Find Profitable Polymarket Trades
Screen a large set of prediction market questions for profit opportunities. Binary forecasting produces calibrated probabilities for each question, which you can compare against live market prices to find mispriced contracts.
The workflow has three steps: find questions, forecast them, then compute expected value against live order books. Here, we screen 100 Polymarket questions on politics, AI, and economics for the best risk-adjusted opportunities.
Add FutureSearch to Claude Code if you haven't already:
claude mcp add futuresearch --scope project --transport http https://mcp.futuresearch.ai/mcp
Start by finding questions:
Find 100 interesting prediction market questions on Polymarket where
there might be profit opportunity. Focus on politics, AI, economics,
and geopolitics — skip sports and crypto.
Claude uses FutureSearch's agent tool to research and compile a list of questions. Then forecast them:
Forecast these Polymarket questions.
Claude calls FutureSearch's forecast MCP tool in binary mode:
Tool: futuresearch_forecast
├─ data: [{"question": "Will the Fed cut rates before July 2027?", ...}, ...]
├─ forecast_type: "binary"
└─ context: "These are Polymarket prediction market questions. Forecast the probability of YES resolution."
→ Submitted: 55 rows for probability forecasting.
Session: https://futuresearch.ai/sessions/...
Tool: futuresearch_progress
→ Running: 12/55 complete, 43 running (120s elapsed)
...
Tool: futuresearch_progress
→ Completed: 55/55 (0 failed) in 590s.
Tool: futuresearch_results
→ Saved 55 rows with probability and rationale columns.
Finally, compare against live prices:
Use the Polymarket API to fetch order book data for these markets.
Compute the expected value profit if these forecasts are right,
and sort by annualized ROI.
Claude writes and runs a script that pulls live order book data and computes expected returns.
Add the FutureSearch connector if you haven't already. Then ask Claude in sequence:
Find 100 interesting Polymarket prediction market questions where there might be profit opportunity. Focus on politics, AI, economics, and geopolitics.
Then:
Filter to Polymarket only, then forecast these questions.
Then:
Use the Polymarket API to fetch live order book data and compute expected value profit sorted by annualized ROI.
Go to futuresearch.ai/app and enter:
Find 100 interesting Polymarket prediction market questions where there might be profit opportunity. Focus on politics, AI, economics, and geopolitics.
After the list is compiled, follow up with:
Filter to Polymarket only, then forecast these questions.
pip install futuresearch
export FUTURESEARCH_API_KEY=your_key_here # Get one at futuresearch.ai/app/api-key
import asyncio
import pandas as pd
from futuresearch.ops import forecast, agent_map
# Step 1: Find prediction market questions
# (You can also start from a CSV of questions you've already collected)
questions = pd.DataFrame([
{
"question": "Will the US Federal Reserve cut rates by at least 25bp before July 1, 2027?",
"resolution_criteria": "Resolves YES if the Fed announces at least one rate cut of 25bp or more.",
"polymarket_url": "https://polymarket.com/event/...",
"current_price": 0.62,
},
{
"question": "Will the EU AI Act enforcement begin before January 2027?",
"resolution_criteria": "Resolves YES if EU AI Act enforcement actions are publicly documented.",
"polymarket_url": "https://polymarket.com/event/...",
"current_price": 0.45,
},
# ... more questions
])
async def main():
# Step 2: Forecast all questions
result = await forecast(
input=questions,
forecast_type="binary",
context="These are Polymarket prediction market questions. "
"Forecast the probability of YES resolution.",
)
# Step 3: Compute expected value
df = result.data
df["forecast_price"] = df["probability"] / 100
df["edge"] = df["forecast_price"] - df["current_price"]
df["ev_profit"] = df["edge"].abs() # Simplified; use order book depth for real trading
profitable = df[df["edge"].abs() > 0.05].sort_values("edge", ascending=False)
print(profitable[["question", "current_price", "forecast_price", "edge"]])
asyncio.run(main())
For production use, fetch live order book data from the Polymarket API to compute actual expected returns accounting for available volume and slippage.
FutureSearch forecasted 55 of the 100 questions (the rest were filtered out because they resolved too soon, had too little volume, or were in categories less suited for AI forecasting). Of those 55, 31 had enough liquidity on Polymarket to be worth analyzing.
The results were sorted by annualized ROI — annualizing is important because prediction markets lock up capital until resolution, so a small edge in a market resolving next week is usually better than a large edge in one resolving a year from now.
Even high-quality forecasts aren't enough to trade blindly. The value is in identifying promising markets where additional research is productive. For example, after identifying an FDA approval question as high-expected-value, you could follow up:
Research the FDA approval of Retatrutide further.
Find the 25 most similar drugs, and whether they were approved or not and why.
The most profitable prediction market strategies use research agents to guide human strategy, rather than relying on AI alone. See the full walkthrough in Forecasting Polymarket Questions with AI.
Built with FutureSearch. See the forecast documentation for all parameters and output formats. Related guides: Turn Claude into an Accurate Forecaster, Forecast Outcomes for a List of Entities, Value a Private Company.