Newest papers

From Economic Explanation to Performance Improvement in Machine-Learning Portfolios

Yunqi Liang, Stefan Zohren, Mihai Cucuringu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.15144 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Untuk memperluas pentingnya fitur model konvensional ke hasil dan keputusan portofolio yang signifikan secara ekonomi, kami mengusulkan kerangka kerja atribusi-proliferasi tingkat pertama lokal yang memetakan eksposur fitur allocation-function ke sensitivitas lokal dari metrik kinerja portofolio berturut-turut. Kami menghubungkan atribusi-proliferasi ke nilai Shapley yang didefinisikan secara langsung untuk tujuan portofolio dan menghasilkan kesimpulan statistik untuk atribusi rasio Sharpe. Intervensi eksposur fitur yang dipandu oleh atribusi yang dihasilkan memungkinkan penyesuaian pasca pelatihan, menerjemahkan penjelasan portfolio-metrik menjadi keputusan out-of-sample tanpa melatih kembali model allocation yang mendasarinya. Kami juga memperkenalkan stabilisasi waktu dan rata-rata cross-model sebagai mekanisme regulasi komplementer.

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

Abstract

To extend conventional model-level feature importance to economically meaningful portfolio outcomes and decisions, we propose a local first-order attribution-propagation framework that maps allocation-function feature exposures to local sensitivities of sequential portfolio performance metrics. We relate the propagated attributions to Shapley values defined directly for portfolio objectives and derive statistical inference for Sharpe-ratio attributions. The resulting attribution-guided feature-exposure intervention enables post-training adaptation, translating portfolio-metric explanations into out-of-sample decisions without retraining the underlying allocation model. We further introduce temporal stabilisation and cross-model averaging as complementary regularisation mechanisms. Empirically, the interventions yield statistically significant improvements in net Sharpe ratios across different model classes.

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

Topics: Portfolio, Econometrics, Sharpe ratio, Inference, Feature (linguistics), Computer science

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