1. What marketXED is, and what it is not
marketXED is a decision-support tool for short-term US equity trades. It continuously scans a watchlist plus dynamic Yahoo screeners, scores each ticker through a committee of independent analytical agents, and produces a small number of actionable signals per session, each accompanied by an explicit, beginner-safe playbook (limit price, stop, target, share count, dollar risk, exit time).
- It is a structured second opinion that enforces process: defined risk, hard exits, calibrated probabilities, and a learning feedback loop.
- It is not a broker, an execution engine, an oracle, or a guarantee. You place every order. You own every loss and every gain.
Read this whole document at least once before placing your first trade. If any section is unclear, paper-trade for two weeks before risking real capital.
2. The data pipeline
Every poll cycle (~60 seconds) the server performs roughly the following work for each ticker in the active universe:
- OHLCV candles are fetched from Yahoo Finance (free, public). Both intraday and daily series are pulled depending on mode (Day vs Swing).
- Sentiment is computed from X/Twitter posts (when feed is enabled) using VADER, an off-the-shelf NLP scorer tuned for short social text. Score range: −1 (very negative) to +1 (very positive).
- Regime detection classifies the broader market (trending / mean-reverting / volatile / quiet) and scales each agent's vote accordingly.
- Vetoes filter out structurally unsuitable setups (e.g. ultra-thin volume, illiquid pre-market, gap-and-fade traps).
- Learning weights from the historical hit-rate of each agent on each regime are applied as multipliers.
All persistent files (state.json, signals.json, learning.json, predictions.jsonl) are written atomically with secrets locked to 0o600 permissions.
3. The 10-agent committee
Ten independent agents each emit a vote in [-1, +1] and a confidence in [0, 1]. They are deliberately heterogeneous so they fail in different ways:
| Agent | Method | Catches |
| Wyckoff | Phase analysis (accumulation/distribution) | Spring loading, distribution tops |
| Bayesian | Posterior from momentum + sentiment | Probabilistic edge in mixed signals |
| Momentum / RSI | 14-period RSI + 12-bar ROC | Acceleration, exhaustion |
| Mean-Reversion | 20-period z-score | Over-extensions to fade |
| Volume-Flow | OBV slope (50 vs prior 50) | Hidden accumulation/distribution |
| Sentiment-X | VADER on X posts | Crowd narrative shifts |
| Postmortem-Helper | Replays past hits/misses | Repeating regime mistakes |
| Volatility-ATR | ATR expansion + bar location | Breakouts vs. coils |
| Trend-MA | 20/50 SMA cross + position | Primary trend direction |
| Microstructure | Wick imbalance (20 bars) | Absorption vs. supply pressure |
| Risk/Kelly | Sharpe + Kelly fraction | Risk-adjusted edge sizing |
The committee then runs a three-round debate:
- Round 1, Declare: each agent states LONG / SHORT / NEUTRAL with thesis text.
- Round 2, Align: every agent is reclassified as AGREE or DISSENT against the running consensus.
- Round 3, Verdict: the chair tallies the longs/shorts/neutrals and declares the conviction percentage.
4. Conviction, agreement, calibrated probability
Score
Σ(vote · confidence) / Σ confidence
Sign tells direction (+ = LONG). Magnitude is between −1 and +1.
Agreement
Pairwise sign-match ratio
How unified the committee is. 0 = totally split, 1 = perfectly aligned.
Conviction
|score| · agreement · coverage
The headline number. Only signals above your Min conviction threshold fire.
Conviction is converted to a raw probability (50 + score · 40) and then calibrated against the historical hit-rate stored in learning.json. The Settings tab lets you require a minimum calibrated probability (default 55%) and a minimum reward/risk after fees (default 1.2×). A signal must clear both gates plus the conviction floor to be promoted to "actionable".
5. From signal to playbook
When a signal becomes actionable the playbook generator (playbook.js) computes a Robinhood-friendly trade plan tuned for tiny accounts:
- Entry: limit order with a small price-protection buffer (no chasing).
- Stop: the larger of
1.5 × ATR, 2% of price, or $0.05.
- Target: sized so realized R/R, after round-trip slippage and friction, still meets your minimum (default 1.2×).
- Hold window: never beyond 5 minutes before the regular session close, regardless of intraday targets.
- SHORT picks on Robinhood return a "skip or use a Put option" notice, the app refuses to draw a short order ticket on a cash account.
6. Position sizing & the R/R math
The sizer is intentionally conservative. Two formulas race; the smaller wins:
risk_per_share = stop_distance + 2 × slippage_per_share
fixed_risk_shares = floor( riskUSD / risk_per_share )
half_kelly_shares = floor( fixed_risk_shares × 0.5 )
shares = max( 1, min( fixed_risk_shares, half_kelly_shares ) )
Worked example: 25 USD risk, $40 stock, $0.60 stop distance:
- Slippage per share ≈ $40 × 0.0015 × 2 = $0.12
- Risk per share = $0.60 + $0.12 = $0.72
- Max shares by fixed-$ rule = floor(25 / 0.72) = 34
- Half-Kelly cap = 17
- Final size = 17 shares · order ≈ $680 · max loss ≈ $12.24
Break-even win-rate at the configured R/R floor of 1.2× is 100 / (1 + 1.2) ≈ 45.5%. If your sustained hit-rate falls below that, the system is losing money even when "right".
7. Alerts: UI, browser push, SMS
- UI banner & sound: every actionable signal pops a sheet at the bottom of the screen and a soft chime.
- Browser notifications: granted via the standard permission prompt; titled "marketXED · LONG TICKER".
- SMS: when Twilio credentials are configured in Admin, the same alert is sent to your phone only between 9 a.m. and 4 p.m. ET and de-duplicated for 6 minutes per ticker/direction.
Every alert is recorded in SMS History. There is no auto-execution: you open Robinhood and place the order.
8. The learning loop
For every actionable pick the system writes a row to predictions.jsonl: ticker, direction, entry, stop, target, conviction, agent votes, and the regime classification. After the trade window closes (or the next day), the actual outcome is matched and the per-agent / per-regime hit-rate is updated.
These rates feed back as multiplicative weights on each agent's confidence in the next cycle. Over time, agents that consistently fail in a given regime are progressively muted; agents that are reliably correct are amplified. There is no neural network and no opaque "AI", every weight is human-readable in learning.json.
9. Risks you must understand
- Market risk. You can lose 100% of capital on any single trade. Stops can and do slip through gaps, halts, and after-hours moves.
- Model risk. Indicators (RSI, ATR, OBV, etc.) are descriptions of the past. Regimes shift; agents that worked yesterday may misfire today.
- Data risk. Free Yahoo data is delayed (typically 15 min for some venues), occasionally wrong, and offers no SLA. Sentiment from X/Twitter is biased toward whoever is loud.
- Execution risk. Limit orders may not fill; market orders can fill far from the screen quote in low-liquidity names.
- Slippage & fees. Even on commission-free brokers, the bid/ask spread is a real cost. The sizer assumes 0.15% one-way for stocks ≥ $5 and 0.5% for sub-$5 names.
- Short-side limitation. Robinhood cash and standard margin accounts cannot short. Inverse ETFs and put options carry their own decay/leverage hazards.
- Over-trading. The cap of 3 actionable picks per session is a feature, not a bug. Ignoring it dilutes edge.
- Psychological risk. A streak of stops triggers revenge-trading. Walk away after two consecutive stops in a session.
- System risk. The app is self-hosted on a single laptop. Power, network, or process failure means missed signals, never depend on it as a sole source of truth.
- Regulatory risk. US Pattern-Day-Trader rules apply at 4 day-trades / 5 business days for accounts under $25,000. Track your own count.
10. Due-diligence checklist (run before every trade)
- Is the calibrated probability ≥ my Settings threshold?
- Is the after-fees R/R ≥ my Settings threshold?
- Is the spread < 1% of price? (Open the ticker in Robinhood and look.)
- Is there a known earnings, FDA, or macro event inside my hold window? If yes, skip.
- Will the trade put me over the PDT count?
- Is the dollar risk ≤ 1% of total liquid net worth? (Ignore the 25 USD default if your real budget is smaller.)
- Have I had two stops in a row today? If yes, stop trading for the day.
- Did I read the playbook's steps in full and understand each one?
11. Glossary
- ATR
- Average True Range: typical bar-to-bar movement; the basis for stop distance.
- R/R
- Reward-to-risk: target distance divided by risk distance, after fees.
- Conviction
- Composite score combining direction strength, agent agreement, and coverage.
- Calibrated probability
- The raw probability adjusted by the engine's actual historical hit-rate.
- Regime
- A classification of current market behavior (trending up/down, range, high-vol, etc.).
- Veto
- A hard rule that disqualifies a signal regardless of score (e.g. liquidity, halts).
- Slippage
- Difference between the price you saw and the price you got filled at.
- Half-Kelly
- Half of the Kelly-criterion size: a defensive scaling that survives bad streaks.
- EOD
- End-of-day: the regular-session 4 p.m. ET close.
- PDT
- Pattern Day Trader: FINRA designation that restricts day-trading on small accounts.
12. Disclaimer
marketXED is software, not financial advice. Nothing displayed in this app, including signals, playbooks, conviction scores, calibrated probabilities, or copilot answers, constitutes a recommendation to buy, sell, or hold any security. Past performance of the engine, of any agent, or of any historical trade does not predict future performance. Trading equities, options, and other instruments involves substantial risk of loss and is not suitable for every investor.
You are solely responsible for your investment decisions, your risk management, your tax obligations, and your compliance with the rules of your broker, your jurisdiction, and your regulator. By using this app you acknowledge that the authors and operators accept no liability for any direct, indirect, incidental, or consequential damages arising from its use.
If you are unsure whether trading is right for you, consult a licensed, fee-only fiduciary advisor before deploying real capital.