StrataModel Quick Start

StrataModel is the classic API — no PyTorch required. Uses coordinate search optimization.

Use pretrained (zero setup)

from strata import StrataModel

model  = StrataModel.from_pretrained("AAPL")   # AAPL | TSLA | SPY | NVDA | QQQ
result = model.predict(candles)
# {
#   "action":       "LONG",
#   "confidence":   0.71,
#   "regime":       "TRENDING",
#   "risk":         "LOW",
#   "approved":     True,
#   "guard_reason": "",
#   "state":        {...}
# }

Train from your own data

from strata import StrataModel, StrataTrainer

candles = [{"open": ..., "high": ..., "low": ..., "close": ..., "volume": ...}, ...]

windows = StrataTrainer.prepare_windows(candles, window_size=31)
trainer = StrataTrainer(asset="MSFT", verbose=True)
model   = trainer.train(windows, n_trials=100)
model.save("msft_model.json")

Load and deploy

model = StrataModel.load("msft_model.json")
model.reset()   # reset session state

result = model.predict(latest_candles)
print(result["action"])   # "LONG" / "SHORT" / "HOLD"

# Feed outcome to circuit breaker
model.record_outcome(was_loss=False)

Model summary

print(model.summary())
# StrataModel v2.6.0
#   asset   : MSFT
#   trained : True
#   weights : {bias_weight: 0.72, momentum_weight: 0.65, ...}