CPE Research Program — Paper 16

Beating a 30-Year-Old Strategy at Its Own Game

Time-Series Momentum (TSMOM) is one of the most established, widely used trend-following strategies at systematic funds. Restricting it to only the instruments it can genuinely predict — and changing nothing else about how it trades — beats the standard, unfiltered version. The edge holds up no matter how the 20-year test is sliced.

0.32 vs 0.29
Full-sample Sharpe ratio, filtered vs. standard TSMOM
+0.4%/yr
Average annual edge — essentially unchanged across every test
10 of 10
Different historical splits tested — filtered version wins the average return in every one

What Time-Series Momentum actually does

A real, published strategy (Moskowitz, Ooi & Pedersen, 2012), implemented exactly as described — no tuning, no fitting to this program's own data.

Look back 252 days (~1 trading year) for each instrument Trend up or down? Go long if price rose, short if it fell Size to a fixed volatility target Bigger position when calm, smaller when turbulent Rebalance monthly Repeat every month, for every instrument
Standard TSMOM's mechanism: same four steps, applied identically to every instrument in the universe.

The one change Predictability-Informed TSMOM makes

Not a different signal — the identical TSMOM engine above, pointed at a smaller, pre-screened universe.

12-instrument universe SPY QQQ IWM XLK XLF XLE AAPL MSFT JPM XOM GLD EURUSD=X no filter TSMOM engine 252d trend, vol-sized, monthly rebalance all 12 Standard TSMOM trades all 12 instruments predictability filter (Paper 11) Keep only instruments with a real pocket near the 252-day lookback SPY · IWM · AAPL · MSFT · GLD 5 of 12 Predictability-Informed TSMOM same engine, trades only 5 same unchanged engine, both lanes Compared across 10 historical splits (3–20 blocks)
The only difference between the two strategies is which instruments reach the TSMOM engine — the engine itself (lookback, sizing, rebalance rule) is identical in both lanes.

The edge doesn't depend on how you slice the test

Same 2006–2026 history, same two strategies, re-run by splitting the period into different numbers of equal-length blocks — from 3 large blocks (~6.7 years each) down to 20 small ones (~1 year each). Each point is the average annualized return across that split's blocks.

Standard TSMOM (12 instruments) Predictability-Informed TSMOM (5 instruments)
1.0% 1.4% 1.8% 2.2% ↓ paper's 5-block result 34567810131620 ~6.7yr~5.1yr~4.0yr~3.4yr~2.9yr~2.5yr~2.0yr~1.6yr~1.3yr~1.0yr Number of blocks the 2006–2026 history is split into (block length shown below) Average annualized return per block

The green line sits above the grey line at every block count tested — the gap barely moves whether the 20-year history is cut into 3 pieces or 20. That consistency, not the size of the gap, is the real result: most backtested edges narrow or flip sign under this kind of stress test. This one didn't.

Why this is a meaningful result

TSMOM isn't a toy benchmark — it's a real strategy that systematic funds actually run, published in full detail (Moskowitz, Ooi & Pedersen, 2012) and implemented here with no tuning and no fitting to this program's own data. Improving on it usually means a new signal, a new asset class, or added complexity. Here, nothing about the strategy itself changed — only which five instruments it's allowed to trade, chosen ahead of time using a separate, already-published measurement of each instrument's own predictability structure (Ramanathan, 2026a). The improvement survives being tested ten different ways, with the historical record cut into anywhere from 3 to 20 pieces.

A narrower, secondary result in the same paper: two individual instruments (JPM, XLB) beat standard TSMOM under every real point estimate checked — using each strategy's real average-return difference rather than a regression-based alpha estimate that flips sign on over half the instruments in this program's panel. See the full preprint for that analysis and its caveats.