Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Frank J. Fabozzi"'
Publikováno v:
European Journal of Operational Research. 297:1162-1177
The recovery rate on defaulted corporate bonds has a time-varying distribution, a topic that has received limited attention in the literature. We apply machine learning approaches for intertemporal analysis of U.S. corporate bonds’ recovery rates.
Autor:
Sergio Focardi, Frank J. Fabozzi
Publikováno v:
SSRN Electronic Journal.
Publikováno v:
International Journal of Forecasting. 38:240-252
This study evaluates a wide range of machine learning techniques such as deep learning, boosting, and support vector regression to predict the collection rate of more than 65,000 defaulted consumer credits from the telecommunications sector that were
Publikováno v:
Emerging Markets Review. 54:100995
Autor:
Frank J. Fabozzi, Suprita Vohra
Publikováno v:
Journal of International Money and Finance. 96:130-146
We analyze the effectiveness of developed and emerging market foreign-exchange options in international portfolios as a complement to forwards for actively managing portfolio currency risks under the behavioral framework. Although prior research find
Publikováno v:
Finance Research Letters. 28:165-170
Several studies have investigated whether there is undervaluation of sin stocks. This undervaluation, it is argued, results in superior sin stock returns compared to non-sin stock returns. Empirical results are mixed. In contrast to the empirical wor
Publikováno v:
Finance Research Letters. 28:185-190
We extend the classical Cox–Ross–Rubinstein binomial model in two ways. We first develop a binomial model with time-dependent parameters that equate all moments of the pricing tree increments with the corresponding moments of the increments of th
Publikováno v:
SSRN Electronic Journal.
Publikováno v:
SSRN Electronic Journal.
We study whether mortgage debt obtained from licensed financial institutions and informal home loans obtained from private lending have differing impacts on stock ownership. Using the China Household Finance Survey data, we show that the two forms of
Incorporating Financial News for Forecasting Bitcoin Prices Based on Long Short-Term Memory Networks
Publikováno v:
SSRN Electronic Journal.
In this paper we investigate how a deep learning machine learning model can be applied to improve Bitcoin price forecasting and trading by incorporating unstructured information from financial news. The two-stage model we propose outperforms other ma