An official website of the United States government
What is the Human Mobility in a New City: Transfer Mobility Knowledge Across Cities
More Like this
-
Transformer-based models are popular for time series forecasting and spatiotemporal prediction due to their ability to infer semantic correlations in long sequences. However, for human mobility prediction, temporal correlations, such as location patterns at the same time on previous days or weeks, are essential. While positional encodings help retain order, the self-attention mechanism causes a loss of temporal detail. To validate this claim, we used a simple approach in the 2nd ACM SIGSPATIAL Human Mobility Prediction Challenge, predicting locations based on past patterns weighted by reliability scores for missing data. Our simple approach was among the top 10 competitors and significantly outperformed the Transformer-based model that won the 2023 challenge.more » « less
-
We conceptualize and measure upward mobility over income or wealth. At the core of our exercise is the Growth Progressivity Axiom: transfers of instantaneous growth rates from relatively rich to poor individuals increases upward mobility. This axiom, along with mild auxiliary restrictions, identifies an “upward mobility kernel” with a single free parameter, in which mobility is linear in individual growth rates, with geometrically declining weights on baseline incomes. We extend this kernel to trajectories over intervals. The analysis delivers an upward mobility index that does not rely on panel data. That significantly expands our analytical scope to data-poor settings. (JEL D31, D63, I32, O15, O40)more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- https://doi.org/10.1145/3366423.3380210
