Antenor Challenge
Most trading models are artifacts of their own backtest. Fit a model hard enough to a decade of Nasdaq data and it will look brilliant, right up to the first live trade. The failure modes are well known and still routinely committed: lookahead leakage, survivorship bias, parameters tuned to the test set, and results reported on the same regime the model was trained on.
The goal of this work was not another signal. It was a trend-identification model for Nasdaq equities whose performance claims could survive hostile scrutiny.
Solution
Antenor developed proprietary models that identify trends in Nasdaq-listed equity markets. We do not disclose how the signals are constructed; the method is the edge. What matters here is how the models were validated, because that is what separates a result from an anecdote:
- Strict temporal separation between the data used to build the models and the data used to judge them.
- Evaluation on genuinely unseen periods, so reported performance reflects what a live deployment would have experienced.
- Explicit controls against the standard sources of self-deception: leakage, overfitting to the evaluation window and cherry-picked reporting.
The methodology passed a bar most models never face: the strategy is offered to the public through Asesores Inteligentes, a supervised automated asset-management platform (roboadvisor) with US-custodied, SIPC-insured accounts. Real capital, real custody and independent supervision are the opposite of a private backtest.
Stack
- Market data pipelines for Nasdaq equities
- Backtesting framework with strict temporal train/test separation
- Statistical validation harness for out-of-sample performance claims
- Signal construction intentionally not disclosed
Results
- The strategy is offered to the public through Asesores Inteligentes, a supervised roboadvisor with SIPC-insured US custody
- Validated with strict out-of-sample discipline designed to make performance claims auditable rather than promotional
- Signal construction kept proprietary; the validation method is what we stand behind
