Newest papers

Residual Learning in Empirical Asset Pricing

Dexin Peng, Xiaoyu Wang · 2026 · SSRN Electronic Journal

DOI: 10.2139/ssrn.7528558 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Shallow model adalah kasus khusus dari model mendalam, dan model mendalam secara teoritis memiliki potensi untuk melampaui yang datar. Namun, literatur harga aset empiris yang ada memberikan referensi yang kuat untuk model datar. Pembelajaran residual memungkinkan model jaringan saraf dalam harga aset untuk pergi lebih dalam dengan mempertahankan dan memperbaiki rekan-rekan datar mereka. Rasio Sharpe out-of-sample untuk portofolio jangka panjang model residual mendalam yang ditimbang nilai (2.07) lebih tinggi daripada yang untuk model datar yang sesuai (1.92) dan lebih dari dua kali lipat dari model feed forward mendalam (0.89).

Machine translation (Meta M2M100); the English original follows.

Abstract

Shallow models are special cases of deep models, and deep models theoretically have the potential to outperform the shallow ones. However, the existing empirical asset pricing literature provides strong benchmarks for shallow models. Residual learning allows neural network models in asset pricing to go deeper by preserving and refining their shallow counterparts. The out-of-sample Sharpe ratio for value-weighted long-short portfolios of deep residual models (2.07) is higher than that for the corresponding shallow ones (1.92) and more than twice that of the deep feedforward models (0.89). We sh

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Capital asset pricing model, Residual, Consumption-based capital asset pricing model, Asset (computer security), Arbitrage pricing theory, Econometrics

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange