Back to AI architectures leaderboard
hobby Color polygraph · architecture detail Best gender AUC, 2026

LightGBM + perceptual features

Same single LightGBM configuration as the Single-LGB baseline, but with 33 extra perceptually-aware features bolted on to the existing 441-feature vector. The new features are mostly LAB-space encodings and gender-prototype distances. One single tree-of-trees beats the full stacked ensemble on gender AUC with this feature set.

Scores

Gender AUC
0.878
+0.002 vs 441-feature single LGB
Age MAE
6.92
-0.03 vs 441-feature single LGB
Mood MAE
8.87
+0.02 vs 441-feature single LGB

Why this is on the leaderboard

The original 441-feature vector encodes colours in RGB and HSL. Neither of those is perceptually uniform - two colours that look equally different to a human can sit at very different distances in the model's input. LAB fixes that, and gradient-boosted trees cannot construct a non-linear sRGB-to-LAB transform from axis-aligned splits, so the new encoding genuinely adds information the model could not infer.

On top of LAB I added a "gender prototype" distance: take a handful of stereotypically girl-coded colours (light pink, hot pink, light purple, red) and boy-coded colours (bright blue, sky blue, green, dark gray), average each set in LAB, and compute Delta-E from the user's picks to each prototype centroid. This is the kind of prior knowledge a tree cannot invent on its own, even from rich features.

The 33 new features

Five blocks of features, all added to the base 441-vector:

Which new features actually matter

Gain-based importance from a full-data LightGBM fit on gender. Ranks are out of all 474 features. Star marks new ones.

Rank Feature Gain Note
★ 1r1_lab_b_std10,689blue-yellow spread across r1 picks
2sel_r1_dr4,045r1 mean red - offered mean red
★ 3r1_to_girl_proto_mean3,234mean Delta-E from r1 to girl-prototype
★ 4r1_relative_decisive_mean3,102decisiveness / group difficulty
5r1_l_mean2,769r1 mean lightness (HSL)
★ 10off_lab_b_std997offered colours b* spread
★ 17r1_relative_decisive_std661variability of relative decisiveness
★ 20r1_lab_L_mean618r1 mean lightness (LAB)

Five of the top 20 features are new, including the single highest-gain feature across all 474. r1_lab_b_std is interesting: it captures how much the user's 16 round-1 picks vary along the blue-yellow axis. A small std means the user stayed on one side of the b* spectrum - i.e. consistently "blue-ish" or consistently "pink/yellow-ish" - which is exactly the perceptual signal the gender task is trying to extract.

Less interesting: the single-colour LAB features for the final pick (final_lab_L, final_lab_a, final_lab_b) all land outside the top 350. The redundancy with existing final_h, final_s, final_l features is too high to add much. The aggregates and the prototype distances are where the gains actually live.

Configuration

Project links

Back to AI architectures leaderboard