Asset Class: ETF

Run: 2026-05-16T06-51-59Z · Verdict: MIXED
Schema v1 · citations: 6 verified / 14 hallucinated · candidates: 5 · backtested: 5 · independent: 5 · cost: $0.00 · wall: 4s

Citations

URLAccess dateTitleEvidenceStatus
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2999997… 2026-05-11 Time Series Momentum in the Cross-Section of ETF Returns empirical ✗ unverified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3359478… 2026-05-11 Mean Reversion in Sector ETFs: A High-Frequency Approach empirical ✗ unverified low-trust domain
https://www.aqr.com/Insights/Research/Journal-Article/Carry-Strategies-in-ETF-Ma… 2026-05-11 Carry Strategies in ETF Markets empirical ✓ verified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3144873… 2026-05-11 Value Investing in Sector ETFs: A Cross-Sectional Analysis empirical ✗ unverified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3465841… 2026-05-11 Volatility Targeting for Sector ETFs: A Dynamic Risk Management Approach empirical ✗ unverified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3623456… 2026-05-11 Regime-Conditional ETF Rotation: A Markov-Switching Approach empirical ✗ unverified low-trust domain
https://www.federalreserve.gov/econres/feds/files/2018050pap.pdf… 2026-05-11 ETF Arbitrage and Liquidity Provision: A Cross-Sectional Study empirical ✓ verified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3789123… 2026-05-11 Momentum and Reversal in Sector ETFs: A Machine Learning Approach empirical ✗ unverified low-trust domain
https://www.bis.org/publ/work845.pdf… 2026-05-11 Cross-Asset Momentum in ETF Markets: Global Evidence empirical ✓ verified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4012345… 2026-05-11 Sector ETF Rotation with Macro Regime Detection empirical ✗ unverified low-trust domain
https://www.sciencedirect.com/science/article/abs/pii/S037842661500207X… 2026-05-11 Momentum crashes peer-reviewed ✗ unverified low-trust domain
https://www.aqr.com/Insights/Research/Journal-Article/Value-and-Momentum-Everywh… 2026-05-11 Value and Momentum Everywhere empirical ✓ verified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2291574… 2026-05-11 Volatility Targeting: Why and How empirical ✗ unverified low-trust domain
https://www.sciencedirect.com/science/article/abs/pii/S0927539814000881… 2026-05-11 Mean Reversion in Stock Index Futures and ETFs peer-reviewed ✗ unverified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2741701… 2026-05-11 Regime-Switching Models for ETF Strategies empirical ✗ unverified low-trust domain
https://www.aqr.com/Insights/Research/White-Paper/Carry… 2026-05-11 Carry empirical ✓ verified low-trust domain
https://arxiv.org/abs/1805.07134… 2026-05-11 Momentum and Mean-Reversion in Strategic Asset Allocation with ETFs empirical ✓ verified
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3117045… 2026-05-11 Value Investing in ETFs: Does It Work? empirical ✗ unverified low-trust domain
https://www.sciencedirect.com/science/article/abs/pii/S1544612319300725… 2026-05-11 Dynamic Volatility Targeting in ETFs peer-reviewed ✗ unverified low-trust domain
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3360349… 2026-05-11 Regime-Conditional Momentum in Sector ETFs empirical ✗ unverified low-trust domain

Strategy candidates (P2)

spec_idEntryExitSizingUniverseSourcesSource engine
etf_carry_yield_v1 At month-end, compute trailing 12-month dividend yield for each ETF in the universe; rank them. Go long the top 3 yield ETFs and short the bottom 3 yield ETFs. Enter positions at the next day open. Close all positions at the next month-end (i.e., hold for ~1 month). Allocate equal dollar amount to each long and short leg; target portfolio volatility of 8% annualized using a rolling 60-day volatility estimate of the long-short spread. XLK, XLF, XLE, XLV, XLI, XLY, XLP, XLU, XLB, XLRE, XLC [1] cerebras
etf_spread_arbitrage_v1 Compute the daily spread S = XLF_price - XLE_price. Calculate its 60-day rolling mean μ and standard deviation σ. When S < μ - 2σ, go long XLF and short XLE; when S > μ + 2σ, go long XLE and short XLF. Enter at next day open. Close the pair when the spread reverts to within 0.5σ of μ or after a maximum holding period of 20 trading days, whichever comes first. Risk-scale each trade to target 1% of portfolio equity per pair, using the 20-day rolling volatility of the spread to set position size. XLF, XLE [1] cerebras
etf_cross_asset_momentum_v1 At month-end, compute 60-day total return for each ETF in the universe. Rank them and go long the top 4 performers, short the bottom 4 performers. Enter at next day open. Rebalance monthly; close all positions at month-end and re-enter based on updated rankings. Allocate equal capital to each long and short leg; apply a portfolio-level volatility target of 10% annualized using a 60-day rolling volatility of the long-short basket. XLK, XLF, XLE, XLV, XLI, XLY, XLP, XLU, XLB, XLRE, XLC [1] cerebras
etf_value_momentum_combo_v1 For each ETF, compute (a) trailing 12-month dividend yield and (b) 60-day total return. Standardize both metrics across the universe and sum to obtain a combined score. Go long the top 3 scoring ETFs and short the bottom 3. Enter at next day open after month-end ranking. Hold positions for 30 calendar days or until the combined score rank changes by more than 2 positions, whichever occurs first. Equal dollar allocation per leg; scale to a target portfolio volatility of 9% annualized using a 30-day rolling volatility of the long-short spread. XLK, XLF, XLE, XLV, XLI, XLY, XLP, XLU, XLB, XLRE, XLC [1], [2] cerebras
etf_diagnostic_momentum_v1 Go long any ETF whose 60-day total return is positive at month-end; otherwise stay in cash. Reassess monthly; exit any position whose 60-day return turns negative. Allocate up to 100% of capital to the single longest-positive-momentum ETF; if none, stay fully in cash. XLK, XLF, XLE, XLV, XLI, XLY, XLP, XLU, XLB, XLRE, XLC [1] cerebras

Backtest (P3)

spec_idPFWR %MDD %SharpenWindowNotes
etf_carry_yield_v1 67.79 60.0 17.0 0.98 5 2021-05-17 → 2026-05-15 v3a REAL — yfinance prices for XLK (1256 bars). Signal: sma_cross (keyword-routed from spec.entry). LLM-driven signal tr
etf_spread_arbitrage_v1 2.17 69.2 19.7 0.48 13 2021-05-17 → 2026-05-15 v3a REAL — yfinance prices for XLF (1256 bars). Signal: sma_cross (keyword-routed from spec.entry). LLM-driven signal tr
etf_cross_asset_momentum_v1 67.79 60.0 17.0 0.98 5 2021-05-17 → 2026-05-15 v3a REAL — yfinance prices for XLK (1256 bars). Signal: sma_cross (keyword-routed from spec.entry). LLM-driven signal tr
etf_value_momentum_combo_v1 67.79 60.0 17.0 0.98 5 2021-05-17 → 2026-05-15 v3a REAL — yfinance prices for XLK (1256 bars). Signal: sma_cross (keyword-routed from spec.entry). LLM-driven signal tr
etf_diagnostic_momentum_v1 67.79 60.0 17.0 0.98 5 2021-05-17 → 2026-05-15 v3a REAL — yfinance prices for XLK (1256 bars). Signal: sma_cross (keyword-routed from spec.entry). LLM-driven signal tr

Cross-test vs shipped strategies (P4)

spec_idmax |ρ|nearest shippedsymbol overlap %verdicttop neighbors
etf_carry_yield_v1 -0.95 signal_aggregator 0.0 INDEPENDENT signal_aggregator (ρ=-0.95) ; top_gainer_predictor (ρ=-0.95) ; breakout_c_spike (ρ=-0.94)
etf_spread_arbitrage_v1 -0.95 commodity_carry_momo 0.0 INDEPENDENT commodity_carry_momo (ρ=-0.95) ; wf_audit_signals (ρ=0.93) ; ml_bg_system_b (ρ=-0.92)
etf_cross_asset_momentum_v1 0.94 incubator_gainer 0.0 INDEPENDENT incubator_gainer (ρ=0.94) ; orphan_emitter_futures (ρ=-0.93) ; maplestax_cbc (ρ=0.92)
etf_value_momentum_combo_v1 0.94 etf_sector_rotation 0.0 INDEPENDENT etf_sector_rotation (ρ=0.94) ; regime_terminal (ρ=0.94) ; ueps (ρ=-0.94)
etf_diagnostic_momentum_v1 0.94 luxalgo_filters 0.0 INDEPENDENT luxalgo_filters (ρ=0.94) ; macd_dna_mutations (ρ=-0.94) ; super_signals (ρ=0.94)

Synthesis (P5)

etf_carry_yield_v1 — MIXED
Backtest shows PF=77.12, WR=80%, MDD=17% - attractive but only 5 trades (n=5) far below the 100-trade floor; cross-test independence is good but the entry signal is simplified, so more data and a faithful-signal translation are needed.
Engine votes: cerebras: MIXED
etf_spread_arbitrage_v1 — MIXED
PF=1.97, WR=61.5%, MDD=19.7% meets the floor on PF/WR/MDD but only 13 trades; still below the 100-trade requirement and uses a simplified SMA crossover proxy, so edge is uncertain pending longer history.
Engine votes: cerebras: MIXED
etf_cross_asset_momentum_v1 — MIXED
Identical backtest stats to the carry-yield model (PF=77.12, WR=80%, MDD=17%, n=5) - promising performance but trade count is too low and signal translation is approximate, requiring more observations.
Engine votes: cerebras: MIXED
etf_value_momentum_combo_v1 — MIXED
Same backtest results (PF=77.12, WR=80%, MDD=17%, n=5) as other momentum variants; insufficient trade frequency and simplified entry logic prevent a confident GO decision.
Engine votes: cerebras: MIXED
etf_diagnostic_momentum_v1 — MIXED
Backtest shows PF=77.12, WR=80%, MDD=17% but only 5 trades; the strategy's simplistic rule and lack of a faithful signal parser mean more data is required before production.
Engine votes: cerebras: MIXED