Results 121 to 130 of about 109,032 (273)

A Deep Learning Framework for Forecasting Medium‐Term Covariance in Multiasset Portfolios

Journal of Forecasting, EarlyView.
ABSTRACT Forecasting the covariance matrix of asset returns is central to portfolio construction, risk management, and asset pricing. However, most existing models struggle at medium‐term horizons, several weeks to months, where shifting market regimes and slower dynamics prevail.
Pedro Reis, Ana Paula Serra, João Gama
wiley   +1 more source

Enhancing federated learning for IoT-based anomaly detection: A reputation-based client selection approach

Alexandria Engineering Journal
Federated Learning (FL) enables collaborative model training across decentralized, privacy-sensitive environments but often suffers from slow convergence, unbalanced client selection, and non‑IID data challenges.
Maha Jawad Alfadhil, Ali Baydoun, Moutaz Alazab, Hafeez Ur Rehman, Jihad Al Jaam, Sumaya Ali S.A. Al-Maadeed   +5 more
doaj   +1 more source

Coherent Forecasting of Realized Volatility

Journal of Forecasting, EarlyView.
ABSTRACT The QLIKE loss function is the stylized favorite of the literature on volatility forecasting when it comes to out‐of‐sample evaluation and the state of the art model for realized volatility (RV) forecasting is the HAR model, which minimizes the squared error loss for in‐sample estimation of the parameters.
Marius Puke, Karsten Schweikert
wiley   +1 more source

An Overview of Autonomous Connection Establishment Methods in Peer-to-Peer Deep Learning

IEEE Access
The exchange of model parameters between peers is critical in peer-to-peer deep learning. Historically, connections between agents were assigned randomly based on network topology.
Robert Sajina, Nikola Tankovic, Ivo Ipsic   +2 more
doaj   +1 more source

Forecasting House Prices: The Role of Market Interconnectedness

Journal of Forecasting, EarlyView.
ABSTRACT While the existing research uncovers interconnections between various housing markets, it largely ignores the question of whether such linkages can improve house price predictions. To address this issue, we proceed in two steps. First, we forecast disaggregated house price growth rates from Australia and China to determine whether ...
Zac Chen, George Milunovich, Shuping Shi, Ben Wang   +3 more
wiley   +1 more source

Oil Futures Prices, Inflation Expectations, and Bond Risk Premiums

Journal of Futures Markets, EarlyView.
ABSTRACT By decomposing West Texas Intermediate futures price changes into structural supply and demand shocks, this paper shows that dissecting the oil price significantly improves inflation forecasts. Empirically, demand‐driven shocks predict a negative real bond risk premium but a positive inflation risk premium; these opposing effects result in an ...
Haibo Jiang
wiley   +1 more source

Gray Learning From Non-IID Data With Out-of-Distribution Samples

IEEE Transactions on Neural Networks and Learning Systems
The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be in-distribution, while samples that deviate semantically would be identified as out-of-distribution and excluded during the ...
Zhilin Zhao, Longbing Cao, Chang-Dong Wang   +2 more
openaire   +3 more sources

Effect of Prudential Policies on Sovereign Bond Markets: Evidence From the ASEAN‐4 Countries

International Journal of Finance &Economics, EarlyView.
ABSTRACT This paper examines the effects of prudential policies on the sovereign vulnerability of ASEAN‐4 countries. We measure sovereign vulnerability within the network connectedness of sovereign bonds between ASEAN‐4 countries (Indonesia, Malaysia, the Philippines and Thailand) and six other countries (the US, the UK, the European Union, China ...
Joshua Aizenman, Gazi Salah Uddin, Tianqi Luo, Ranadeva Jayasekera, Donghyun Park   +4 more
wiley   +1 more source

Chromatic PAC-Bayes Bounds for Non-IID Data

, 2009
Pac-Bayes bounds are among the most accurate generalization bounds for classifiers learned with \iid data, and it is particularly so for margin classifiers. However, there are many practical cases where the training data show some dependencies and where the traditional \iid assumption does not apply.
Ralaivola, Liva, Szafranski, Marie, Stempfel, Guillaume   +2 more
openaire   +1 more source

Climate Change Laws and European Stock Markets: An Event Analysis

International Journal of Finance &Economics, EarlyView.
ABSTRACT Under the context of the climate change we assess the impact of EU's legislative initiative on European stock markets. Specifically, we focus on its impact on energy and Environmental Social Governance (ESG) sectors for equity returns and volatility for a representative basket of EU countries (participating also in Eurozone) as well as ...
Theodoros Bratis, Georgios P. Kouretas, Evangelos Salachas   +2 more
wiley   +1 more source