← All tasks
T09 · Mean Reversion

Deep Learning Statistical Arbitrage

Jorge Guijarro-Ordonez et al. (3 authors), 2025 · Management Science

0%
pass@1 across 16 systems
0/16
systems with ≥1 successful attempt
0/5
no system produced a successful attempt
80 attempts · 16 systems × 5
Claude Code + Opus 5
0%
Claude Code + Opus 4.8
0%
Claude Code + Opus 4.7
0%
Codex + GPT-5.6-sol
0%
Codex + GPT-5.5
0%
OpenCode + Kimi-K3
0%
OpenCode + Opus 4.7
0%
OpenCode + GPT-5.5
0%
OpenCode + Sonnet 4.6
0%
OpenCode + Qwen3.7-Max
0%
OpenCode + GLM-5.2
0%
OpenCode + DeepSeek V4-Pro
0%
OpenCode + GLM-5.1
0%
OpenCode + Qwen 3.6 Plus
0%
OpenCode + MiniMax-M3
0%
OpenCode + MiniMax M2.7
0%
all checkers pass Type-A clean, Type-B fail fail checking timeout no result / incomplete
Strategy

What the paper asks for.

Construct daily arbitrage portfolios as IPCA-style residuals against conditional latent factors built from firm characteristics, feed a 30-day cumulative-residual window through a CNN+Transformer to extract a per-stock signal, then map signals to long-short allocation weights with an FFN allocator trained jointly to maximize risk-adjusted returns under a unit L1-leverage constraint; daily rebalanced.

Type
ml
Implementation
torch
Rebalance
daily
Long-short
yes
Declared task setup
Data
One-command fetcher for WRDS-sourced task data
Operational scope
Use a reduced liquid-stock universe, executable IPCA-style residualization, and an initial-period fitted model within the benchmark compute envelope.
Six-stage quantitative strategy pipeline
  1. 01 Data loading
  2. 02 Feature engineering
  3. 03 Model fitting
  4. 04 Signal generation
  5. 05 Portfolio construction
  6. 06 Execution
Checker suite

15 properties · 80 attempts.

Each row is one requirement the strategy must satisfy. The bar reports the share of observed checker verdicts that pass; missing checker output is not converted into a property verdict.

TYPE A · DOMAIN-LEVEL (7)
  • A2
    no global normalize
    stage · feature eng
    44/76
  • A3
    no future data access
    stage · signal gen
    53/76
  • A4
    causal consistency
    stage · execution
    59/76
  • A5
    no survivorship bias
    stage · data loading
    70/76
  • A6
    train test temporal order
    stage · model fit
    44/76
  • A9
    signal delay test
    stage · execution
    64/76
  • A10
    e2e metric consistency
    3/76
TYPE B · PAPER-SPECIFIC (8)
  • B1
    lookback window l 30
    §§III.D / §IV “The trading signal is based on a local lookback window of L = 30 days.”
    provenance · paper-explicit
    stage · feature eng
    27/76
  • B2
    weight normalization l1 unit
    §§III “the absolute values of the individual stock portfolio weights sums up to one, i.e. we use the normalization ||ω_t||_1 = 1.”
    provenance · paper-explicit
    stage · portfolio
    40/76
  • B3
    rebalance frequency daily
    §§III / §IV “outputs the predicted optimal allocation weight for that residual for the next time ... Our main models estimate arbitrage strategies”
    provenance · paper-explicit
    stage · execution
    44/76
  • B4
    oos period 2002 2016
    §§IV “out-of-sample trading performance from January 2002 to December 2016 as we use the first four years to estimate the signal and allocation function.”
    provenance · paper-explicit
    stage · data loading
    4/76
  • B5
    universe top liquid us
    §§IV.A “roughly the 550 largest and most liquid stocks in the U.S. from 1998 to 2016”
    provenance · benchmark-specified
    stage · data loading
    69/76
  • B6
    ffn allocation after signal
    §§III.E “We use a flexible feedforward neural network for the allocation function”
    provenance · paper-explicit
    stage · model fit
    64/76
  • B7
    input is cumulative residuals
    §§III.D “The input to the signal extraction functions are the last L cumulative residuals.”
    provenance · paper-explicit
    stage · feature eng
    31/76
  • B8
    weights continuous not discretized
    §§III.C “The allocation function w^ε can be a complex nonlinear function ... outputs the predicted optimal allocation weight”
    provenance · paper-explicit
    stage · portfolio
    50/76
What this task reveals

The lowest-passing observed requirement is e2e metric consistency: 3 of 76 observed checker verdicts pass. The full property list above shows whether errors concentrate in domain-level validity or the paper-specific strategy logic.