How the EV Scanner Works
Understanding signals, edge, and AI probability estimates
The EV Scanner is the core intelligence tool in Predite. It continuously monitors prediction markets across Polymarket and Kalshi (Pro plan and above) to identify opportunities where the market price diverges meaningfully from estimated true probability.
This document covers how the scanner works under the hood, how to interpret its output, and how to integrate it into your trading workflow.
## What the Scanner Actually Does
Every 4 hours, our infrastructure:
1. Fetches the current list of active markets from Polymarket (and Kalshi for Pro plan) 2. Pulls orderbook data, volume, liquidity, and recent price action 3. Sends market questions and context through our 3-model AI consensus engine 4. Computes expected value for each potential position 5. Ranks markets by absolute edge size 6. Filters out markets that fail liquidity, freshness, or quality checks 7. Updates the scanner UI with the latest ranked list
You see the results in the scanner table, sortable by any column.
## Reading the Scanner Table
The default columns are:
## What Edge Sizes Mean
Based on backtesting and real-world experience:
## What Confidence Means
The AI provides a confidence level alongside its estimate:
For most trades, target signals with confidence >70%. Below that, you're amplifying AI's uncertainty.
## Filtering and Sorting
The scanner supports several filters:
- **Minimum edge**: hide markets below your edge threshold (default 5pp)
- •**Minimum volume**: require at least $X 24h volume (default $10k)
- •**Maximum days to resolution**: skip markets resolving too far in the future
- •**Category**: politics, sports, crypto, economics, entertainment
- •**Platform**: Polymarket, Kalshi, or both
Sort by:
- •Edge (highest first) — default
- •Volume (most liquid first)
- •Confidence (highest first)
- •Resolution time (sooner first)
## Common Scanner Patterns
After using the scanner for a while, you'll notice patterns:
## How to Use Scanner Output
A reasonable workflow:
1. Open scanner first thing in the trading day 2. Filter for >5pp edge, >70% confidence, >$10k volume 3. Read top 10-15 results 4. Pick 2-3 that interest you (you can articulate WHY there's edge) 5. Click into each for full AI reasoning + market context 6. Verify resolution criteria, recent news, liquidity 7. If still convinced, place trade with appropriate sizing 8. Track each trade in your journal
This takes about 20-30 minutes daily. After 100+ trades using this workflow, you'll know whether your edge identification is accurate enough to compound.
## Limitations to Know
The scanner is a starting filter, not a magic oracle:
- **AI estimates have variance**. Same question asked twice might get slightly different probabilities. Don't chase tiny edges.
- •**Training data has cutoffs**. AI doesn't know what happened in the last 24 hours unless we explicitly feed it news.
- •**Edge isn't guaranteed**. A 10pp edge signal can lose money. Variance is real.
- •**Past performance ≠ future**. Signals that worked last month might not work this month due to regime change.
Always verify scanner output with your own analysis. The scanner saves you time by filtering thousands of markets to a manageable list — but YOU make the final trade decision.
## Customization for Power Users
Pro and Bot plan users can:
- •Save custom filter presets
- •Set alerts when specific market types hit edge thresholds
- •Export scanner data via API
- •Backtest strategy ideas against historical scanner output
## Related Docs
- [AI Probability Engine](/docs/ai-probability)
- •[Reading Signals](/docs/reading-signals)
- •[Paper Trading](/docs/paper-trading)
- •[Bot Strategies](/docs/bot-strategies)