TradeWell’s ten prediction horizons
Searching for TradeWell ten horizons, AI stock prediction time horizons, or 1D 3D 1W 2W 1M 3M 6M 1Y 3Y 5Y stock scores? TradeWell does not publish one blended rating. Each covered stock gets a separate TW Quant Score, expected return, and model-implied price target for each of ten forecast windows, refreshed daily.
TW Quant Score is research, not investment advice. It is not a guarantee of future performance and does not tell you what to buy or sell. Nothing on this page is a live price, score, or return — see the current numbers in the app. TradeWell does not publish fabricated win-rate or IC figures as product claims.
The ten windows
Every horizon answers a different research question. Scores are not normalized across windows — a 1-day rank and a 5-year rank are not the same number on a stretched scale.
| Horizon | Window | What the score is for |
|---|---|---|
| 1D | 1 trading day | Next-session research: the shortest published forecast window. |
| 3D | 3 trading days | A few sessions out — still short-horizon, not a weekly thesis. |
| 1W | 1 week | This week’s research question, scored independently of 1D and 1M. |
| 2W | 2 weeks | A two-week window between weekly setup and a one-month swing. |
| 1M | 1 month | A one-month holding-period research score, not a mash-up of 1W and 3M. |
| 3M | 3 months | Quarter-scale research. A strong 3M rank does not imply a strong 1Y rank. |
| 6M | 6 months | A half-year thesis window between swing and one-year forecasts. |
| 1Y | 1 year | The one-year board. Often the default view in the product — still one of ten, not the blend. |
| 3Y | 3 years | A multi-year research window. Separate model output from 1Y and 5Y. |
| 5Y | 5 years | The longest published horizon. Not a stretched 1Y score. |
Why scores are not comparable across horizons
A ticker can sit near the top of the 1D list and mid-pack on 5Y, or the reverse. That disagreement is the point. Flattening ten windows into one “AI score” would hide which question the number actually answers.
Each horizon carries its own TW Quant Score, expected return, and model-implied price target. See what the TW Quant Score is and how to screen stocks by time horizon.
How ranking accuracy is measured
Live rankers are evaluated on NDCG@30 (normalized discounted cumulative gain at thirty) for that horizon. When the evaluated list is shorter than 30 names, the product reports NDCG@20. NDCG@10 remains a secondary diagnostic, not the live ranking-accuracy headline. TradeWell does not invent win rates, hit rates, or IC percentages as product claims. Full walkthrough: how TradeWell accuracy is measured.
TradeWell ten horizons — FAQ
- What are TradeWell’s ten prediction horizons?
- 1D, 3D, 1W, 2W, 1M, 3M, 6M, 1Y, 3Y, and 5Y. Each stock receives a separate TW Quant Score, expected return, and model-implied price target per window, refreshed daily.
- Are TW Quant Scores normalized across time horizons?
- No. Scores are horizon-specific and are not normalized, averaged, or blended across windows.
- How is TradeWell ranking accuracy measured?
- Live rankers are evaluated on NDCG@30. When the evaluated list is shorter than 30 names, the product reports NDCG@20. NDCG@10 is secondary. Fabricated win-rate or IC figures are not product claims.
- Is TradeWell investment advice?
- No. TradeWell publishes research scores and forecasts, not investment advice, and does not tell users what to buy or sell.
Read more: methodology · TW Quant Score · how accuracy is measured · horizon screener · AI stock predictor · research library.