Research Backtest — Python SDK

pip install event-trader

Run a backtest

from event_trader import Client

et = Client(api_key="YOUR_KEY")

run = et.research_backtest.run(
    themes=["defi tokens", "ai tokens"],
    algo_model="aib_sentiment",
    spike_window_hours=24, spike_up_min_pct=5,
    hold_days=2, top_k=12,
)
result = et.research_backtest.get(run["run_id"])
print(result["summary"])           # n_baskets, hit_rate_pct, mean_vs_btc_pct …
for row in result["rows"][:5]:
    print(row["title"], row["direction"], row["vs_btc_pct"])

Themes, models, leaderboard

et.research_backtest.themes()        # selectable themes
et.research_backtest.models()        # algo models (+ experimental caveats)
et.research_backtest.leaderboard()   # ranked runs + launched cards

Launch a Rally Card

out = et.research_backtest.launch_rally_card(run["run_id"], basket_index=0)
print(out["trade_url"])              # $0.99 fee from your balance; signal-only card

Note: algo_model="odiv"/"oboss" are experimental research models — gross signal real, net-of-cost negative. Not tradeable-validated.