More history sounds safer: more examples, less estimation noise. In markets, old examples can also teach relationships that no longer transfer. Chalvatzis holds one cross-sectional Transformer and one 572-feature library fixed, then changes only which months enter training. The answer is not “use more data.” It depends on how far ahead the prediction reaches.
The paper's sharper warning sits in the appendix. The retrospectively best individual configuration changes at all 8 forecast horizons between 2025 and 2026. A clean full-period winner table is therefore a map of this backtest, not a stable rule for the next one.
What the score measures
At each forecast origin, the model ranks stocks. Rank IC is the Spearman correlation between that ranking and the ranking of future returns: +1 means perfect ordering, 0 means no monotone relationship. The target is a future five-factor residual return—the part left after removing common market, size, value, profitability, and investment factor exposure. Scores are averaged within sessions and then across 451 sessions, so a reported 1.90% means correlation 0.019, not a 1.90% return.
Recent data win quickly, then run out of road
R6, R12, and R24 sample respectively 6, 12, or 24 months with a recency preference from widening historical pools. R6 reaches 1.90% Rank IC at five minutes, but falls to 0.32% at 120 minutes; R24 rises above it at the long end. The TypeScript core feeds the exact paper-reported rows to this chart.
The ensemble wins three columns, not the argument
Averaging all twelve forecasts beats every individual point estimate at 15, 20, and 25 minutes. At the other five horizons it dilutes a stronger model. The calculation below is deliberately signed: positive means the ensemble wins; negative means the best individual wins.
def ensemble_gaps(rows, ensemble_name):
ensemble = next(row for row in rows if row.name == ensemble_name)
individuals = [row for row in rows if row.name != ensemble_name]
gaps = []
for horizon in range(len(ensemble.values)):
best = max(row.values[horizon] for row in individuals)
gaps.append(ensemble.values[horizon] - best)
return gaps| Horizon | Full best | Best IC % | Ensemble % | Ens. gap | 2025 best | 2026 best |
|---|---|---|---|---|---|---|
| 5m | R6 | 1.90 | 1.53 | -0.37 | R6 | U24 |
| 10m | R6 | 1.57 | 1.45 | -0.12 | M6 | C6 |
| 15m | R6 | 1.00 | 1.10 | +0.10 | C12 | U24 |
| 20m | M12 | 1.26 | 1.31 | +0.05 | M6 | M12 |
| 25m | M24 | 1.08 | 1.17 | +0.09 | U12 | M24 |
| 30m | M24 | 1.09 | 0.98 | -0.11 | U12 | M24 |
| 60m | U24 | 0.87 | 0.81 | -0.06 | U12 | U24 |
| 120m | U12 | 0.76 | 0.63 | -0.13 | U12 | M24 |
A full-period mean hides the regime break
The equal ensemble's 5-minute IC is 3.72% in the first half of 2025 and 1.01% in 2026 through 20 October: only 27% of the earlier score remains. Retention is below one at every horizon. That does not prove “alpha decay”— market conditions, stock coverage, labels, and sampling noise can all move the estimate—but it does defeat any claim of stable superiority.
Why the horizon story remains an association
Each policy changes more than “freshness.” Wider training quantities also widen the eligible historical pool; sampled policies change month composition and validation behavior. The data are proprietary intraday US equity records, the architecture is fixed, and transaction costs are not the evaluation target. Rank IC says whether the ordering contains signal, not whether latency, turnover, spreads, and market impact leave a tradeable strategy.
What to probe next
Pre-register a history-selection rule using only past months, then compare it with fixed R6, U24, and equal-ensemble baselines in a nested walk-forward test. Report paired monthly uncertainty, turnover, and net returns. Most importantly, treat history length as a time-varying policy choice whose own selection can overfit—not as another row to maximize on the final table.
The site's Transformer page exposes the attention computation used by the model family; the linearpage helps unpack rank correlation's covariance logic. This paper's lesson lives one level above architecture: what the model is allowed to remember.
References
- Chalvatzis, C. (2026). Which Past Matters? Training History and Multi-Forecast Horizon in Equity Transformers. arXiv:2611.23126 [q-fin.ST]
- Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems 30