Back to Community

XGBoost vs LightGBM for alpha generation

QUQuantDev42
Jan 18, 2026
2,614 views
15 posts
strategy
machine-learning
gradient-boosting

Both XGBoost and LightGBM are popular choices. My experiments show:

  • LightGBM: 2-3x faster training, similar accuracy, better with categorical features
  • XGBoost: More robust to hyperparameter choices, slightly better on small datasets
For the current competition datasets (300K+ rows), LightGBM wins on training speed without sacrificing performance.

14 Replies

7
MIMicroAlphaFeb 1, 2026

Thanks for sharing! This is exactly the kind of insight that helps the community grow. Bookmarking this thread.

15
NEnewbie_trader6d ago

Can confirm this approach works. I implemented something similar and jumped from rank 150 to rank 23 in two weeks.

11
NEnewbie_trader1d ago

Have you considered using PCA to reduce the dimensionality of the feature space? I found that the first 10 components capture 80%+ of the variance.

10
BABayesianBull1d ago

For factor models, I'd strongly recommend the Fama-French 5-factor model as a starting point. It captures most systematic risk.

8
MIMicroAlphaFeb 2, 2026

I think the platform should add a paper trading mode so we can test strategies in a more realistic setting between competitions.

32
COCovarianceKidFeb 24, 2026

Can confirm this approach works. I implemented something similar and jumped from rank 150 to rank 23 in two weeks.

32
RERegimeDetectorFeb 12, 2026

Turnover control is crucial. My best performing model has a turnover of only 8% daily. High turnover strategies rarely survive transaction costs.

16
RIRiskQuantFeb 22, 2026

For those new to the platform: start with the tutorial competition. It has a smaller dataset and more forgiving scoring.

6
BABayesianBullJan 31, 2026

Has anyone tried using attention mechanisms for this? The temporal attention weights could tell you which historical periods are most relevant.

2
BABayesianBullFeb 2, 2026

Interesting thread! I've been exploring reinforcement learning for portfolio allocation. The challenge is defining the right reward function.

Post a Reply