility, and spread to identify the most likely differences behind the result.
Position-sizing discipline:
Analyze trade sizes from the last six months against equity, recent results, stop distance, volatility, and subsequent outcome. Flag credible size escalation or undersizing and estimate the effect of consistent percentage risk.
Revenge trading:
Search trades from the last three months for clusters opened after losses. Compare their size, timing, direction changes, holding time, cost, and expectancy with ordinary trades, then propose evidence-based cooldown rules.
Overtrading cost:
Using the last month of trades, compare results on low- and high-frequency trading days by gross profit, net profit after costs, expectancy, drawdown, and later-trade performance. Recommend a daily trade limit only if the sample supports it.
Exit-management score:
Use M15 data for trades closed in the last two months to estimate MAE and MFE. Score exits as efficient, premature, late, stop-driven, target-driven, or discretionary, and break the score down by symbol and market regime.
Stop-loss behavior:
Review this month's winning and losing trades for stop distance relative to volatility and nearby H1 structure. Identify tight, wide, or repeatedly obvious stop locations, and report rules only where the sample is adequate.
Strategy drift:
Compare my last month of trading with the previous three months by symbols, sessions, direction, sizing, stop distance, frequency, expectancy, and drawdown. Identify when meaningful changes began and their impact.
High-quality setup classifier:
Classify trades from the last six months by trend, volatility, session, breakout or pullback context, stop distance, and previous trade outcome. Create a short checklist that separates the strongest setups from lower-quality trades.
Personal trading playbook:
Use my last six months of history to create a trading playbook covering my best markets, sessions, setup conditions, sizing, frequency, stops, exits, and behavioral warning signs. Show the supporting statistics and label uncertain findings.
Disposition-effect coefficient:
Using the latest 200 closed trades from the last six months, compute the proportion of gains realized and losses realized from daily position snapshots. Estimate my disposition-effect coefficient with a simple proportion confidence interval, then compare the median holding time and subsequent 10-bar return of sold winners and retained losers.
House-money and break-even effects:
Using my latest 100 trades, classify each entry as following a daily gain, following a daily loss, or neutral. Compare the three groups by volume, stop distance, and expectancy, and count how often a post-loss trade was sized so its target would approximately restore the prior daily balance.
Round-number anchoring:
For my latest 100 EURUSD, XAUUSD, and US500 orders, test whether entry, stop, target, and exit prices cluster at whole or half levels more than the tick grid implies. Compare their fills and outcomes with the nearest historical ticks just beyond those levels and estimate the observed cost of anchoring.
Attention-driven buying:
Within the available news window, examine my latest 50 purchase trades. Mark a purchase when its symbol had a top-decile same-day return, top-decile tick activity, or a recent headline, then compare these attention-triggered purchases with the remaining purchases by next-day net return.
Outcome-bias audit:
For my latest 80 entries, score decision quality from four fixed entry-time facts: rule compliance, spread acceptability, stop definition, and portfolio-risk compliance. Compare the 20 closest matched pairs of high-quality losses and low-quality wins, then check whether the next trade's size reacted more to outcome than to quality.
Action-bias counterfactual:
For each of my latest 20 trading days, compare my actual result with two simple alternatives: no trade and the strongest qualifying setup among EURUSD, GBPUSD, USDJPY, XAUUSD, and US500. Use the same predefined entry rule on every day and estimate the return and cost attributable to taking additional actions.
Lottery-preference test:
Using my latest 100 trades in EURUSD, GBPUSD, USDJPY, XAUUSD, US500, and NAS100, estimate each symbol's return skewness from its latest 120 D1 bars. Test whether I overselect the two most positively skewed symbols despite lower trade expectancy, and whether those selections occur more often immediately after losses.
Narrow-framing penalty:
For my latest 50 closing decisions, evaluate the closed position together with the five largest simultaneous exposures by notional value using the preceding 60 D1 returns. Find closures that removed a useful hedge or retained concentrated risk, and estimate the next-day portfolio difference from keeping versus closing that leg.
Recency-weighting fingerprint:
Using my latest 100 trades, model the next trade's direction and relative size from only the previous one to five outcomes. Compare these five simple lag models and flag whether the last one or two trades influence decisions more strongly than longer history despite having no useful relationship with the next result.
Familiarity-bias opportunity cost:
Over my latest 60 trading days, compare my five most frequently traded symbols with EURUSD, GBPUSD, USDJPY, XAUUSD, and US500 using one predefined signal. Separate specialization from familiarity bias by comparing signal selection frequency, net trade expectancy, and the forward return of skipped alternatives.