AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Fairness-Aware Demand Prediction for New Mobility

An Yan, Bill Howe

AAAI 2020 · Learning theory and algorithms › Fairness · approach: Fair allocation and selection · 39 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add region-based fairness (RF) loss with large weight (ablation)FairST · Seattle bikeshareRFG (race): 83.127 -> 8.650Improved
add RF loss with large weight (ablation)FairST · Seattle bikeshareMAE: 0.382 -> 0.460Hurt
add RF loss with small weight (ablation)FairST · Seattle bikeshareMAE: 0.382 -> 0.377Improved
add individual-based fairness (IF) loss (ablation)FairST · RideAustinIFG (race): 54.27 -> 9.47Improved
add IF loss with large weight (ablation)FairST · RideAustinMAE: 0.47 -> 0.52Hurt
add RF loss (ablation)FairST · RideAustinRFG (race): 76.34 -> 0.35Improved
add 1D weather stream to 3D CNN (ablation)3D CNN · Seattle bikeshareMAE: 0.408 -> 0.387Improved
add 2D urban feature stream to 3D CNN (ablation)3D CNN · Seattle bikeshareMAE: 0.408 -> 0.378Improved
add 1D weather stream to 3D CNN (ablation)3D CNN · RideAustinMAE: 0.53 -> 0.48Improved
add both 1D and 2D streams (full FairST, lambda 0) vs 3D CNN + 2D (ablation)3D CNN · Seattle bikeshareMAE: 0.378 -> 0.382No clear effect
use 3D CNN based FairST (lambda 0) instead of ConvLSTMdemand prediction · RideAustinMAE: 0.57 -> 0.47Improved
use RF/IF loss instead of Equal Means or Pairwise lossesFairST · Seattle bikeshareSpearman's rho (race): 0.168 -> near zeroImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy