RSAP-DFM: Regime-Shifting Adaptive Posterior Dynamic Factor Model for Stock Returns Prediction
Abstract
Node classification in heterophilous graphs, where connected nodes often have different characteristics, which presents a significant challenge. We introduce HAPPY, which combines heterophily-aware random walks with targeted subgraph extraction. Our approach enhances Personalized PageRank by incorporating both label and feature diversity into the random walk process. Through theoretical analysis, we demonstrate that HAPPY effectively captures both homophilous and heterophilous relationships. Comprehensive experiments validate our method’s state-of-the-art performance across challenging heterophilous benchmarks.
Cite
Text
Xiang et al. "RSAP-DFM: Regime-Shifting Adaptive Posterior Dynamic Factor Model for Stock Returns Prediction." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/676Markdown
[Xiang et al. "RSAP-DFM: Regime-Shifting Adaptive Posterior Dynamic Factor Model for Stock Returns Prediction." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/xiang2024ijcai-rsap/) doi:10.24963/ijcai.2024/676BibTeX
@inproceedings{xiang2024ijcai-rsap,
title = {{RSAP-DFM: Regime-Shifting Adaptive Posterior Dynamic Factor Model for Stock Returns Prediction}},
author = {Xiang, Quanzhou and Chen, Zhan and Sun, Qi and Jiang, Rujun},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {6116-6124},
doi = {10.24963/ijcai.2024/676},
url = {https://mlanthology.org/ijcai/2024/xiang2024ijcai-rsap/}
}