User profiles for Igor Halperin
 | Igor HalperinFidelity Verified email at fmr.com Cited by 1880 |
[BOOK][B] Machine learning in finance
MF Dixon, I Halperin, P Bilokon - 2020 - Springer
… Igor Halperin Tandon School of Engineering New York University Brooklyn, NY, USA …
Igor Halperin is a Research Professor in Financial Engineering at NYU and an AI Research …
Igor Halperin is a Research Professor in Financial Engineering at NYU and an AI Research …
The QLBS Q-Learner goes NuQLear: fitted Q iteration, inverse RL, and option portfolios
I Halperin - Quantitative Finance, 2019 - Taylor & Francis
The QLBS model is a discrete-time option hedging and pricing model that is based on
Dynamic Programming (DP) and Reinforcement Learning (RL). It combines the famous Q-…
Dynamic Programming (DP) and Reinforcement Learning (RL). It combines the famous Q-…
[BOOK][B] Reinforcement Learning and Stochastic Optimization: A Unified Framework for Sequential Decisions: by Warren B. Powell (ed.), Wiley (2022). Hardback. ISBN …
I Halperin - 2022 - Taylor & Francis
What is reinforcement learning? How is reinforcement learning different from stochastic
optimization? And finally, can it be used for applications to quantitative finance for my current or …
optimization? And finally, can it be used for applications to quantitative finance for my current or …
BSLP: Markovian bivariate spread-loss model for portfolio credit derivatives
M Arnsdorf, I Halperin - arXiv preprint arXiv:0901.3398, 2009 - arxiv.org
BSLP is a two-dimensional dynamic model of interacting portfolio-level loss and spread (more
exactly, loss intensity) processes. The model is similar to the top-down HJM-like …
exactly, loss intensity) processes. The model is similar to the top-down HJM-like …
Qlbs: Q-learner in the black-scholes (-merton) worlds
I Halperin - arXiv preprint arXiv:1712.04609, 2017 - arxiv.org
This paper presents a discrete-time option pricing model that is rooted in Reinforcement
Learning (RL), and more specifically in the famous Q-Learning method of RL. We construct a risk…
Learning (RL), and more specifically in the famous Q-Learning method of RL. We construct a risk…
Soft contribution to the pion form factor from light-cone QCD sum rules
V Braun, I Halperin - Physics Letters B, 1994 - Elsevier
We propose a simple method to calculate the pion form factor at not very large momentum
transfers, which combines the technique of the QCD sum rules with the description of the pion …
transfers, which combines the technique of the QCD sum rules with the description of the pion …
G-learner and girl: Goal based wealth management with reinforcement learning
M Dixon, I Halperin - arXiv preprint arXiv:2002.10990, 2020 - arxiv.org
We present a reinforcement learning approach to goal based wealth management problems
such as optimization of retirement plans or target dated funds. In such problems, an investor …
such as optimization of retirement plans or target dated funds. In such problems, an investor …
decay as a unique probe of the meson
I Halperin, A Zhitnitsky - Physical Review D, 1997 - APS
A theory of the B→ K η′ decay is proposed. It is based on the Cabibbo-favored b→ c cs
process followed by a direct materialization of the cc pair into the η′. This mechanism works …
process followed by a direct materialization of the cc pair into the η′. This mechanism works …
The four horsemen of machine learning in finance
MF Dixon, I Halperin - Available at SSRN 3453564, 2019 - papers.ssrn.com
Abstract Machine Learning has been used in the financial services industry for over 40 years,
yet it is only in recent years that it has become more pervasive across investment …
yet it is only in recent years that it has become more pervasive across investment …
Why is the Decay Width So Large?
I Halperin, A Zhitnitsky - Physical Review Letters, 1998 - APS
A new mechanism for the observed inclusive B→ η′ X decay is suggested. We argue that
the dominant contribution to this amplitude is due to the Cabibbo favored b→ c cs process …
the dominant contribution to this amplitude is due to the Cabibbo favored b→ c cs process …