MarketPawns Docs

Appearance

MarketPawns — Lite Paper ​

Version: 1.0
A concise investor-friendly version based on the implemented MarketPawns architecture and white paper v1.4

1. Executive Thesis ​

MarketPawns is a trading and analytics ecosystem that combines formalized market geometry, AI-based probability assessment, a mathematical EV filter, and community mechanics around the internal PAWN-COIN economy.

The project is built on a simple premise: trading decisions should not rely on intuition, but on formalized structures, probabilistic assessment, and strict risk control.

2. The Problem ​

Retail and semi-professional trading is structurally limited by three weaknesses:

  • Subjectivity: decisions are often driven by emotion rather than mathematically verifiable scenarios.
  • Static algorithms: classical automated systems adapt poorly to changing market context.
  • Weak trade lifecycle control: many systems do not re-evaluate a position at each critical stage after entry.

MarketPawns addresses this through continuous position re-evaluation at key levels and decision filtering through the Expected Value (EV) metric.

3. How MarketPawns Works ​

3.1. Market Models Instead of Noisy Signals ​

The analytical core does not rely on a conventional indicator stack. It works with structural market models. Each model is formalized through:

  • price-movement geometry;
  • price/time proportions;
  • calculated levels;
  • a large feature set describing context.

The MarketPawns database already aggregates many millions of such models across instruments and timeframes.

3.2. AI as a Probabilistic Layer, Not a "Black Box" ​

The system uses an ensemble of specialized AI models. These models do not place trades directly; they estimate the probabilities of specific outcomes:

  • reversal;
  • target achievement;
  • scenario continuation;
  • trade exhaustion.

The AI output is then integrated into a mathematical decision layer.

3.3. EV Filter as the Final Gate ​

The final trading action passes through the Expected Value filter:

EV = P(win) × Profit − P(loss) × Risk

In practical terms:

  • if EV > 0, a signal may be executed;
  • if market context changes and EV turns negative, the position may be closed algorithmically;
  • risk is not handled rhetorically, but through formula-driven sizing and controlled downside.

4. Trade Lifecycle ​

The system re-evaluates a position not only at entry, but at subsequent key stages:

  • entry;
  • intermediate target (bumper);
  • pullback to entry;
  • first major target.

This creates a multi-level control loop in which the decision to continue or close the trade is updated as the scenario evolves.

5. Product Infrastructure ​

MarketPawns is described as an implemented architecture that already includes:

  • independent trading agents;
  • distributed Python workers for AI processing;
  • MT4 and MT5 support;
  • web monitoring of agents, balances, and orders;
  • auditable decision history through EV snapshots;
  • local buffering designed to protect command flow during temporary connection issues.

This means the project is not built around concept alone, but around an existing applied technology stack.

6. Ecosystem Layer ​

MarketPawns is evolving not as a single trading bot, but as an interconnected ecosystem:

  • core analytics platform with market models and AI-driven signals;
  • Sandbox for visual analysis and hypothesis testing without real capital;
  • Prediction Markets / Backed Forecasts for community participation;
  • community layer for idea exchange, analytics, and reputation growth.

This structure combines trading technology, research tooling, and a community-driven growth loop.

7. PAWN-COIN and the Ecosystem Economy ​

PAWN-COIN is the base unit of account of the internal MarketPawns economy.

In the current architecture, the token is already connected to real platform activity through a shared market-settlement contour and supporting layers:

  • Community Wall: a user places a stake on a forecast based on a model, and that stake is settled under the same scheme as Prediction Markets; stake size affects both the staker reputation coefficient and the model's position in the Community Pool.
  • Prediction Markets: users play against each other, while a fee is charged only on winnings and routed into a separate fee pool.
  • Reward bank: fed by 50% of the fee pool from Prediction Markets, then distributed proportionally among successful stakers based on stake size.
  • Supporting utility: contribution rewards and the Expert Follow System, where a user holds PAWN to access forecasters from the required reputation tier, copies their bets, and on a winning copied bet pays a surcharge on top of the fee in favor of the forecaster, complement the core loops but do not replace them as the source of long-term economic demand.

The key investment thesis is that PAWN-COIN is positioned not as an abstract speculative token, but as the internal economic interface through which risk-based participation, fee-based value capture, reputation, and token-gated access to stronger forecasters are aligned inside the MarketPawns ecosystem.

8. Why the Trust Layer Matters ​

Trust in MarketPawns is meant to be built not only on narrative, but on verifiability:

  • AI models are tied to historical data and attestation metrics;
  • trading decisions pass through a formalized EV filter;
  • EV snapshot history makes decisions auditable;
  • internal prediction markets are resolved algorithmically rather than manually.

For algorithmic trading and a future tokenized ecosystem, this is critical: transparency is part of the product layer, not just the marketing layer.

9. Current Stage of Development ​

According to the current roadmap:

  • Phase 1 — implemented: core database, AI layer, EV filter, risk management, infrastructure, and MT4/MT5 integrations are in place.
  • Phase 2 — current stage: community scaling, deeper engagement in Prediction Markets, development of the Community Wall, new strategies, and expansion of token utility.
  • Phase 3 — planned: launch of the Expert Follow System, conversion of PAWN-COIN into a public crypto asset, and expansion of the economic layer built on the platform's validated product loops.

This positions the project as an infrastructure layer that already has a product foundation and is moving toward a broader crypto-economic form.

10. Investment Thesis ​

MarketPawns can be viewed as a combination of three value layers:

  1. Trading Infrastructure Value — an applied architecture for formalized algorithmic decision-making.
  2. Data & AI Value — a large corpus of structural market models, an AI ensemble, and a probabilistic classification system.
  3. Tokenized Ecosystem Value — the internal PAWN-COIN economy tied to Community Wall, Prediction Markets, the reward bank, contribution, reputation, and future tokenization.

If the project continues converting its technical core into a growing product and community ecosystem, and the two base loops are confirmed in the live product, PAWN-COIN can evolve into an economic layer for liquidity, participation, network effects, and the Expert Follow System inside MarketPawns.

11. Further Reading ​

This lite paper is a condensed overview.

For the full description of the architecture, tokenomics, and roadmap, refer to:

Built with VitePress for MarketPawns documentation.

Copyright © 2026 MarketPawns