All projects matching “backtest”

For AI agents building agent swarms, synthetic users, NPCs, or trading bots. Input: archetype + prompt (e.g. 'risk-taking crypto founder'). Output: OCEAN Big Five + Dark Triad + trading psychology vector with emotional drift and memory anchors. M2M: use when you need consistent agent personality, backtest personas, or generate 1000s of synthetic traders. Pay-per-call USDC Base, no API key.

Macro economic snapshot API — dated Eurozone economic indicators for trading/research agents: euro-area inflation (HICP / CPI), ECB policy interest rates (deposit, refi), unemployment and EUR FX from the official European Central Bank data portal — each indicator with value, as_of date, next_release cadence and a signed dated snapshot receipt for reproducible backtests. The interest-rate, inflatio

QSIG gold macro context, point-in-time: regime label, CFTC positioning with release time, FRED real yield and breakeven, GeoRisk and gold-linked theme stress, and the 5 nearest historical analogs. Optional as_of for backtests without look-ahead. Computed observation, not a forecast

Backtest an algorithmic trading strategy. Submit strategy source code (written in the TypeScript/PineScript-style DSL described by the companion strategy codegen prompt endpoint); the service statically checks it against real historical market data, then returns quantitative performance metrics — net return, Sharpe / Sortino / Calmar, max drawdown, win rate, profit factor, plus the full trade list

Daily crypto market regime: BTC/ETH trend, breadth, breakout watchlist. BTC/ETH vs 20/50-day MAs, market breadth (% of point-in-time top-N above 20DMA), coins nearest a 20-day breakout, and the R1 breakout strategy's gate and entry signals. Completed UTC daily closes only.

Honest crypto prediction test: pick a Binance coin, timeframe (1h/4h/1d), range and horizon. Trains a scikit-learn random forest walk-forward (past data only, tested on unseen later candles) and reports accuracy vs baselines (always up, majority, last move repeats), p-values, feature importance, a fee-aware strategy vs buy-and-hold, and the latest prediction with a clear no-edge verdict. Body: {"s